CN119945495A

CN119945495A - Communication method, device and medium based on scalable decellularized MIMO system

Info

Publication number: CN119945495A
Application number: CN202510091749.XA
Authority: CN
Inventors: 张钺; 廖漩
Original assignee: Shantou University
Current assignee: Shantou University
Priority date: 2025-01-21
Filing date: 2025-01-21
Publication date: 2025-05-06

Abstract

The present application discloses a communication method, device and medium based on a scalable decellularized MIMO system, and relates to the field of communication technology. The communication method based on a scalable decellularized MIMO system includes: determining a first target access terminal through large-scale fading information between a user terminal and multiple access terminals, then the user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association, on this basis, the user terminal determines a second target access terminal according to its own service demand information, then the user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user that can cancel the association, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more. By performing the above operations, the service quality of the user is improved.

Description

Communication method, equipment and medium based on extensible cellular MIMO system

Technical Field

The present application relates to the field of communications technologies, and in particular, to a communication method, device, and medium based on an extensible cellular MIMO system.

Background

The scalable de-cellular large-scale Multiple Input Multiple Output (MIMO) system is a new wireless communication architecture that can achieve more reliable coverage and provide stable quality of service to users due to its Gao Hong diversity gain, ideal propagation conditions, and channel hardening effects.

In the cellular MIMO system in the related art, all access points are connected to a single central processing unit, and all access points serve all users together, so that the signaling overhead and the computational complexity of the front end increase linearly with the increase of the number of users, and meanwhile, it cannot be ensured that the users of each access network can continuously obtain the service of the access point, and there is a risk that the users exit the network halfway.

Disclosure of Invention

The embodiment of the application mainly aims to provide a communication method, equipment and medium based on an extensible cellular MIMO system, aiming at dynamically selecting the most suitable access point for each user to provide service so as to improve the service quality of the user.

To achieve the above object, an aspect of an embodiment of the present application provides a communication method based on a scalable cellular MIMO system, including the following steps:

the user terminal determines a first target access terminal according to the large-scale fading information between the user terminal and the plurality of access terminals;

The user end establishes service association with the first target access end, and the user end is determined by the first target access end to be a user which cannot be in un-association;

The user terminal determines a second target access terminal according to the self service demand information;

the user end establishes service association with the second target access end, and the user end is determined by the second target access end to be a user which can be disassociated;

the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

In some embodiments, the method further comprises:

the access terminal jointly optimizes the total transmission power and downlink power distribution of the access terminal through a power optimization model according to the acquired large-scale fading information between the access terminal and the served user terminal;

Determining the downlink transmission power of the access terminal according to the total transmission power and the downlink power distribution;

The access terminal comprises the first target access terminal and/or the second target access terminal, and the power optimization model is obtained through training based on a convolutional neural network.

In some embodiments, the power optimization model includes a residual network-based stackable feature extraction network and 2 parallel output networks, the training step of the power optimization model comprising:

determining an input tensor according to the acquired large-scale fading information, wherein the dimension of the input tensor is determined by the maximum service user number of a communication system and the number of access terminals connected with an edge processor;

inputting the input tensor into the feature extraction network to obtain large-scale fading information features;

inputting the large-scale fading information characteristics into the convolutional neural network, and obtaining a total transmission power decision tensor and a downlink power allocation decision tensor of an access terminal through the parallel output network;

And optimizing model parameters based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power distribution decision tensor, and completing training.

In some embodiments, the determining the downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation includes:

and determining the downlink transmission power of the access terminal according to the total transmission power decision tensor, the downlink power distribution decision tensor and the maximum transmission power of the access terminal.

In some embodiments, the access terminal includes a disassociatable user, and the user terminal determines a first target access terminal according to the large-scale fading information between the plurality of access terminals, including:

The user terminal determines large-scale fading coefficients between the user terminal and a plurality of access terminals, determines the access terminal with the largest large-scale fading coefficient as a first access terminal and sends an association request;

If the number of the user terminals served by the first access terminal is smaller than the maximum number of the serviceable users, receiving an association request sent by the user terminal, and determining the first access terminal as a first target access terminal;

If the number of the user terminals served by the first access terminal is equal to the maximum number of the users which can be served and the first access terminal has the users which can be disassociated, controlling the first access terminal to cancel the association of the associated users corresponding to the minimum maximum scale fading coefficient under the condition that the large scale fading coefficient between the user terminal and the first access terminal is larger than the minimum large scale fading coefficient of the users which can be disassociated, receiving the association request sent by the user terminal, and determining the first access terminal as a first target access terminal;

If the first access terminal does not have the user which can be disassociated, the user terminal determines the access terminal with the second largest large-scale fading coefficient as a new first access terminal and sends an association request.

In some embodiments, the determining, by the ue, the second target access according to the self service requirement information includes:

the user terminal determines a large-scale fading coefficient between the user terminal and a plurality of access terminals, and determines the access terminal with the large-scale fading coefficient larger than or equal to the self service demand information as a second access terminal;

The user terminal sends an association request to all the second access terminals;

If the number of the user terminals served by the second access terminal is smaller than the maximum number of the serviceable users, receiving an association request sent by the user terminal, and determining the second access terminal as a second target access terminal;

And if the number of the user terminals served by the second access terminal is equal to the maximum number of the users which can be served and the second access terminal has the users which can be disassociated, controlling the second access terminal to cancel the association of the associated users corresponding to the minimum maximum scale fading coefficient under the condition that the large scale fading coefficient between the user terminal and the second access terminal is larger than the minimum maximum scale fading coefficient of the users which can be disassociated, receiving the association request sent by the user terminal, and determining the second access terminal as a second target access terminal.

In order to achieve the above object, another aspect of the embodiments of the present application provides a communication method based on an expandable cellular MIMO system, which is applied to a user terminal, and the communication method based on the expandable cellular MIMO system includes the following steps:

Determining a large-scale fading coefficient between the access terminal and a plurality of access terminals, determining the access terminal with the largest large-scale fading coefficient as a first access terminal, and sending an association request;

under the condition that an association-allowing message sent by the first access terminal is received, the first access terminal is determined to be a first target access terminal, wherein the first access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users which can be disassociated and a competition mechanism;

a user establishing service association with the first target access terminal and being determined by the first target access terminal as non-associable;

Determining an access terminal with the large-scale fading coefficient larger than or equal to the self service demand information as a second access terminal;

Sending association requests to all the second access terminals;

Under the condition that an association-allowing message sent by the second access terminal is received, the second access terminal is determined to be a second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users which can be disassociated and a competition mechanism;

Establishing service association with the second target access terminal and determining the second target access terminal as a user capable of being disassociated;

In order to achieve the above object, another aspect of the embodiments of the present application provides a communication method based on an expandable cellular MIMO system, which is applied to an access terminal, and the communication method based on the expandable cellular MIMO system includes the following steps:

Receiving an association request sent by a user terminal, wherein the association request comprises a corresponding large-scale fading coefficient;

Determining whether to provide associated service for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of unassociated users and a competition mechanism;

According to the obtained large-scale fading information between the associated user terminal and the power optimization model, the total transmission power and the downlink power distribution of the user terminal are jointly optimized;

determining a downlink transmission power from the total transmission power and the downlink power allocation;

The access terminals comprise first target access terminals and/or second target access terminals, the number of the first target access terminals is 1, the number of the second target access terminals is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

To achieve the above object, another aspect of the embodiments of the present application provides an electronic device, which includes a memory storing a computer program and a processor implementing the above method when executing the computer program.

To achieve the above object, another aspect of the embodiments of the present application proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-mentioned method.

The embodiment of the application at least comprises the following beneficial effects:

The application provides a communication method, equipment and medium based on an extensible cellular MIMO system, wherein a first target access end is determined through large-scale fading information between a user end and a plurality of access ends, then the user end and the first target access end establish service association, the user end is determined to be an irrevocable user by the first target access end, on the basis, the user end determines a second target access end according to self service demand information, then the user end and the second target access end establish service association, the user end is determined to be a user capable of canceling the association by the second target access end, the number of the first target access ends is 1, the number of the second target access ends is 1 or more, and therefore the user end determines the first target access end through the large-scale fading information, the service access end can be selected on the macro-scale attenuation characteristic of a signal, the service stability of the user end is ensured, on the basis that the user end and the first target access end establish service association and are determined to be the irrevocable users, the user end can be ensured to withdraw from a service point, the user end can be a service point, the number of the second target access point can be a plurality of target access points can be continuously obtained, the service points can be a service point can be continuously formed, the service point can be a target access point, the user can be dynamically, the service point can be dynamically is provided on the basis of the user, and the user can be dynamically, the user can be provided with the service point, and the user can be stably has a plurality of service points, and the service points can be easily and the service points.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the application will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:

fig. 1 is a schematic diagram of a communication system based on a scalable cellular MIMO system provided by some embodiments of the present application;

fig. 2 is a flow chart of a communication method based on a scalable cellular MIMO system provided by some embodiments of the present application;

Fig. 3 is a schematic diagram of a system architecture based on a first phase association of a scalable cellular MIMO system provided by some embodiments of the present application;

fig. 4 is a schematic system architecture diagram of a second phase association based on a scalable cellular MIMO system provided by some embodiments of the present application;

Fig. 5 is a schematic diagram of a communication flow based on a scalable cellular MIMO system provided by some embodiments of the present application;

Fig. 6 is a block schematic diagram of a communication device based on an extensible cellular MIMO system provided by some embodiments of the present application;

fig. 7 is a block schematic diagram of another communication device based on an extensible cellular MIMO system provided in accordance with some embodiments of the application;

fig. 8 is a schematic diagram of a hardware architecture for communication based on a scalable cellular MIMO system, provided by some embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be appreciated that reference herein to "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments. The implementations described in the following exemplary embodiments do not represent all implementations consistent with embodiments of the application, but are merely examples of apparatuses and methods consistent with aspects of embodiments of the application as detailed in the accompanying claims.

It is to be understood that the terms "first," "second," and the like, as used herein, may be used to describe various concepts, but are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of embodiments of the present application. The words "if", as used herein, may be interpreted as "when" or "in response to a determination", depending on the context.

The terms "at least one", "a plurality", "each", "any" and the like as used herein, at least one includes one, two or more, a plurality includes two or more, each means each of the corresponding plurality, and any one means any of the plurality.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to facilitate understanding of the inventive concept, before explaining the embodiments of the present application in detail, the english abbreviations (terms)/related concepts involved in the embodiments of the present application are first explained, and the english abbreviations (terms)/related concepts involved in the embodiments of the present application are applicable to the following explanation.

MIMO (Multiple Input Multiple Output ) is a wireless communication technology that improves the performance and data transmission rate of communications by using multiple antennas at the transmitting and receiving ends. The MIMO technology can transmit a plurality of data streams on the same frequency band, thereby effectively improving spectral efficiency and capacity of a communication system.

Large-scale fading coefficients-in wireless communications, signals are attenuated by factors such as distance increase, obstruction by obstructions, etc., which attenuation is referred to as path loss and can be quantified by a coefficient. Large scale fading coefficients are typically used to describe the average power attenuation of a signal on a macro scale, and are related to factors such as distance between the user and the access point, environment, etc.

Access point in a wireless communication system, an access point (e.g., base station, wi-Fi hotspot, etc.) is a device that is fixed in the network for communicating with mobile user devices.

The de-cellular large-scale MIMO system is a novel wireless communication architecture, and is expected to become an essential component of a sixth generation wireless network because of Gao Hong diversity gain, ideal propagation conditions and channel hardening effect, so that more reliable coverage can be realized, and stable service quality is provided for users. However, in a conventional de-cellular massive multiple-input multiple-output system, all access points are connected to a single central processing unit and all access points serve all users together, which is impractical because the signaling overhead of the front-end and the computational complexity increase linearly with the number of users. Furthermore, in a de-cellular large-scale multiple-input multiple-output system, the system environment is highly susceptible to interference due to the dense distribution of access points and users. Therefore, efficient power allocation is critical to suppressing interference and improving overall system performance.

In the related art, there is a user association technology that combines a user-centric approach with a de-cellular massive multiple-input multiple-output system, where each access point selects a limited number of users to provide services. In addition, there is a downlink power control method based on a fully connected neural network, each model is deployed in an edge processor, and power control tasks can be performed only by using locally collected large-scale fading information.

However, in the related communication architecture, since the access point only selects the user with the optimal channel environment to provide services, and some users with poor channel quality may not obtain the services of the access point, it cannot be guaranteed that each user accessing the network can continuously obtain the services of the access point, which may cause a part of users to lose connection in the communication process, and there is a risk that the users exit the network halfway. In addition, the power control is performed by a machine learning method, and the preparation of training data and the training process of the model require a large amount of computing resources. At the same time, the system is limited by the network design and it is difficult to reach an optimal solution on the downlink power allocation problem. Furthermore, a single model of the method cannot accommodate a scenario in which the number of associated users in the system dynamically changes.

In view of the above, the application provides a communication method, device and medium based on an extensible cellular MIMO system, in the embodiment of the application, a first target access terminal is determined by large-scale fading information between a user terminal and a plurality of access terminals, then the user terminal and the first target access terminal establish service association, the user terminal is determined by the first target access terminal as an irrevocable user, on the basis, the user terminal determines a second target access terminal according to self service demand information, then the user terminal and the second target access terminal establish service association, the user terminal is determined by the second target access terminal as a user capable of canceling the association, wherein the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more, therefore, the user terminal can select the service access terminal on the macro-scale fading characteristics of signals by the large-scale fading information, thereby ensuring the service stability of the user terminal, on the basis that the user terminal and the first target access terminal establish service association and the first target access terminal are determined as irrevocable users, then the user terminal is determined by the first target access terminal is able, the user terminal is able to withdraw from the service demand information, the user terminal is determined by the second target access terminal is able to be able, the service point is able, the user terminal is able to be the service point on the basis, the basis that the user terminal is able to acquire service points, the service points are able to be stably, the service points are able to be dynamically, the user access point is stable, and the user demand is ensured, and the user terminal is based on the user terminal is able, and can be dynamically has access quality is 1, and can be based on the user access point.

The embodiment of the application provides a communication method based on an extensible cellular MIMO system, and relates to the technical field of communication. The method and the device can be applied to the electronic equipment. The electronic device may be a user terminal, or may be an access point or an edge server.

In some embodiments, the terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a car terminal, and the like.

The access point may be, but is not limited to, a macro base station, a micro base station, a pico base station, a distributed access point, massive MIMO, multi-user MIMO, or Beamforming (Beamforming) MIMO, etc.

The edge server can be configured as an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can be configured as a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligence platforms, and the server can also be a node server in a blockchain network.

The application is operational with numerous general purpose or special purpose computer system environments or configurations. Such as a personal computer, a server computer, a hand-held or portable device, a tablet device, a multiprocessor system, a microprocessor-based system, a set top box, a programmable consumer electronics, a network PC, a minicomputer, a mainframe computer, a distributed computing environment that includes any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

It should be noted that, in each specific embodiment of the present application, when related processing is required according to user information, user behavior data, user history data, user location information, and other data related to user identity or characteristics, permission or consent of the user is obtained first, and the collection, use, processing, and the like of the data comply with related laws and regulations and standards. In addition, when the embodiment of the application needs to acquire the sensitive personal information of the user, the independent permission or independent consent of the user is acquired through popup or jump to a confirmation page and the like, and after the independent permission or independent consent of the user is definitely acquired, the necessary relevant data of the user for enabling the embodiment of the application to normally operate is acquired.

Before introducing the communication method of the scalable cellular MIMO system according to the present application, a brief description will be given of a communication system on which the implementation of the communication method according to the present application depends.

Referring to fig. 1, fig. 1 is a schematic diagram of a communication system based on a scalable cellular MIMO system according to some embodiments of the present application. In fig. 1, 2 users are exemplarily shown, where each of the 2 users has a service cluster, and each service cluster includes 3 access points, where the access points may provide services for user 1 or user 2, respectively, and may also provide services for user 1 and user 2 at the same time, and the access points are associated with an edge processor, and perform corresponding computing tasks through the edge processor.

The implementation steps of a communication method based on a scalable cellular MIMO system according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

Referring to fig. 2, fig. 2 is a flowchart of a communication method based on a scalable cellular MIMO system according to some embodiments of the present application. It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order different than that herein.

The method of the embodiment of the application comprises the following steps:

Step 201, a user terminal determines a first target access terminal according to large-scale fading information between the user terminal and a plurality of access terminals;

step 202, a user end establishes service association with a first target access end, and the user end is determined by the first target access end to be a user which cannot be in association;

Step 203, the user terminal determines a second target access terminal according to the self service demand information;

204, establishing service association between the user terminal and the second target access terminal, wherein the user terminal is determined by the second target access terminal as a user capable of canceling the association;

In the steps 201 to 204 shown in the embodiment of the present application, the first target access terminal is determined through the large-scale fading information, so that the service access terminal can be selected on the macro-scale fading characteristic of the signal, thereby ensuring the service stability of the user terminal, on the basis that the user terminal establishes a service association with the first target access terminal and is determined as an irrevocable user by the first target access terminal, the user terminal is ensured to obtain continuous stable service of one access point, avoiding the risk that the access terminal exits the network halfway, on the basis, the user terminal determines the second target access terminal according to the service requirement information thereof, thereby expanding the service quality according to the service requirement thereof to the access points of the service thereof, and further forming the service clusters of the access points thereof, namely, the number of the second target access terminals is 1 or more, thereby ensuring that each user terminal dynamically selects one or more suitable access points to provide the service, and further improving the service quality of the user.

A specific implementation of each of the above steps is described below.

In step 201, the user terminal determines a first target access terminal according to the large-scale fading information between the user terminal and the plurality of access terminals.

Referring to fig. 3, in an actual system, a user (a user end) periodically transmits a synchronization signal, and an access point (an access end) can locally calculate a large-scale fading coefficient of each user according to the received signal strength (it should be understood that the user end can also calculate and correspond to the large-scale fading coefficient of the access point according to the received broadcast information). Let the number of access points in the communication system be M, and the set of access points beFor the mth access point, the set of users served by it is defined asWherein the method comprises the steps ofWhether the user is served by the access point may be determined by the large-scale fading information. The method proposed by the embodiment of the present application may consist of two phases, where the first phase is first introduced, namely, in the first phase, at least one access point is allocated to each user in the system to ensure that its basic service requirements are met.

Alternatively, the large-scale fading information may include a large-scale fading coefficient (path loss), shadow fading, penetration loss, or received signal strength, etc., but is not limited thereto.

Illustratively, the user side may measure the large-scale fading coefficient from a periodically broadcasted synchronization signal in the communication system, where the periodically broadcasted synchronization signal is present in a standard of the cellular network, such as a primary synchronization signal and a secondary synchronization signal in 5G. It can be understood that the ue receives broadcast signals sent by the multiple access terminals, so that large-scale fading information between the ue and the multiple access terminals can be calculated, on the basis of the large-scale fading information, the ue selects the access point m _k with the largest large-scale fading coefficient to send an association request, and determines the access point m _k as the first target access terminal when receiving a message that allows association and returns from the access point m _k.

In some embodiments, the access terminal includes a disassociatable user, and the user terminal may determine the first target access terminal based on the large-scale fading information with the plurality of access terminals. The method comprises the steps of determining a large-scale fading coefficient between a user terminal and a plurality of access terminals, determining the access terminal with the largest large-scale fading coefficient as a first access terminal and sending an association request, receiving the association request sent by the user terminal if the number of the user terminals served by the first access terminal is smaller than the maximum number of serviceable users, determining the first access terminal as a first target access terminal, determining the first access terminal as a new access terminal with a second large-scale fading coefficient if the number of the user terminals served by the first access terminal is equal to the maximum number of serviceable users and the first access terminal has a user capable of being disassociated, and controlling the first access terminal to cancel the association of the associated user corresponding to the smallest large-scale fading coefficient and receiving the association request sent by the user terminal if the number of the user terminals does not have the user capable of being disassociated.

Optionally, in the first phase, for the kth user newly joining the system, first measure its large-scale fading coefficients β _m,k with surrounding neighboring access points, then user k sends an association request to access point m _k with the largest large-scale fading coefficient, where m _k is calculated by:

When the number of users served by the access point m _k is smaller than the maximum number of serviceable users, the association request of the user k is accepted and the association permission information is returned to the user k, and if the number of users served by the access point m _k is equal to the maximum number of serviceable users and the user which can be disassociated exists in the access point m _k, a competition mechanism is triggered at the moment, wherein the mechanism is to ensure that each user newly joining the network can be served. The principle of the contention mechanism is that the access point will disassociate with the user having the smallest macro-scale fading coefficient from the set of users that can cancel the service and then associate with user k (it will be appreciated that the access point will compare the magnitudes of the macro-scale fading coefficients of the requesting user and the user having the smallest macro-scale fading coefficient, and will choose to associate with the requesting user when the macro-scale fading coefficient of the requesting user is greater than the smallest macro-scale fading coefficient of the cancelable services in the access point), and if there is no user in access point m _k that can cancel the association, user k will send an association request to the access point having the largest macro-scale fading coefficient other than access point m _k in the neighboring access points and repeat the above procedure.

The embodiment of the application determines the first target access terminal through the large-scale fading information between the first target access terminal and the plurality of access terminals, can ensure that at least one stable access point of a user serves the first target access terminal, and avoid the risk that the user exits the network halfway.

In step 202, the ue establishes a service association with the first target access terminal, and the ue is determined by the first target access terminal to be a non-disassociatable user.

For example, after the first target access terminal is determined, the user terminal may establish a service association with the first target access terminal, at which time the communication service is provided for the user by the first target access terminal.

It should be understood that, in the technical solution provided in the present application, the users of the access terminal service include two types, namely, a user type of the service that cannot be canceled and a user type of the service that can be canceled.

After the user determines the access terminal as the first target access terminal, at this time, the first target access terminal determines the requested user as a non-disassociatable user. Therefore, at least one stable access point is ensured to serve the user, and the risk that the user exits the network halfway is avoided.

In fig. 3, user 1 and 1 access point determine an associated service, and user 2 and another 1 access point determine an associated service, where the service clusters of user 1 and user 2 each include 1 access point. In this case, the client will further extend its own service cluster.

In step 203, the ue may determine a second target access terminal according to the own service requirement information.

Referring to fig. 4, the service clusters of each user may be further expanded according to the service requirement of each user, so as to optimize the system performance. Wherein the service clusters of each user are formed by two mutually disjoint subsets, wherein a first subset is determined in a first stage of the method, wherein the users are not disassociatable, and a second subset is determined in a second stage of the method, wherein the served users are disassociatable. The method assumes that the processing power of each access point is limited, i.e. each access point can only serve a limited number of users, and therefore has a limit on the maximum number of service users.

It should be understood that there may be multiple access points around the ue, by measuring the large-scale fading information, where there are multiple access points that satisfy the conditions for serving the multiple access points, the ue may determine the access points that satisfy the conditions for serving the multiple access points as the second target access points, and send association requests to all the second target access points.

In some embodiments, a user terminal first determines a large-scale fading coefficient between itself and a plurality of access terminals, determines an access terminal with the large-scale fading coefficient greater than or equal to self service requirement information as a second access terminal, the user terminal sends an association request to all the second access terminals, receives the association request sent by the user terminal if the number of the user terminals served by the second access terminal is smaller than the maximum serviceable user number, determines the second access terminal as a second target access terminal, and determines the second access terminal as the second target access terminal if the number of the user terminals served by the second access terminal is equal to the maximum serviceable user number and the second access terminal has a user capable of canceling association, if the large-scale fading coefficient between the user terminal and the second access terminal is greater than the minimum large-scale fading coefficient of the users capable of canceling association, and receives the association request sent by the user terminal.

Optionally, in the second stage, the user k expands its own access point service cluster according to its own service requirement. User k attempts to select all access points m satisfying β _m,k > epsilon as its service, where epsilon represents the service requirements of each user. If the number of users served by the access point m does not reach the maximum number of user services, the association request of the user k is accepted, and if the number of users served by the access point m reaches the maximum number of user services and there are users which can cancel the association, the competition mechanism is triggered.

Illustratively, the contention mechanism may be that when the large-scale fading coefficient of the user k with the access point m is greater than the user having the smallest large-scale fading coefficient among the disassociatable users, the access point will disassociate with the user having the smallest large-scale fading coefficient among the disassociatable users and establish an association with the user k. The contention mechanism of the second phase is to ensure that each access point will choose users with better channel conditions to provide service.

In fig. 4, the user 1 and 3 access points determine the associated service, and the user 2 and 3 access points determine the associated service, where the service clusters of the user 1 and the user 2 each include 3 access points, and the 3 access points provide communication services for the user 1 and the user 2 respectively. It should be appreciated that in embodiments provided by the present application, there may be access points that provide services to both user 1 and user 2. In this case, a plurality of access points serve the user, so that the service quality of the user can be further improved, and the communication experience and the use satisfaction of the user are improved.

It should be understood that the first stage and the second stage of the method provided by the embodiment of the application are performed separately, and the first stage is performed before the second stage. The first stage completes the operation of the user to initially access the network, and the second stage is to expand the service cluster. In addition, the selection between the user end and the access end is bidirectional, the user can send the association request to all the access points with the large-scale fading coefficients larger than the service requirement, and the access point receiving the association request can decide whether to accept the association request of the user at the local end.

In the embodiment of the application, the first stage is to finish the operation of the initial access system of the user, and the second stage is to further optimize the service quality of the user. The period of operation of the second phase may be determined by the complexity of the method, wherein the time complexity is related to the number M of access points in the communication system and the maximum number of accessible users of the access points, and the operation period is related to the number M of access points in the system, since the maximum number of accessible users is usually a constant value, the greater the number of access points, the longer the operation period.

According to the embodiment of the application, the second target access terminal is determined through the service demand information of the user terminal, so that the service cluster of each user can be further expanded according to the service demand of the user, the service quality of the user is improved, and the overall performance of the communication system is further optimized.

The embodiment of the application can dynamically select the most suitable access point to provide service for each user by introducing a competition mechanism in the user association method and comprehensively considering the user service requirement and the access point workload, and only needs the local terminal to select whether to associate with the request user according to the access user condition per se in the whole association process, thereby further simplifying the calculation flow, reducing the signaling cost and saving the calculation resources.

In step 204, the ue establishes a service association with the second target access terminal, where the ue is determined by the second target access terminal to be a user capable of being disassociated, and the number of the first target access terminals is 1, and the number of the second target access terminals is 1 or more.

For example, after the second target access terminal is determined, the user terminal may establish a service association with the second target access terminal, at which time the communication service is provided for the user by the second target access terminal.

The second target access terminal is typically a plurality, such as 2, 3 or 5, and the present application is not limited in this regard.

The user terminal establishes service association with a plurality of second target access terminals, so that the range of access points serving the user terminal can be enlarged, namely, an access point cluster serving the user terminal is established, wherein each access terminal in the cluster serves the user.

The plurality of access points may serve one user, for example, by joint transmission, or may be implemented by cross-site carrier aggregation, cooperative beamforming, or cooperative multipoint access, which is not limited in this regard by the present application.

After the user determines the access terminal as the second target access terminal, at this time, the second target access terminal determines the requested user as a disassociatable user. Therefore, more users in the system are guaranteed to obtain better service, and the performance of the communication system is further improved.

By the method, the service cluster of the user can comprise one access point with the largest scale fading selected for the user in the first stage and the access point meeting the service requirement of the user in the second stage. When the user position is fixed, the cluster is fixed in the system and does not change dynamically, and when the user position moves, the wireless channel environment of the user also changes, so that the large-scale fading coefficient also changes, on the basis, when the change is larger than a preset threshold value, the first-stage and/or second-stage association operation can be triggered again, and the specific triggering of which stage can be judged according to the preset threshold value, and it is understood that after the first-stage association operation is triggered again, the second-stage association operation is triggered again, and unless the comprehensive evaluation is carried out, the service effect provided by the service cluster of the user can meet the current requirement of the user.

In some embodiments of the present application, the communication method based on the scalable cellular MIMO system further includes that the access terminal jointly optimizes its own total transmission power and downlink power allocation through a power optimization model according to the acquired large-scale fading information between the access terminal and the served user terminal, and determines the downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation, where the access terminal includes a first target access terminal and/or a second target access terminal, and the power optimization model is obtained through training based on a convolutional neural network.

According to the service relation between the access point and the user determined by the user association algorithm, each edge processor can complete the task of power distribution to all users in the system only by relying on the locally collected large-scale fading information. Meanwhile, each access point performs a power allocation operation only for users it serves. Therefore, the signaling overhead is reduced as much as possible, and the computing resource is saved. The power control algorithm can take the maximized downlink communication rate as an optimization target, has instantaneity and robustness, and can flexibly adapt to system scenes of different associated user numbers.

The power optimization method can be based on convolutional neural network design, and jointly optimize the total transmission power of the access point and the power allocation strategy of the downlink. The power optimization model is deployed in the edge processor, and aims to perform efficient power allocation tasks by learning and optimizing with the aim of maximizing long-term downlink data rate in the whole communication network range.

Optionally, the power optimization model includes a stackable feature extraction network based on a residual network and 2 parallel output networks, and the training step of the power optimization model may be:

determining an input tensor according to the acquired large-scale fading information, wherein the dimension of the input tensor is determined by the maximum service user number of the communication system and the number of access terminals connected with the edge processor;

inputting the input tensor into the feature extraction network to obtain the large-scale fading information features;

inputting the large-scale fading information characteristics into a convolutional neural network, and obtaining a total transmission power decision tensor and a downlink power allocation decision tensor of an access terminal through a parallel output network;

And optimizing model parameters based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor, and completing training.

Illustratively, large scale fading information collected locally in the edge processor may be processed by a stackable feature extraction network based residual network. It should be appreciated that the communication system includes a plurality of edge processors, and that the large-scale fading information collected by the nth edge processor may be modeled as a tensorWhere M _n and T represent the number of access points and the number of input samples, respectively, to which the edge processor n is connected. The operation of the feature extraction network is as follows:

C=ConvBlock(B_n;{W,b});

Wherein ConvBlock denotes a feature extraction network, W and b denote weights and bias parameters in the feature extraction network, respectively, and C denotes an output value of the feature extraction network, which can be regarded as a feature of the extracted large-scale fading information. It should be understood that the network proposed by the present application is constructed based on the maximum number of users in the system, and the maximum number of users K can be flexibly set according to the configuration of the actual system, and in general, the configuration of the system is determined, and the maximum number of users is also determined, so that the configuration of the neural network in the present application is also determined.

In the power optimization model, the data dimension for each process is fixed at M _n K, where M _n and K are typically constants in the case of network system architecture determination.

In an actual communication system architecture, the embodiment of the application adopts zero filling operation of a convolutional neural network in the process of running calculation, so that the input and output of the network can adapt to the number of associated users which dynamically change in the system. Thereby increasing the flexibility of distributed downlink power allocation. Therefore, on the basis, the scenes with different numbers of associated users can be efficiently processed by only single training, and the power distribution requirement in a dynamic network environment is met.

In the practical model training process, the training is not needed for all conditions, and only the maximum number of users can be accommodated in the system for training, so that the training can process scenes with different numbers of associated users, the data resources are saved, the data under the scenes associated with various users are not needed to be collected, the training times are reduced, and the computing resources are further saved.

On the basis, the embodiment of the application learns two decision variables through two parallel output networks, which are respectively used for optimizing the total transmitting power and the downlink power distribution of the access point. The operation of the output network can be expressed as:

Y_P＝δ(FCB(C);θ_P)

Y_η＝δ(FCB(C);θ_η);

Wherein FCB represents the output layer, δ is an activation function for normalizing the output of the neural network to satisfy the power control constraint such that the total power of each power allocation does not exceed the maximum transmission power of each access point, θ represents the set of weights and offsets in the network, C represents the output value of the feature extraction network, subscripts P and η are used to refer to two types of parameters in the network, respectively, and Y represents the output tensor of the output network.

The dimensions of the output tensors are respectivelyAnd (3) withThat is, the output tensor dimension of the output layer is also designed to be constant, which means that the neural network provided by the application can effectively solve the problem that the input and output dimensions of the model are variable due to the change of the number of associated users in the system. Through the design, the neural network can flexibly adapt to dynamically-changed user association scenes on the premise of fixed input and output dimensions.

And optimizing model parameters based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor.

Illustratively, the neural network may be trained by an unsupervised learning strategy in order to maximize the total transmission rate of the network-wide downlink. Wherein the loss function can be expressed as:

In the formula, Θ is the total parameter learned by the neural network, and R _k is the downlink transmission rate of user k. In the training process, a gradient descent strategy is adopted for parameter updating.

And thus completing the training of the power optimization model.

In some embodiments, the downlink transmission power of the access terminal may be determined by a total transmission power decision tensor, a downlink power allocation decision tensor, a maximum transmission power of the access terminal.

Illustratively, the downlink transmission power of the access terminal may be expressed as:

P=diag(P_maxY_P)·Y_η;

In the above formula, P _max represents the maximum transmission power of each access point, diag (·) can generate a diagonal matrix with input vector as diagonal element, and the power control task is completed according to the operation between the maximum transmission power of each access point and decision variables of downlink power allocation.

The embodiment of the application can finish operation by adopting a distributed computing method and only relying on information locally collected by an access point without centralized processing, simplifies the computing flow, and cooperatively optimizes the total transmission power and downlink power distribution of the access point to obtain the optimal solution of the power control problem, thereby improving the network performance.

The application also provides a communication method based on the scalable cellular MIMO system, which is applied to the user terminal.

The communication method based on the scalable cellular MIMO system applied to the user terminal comprises the following steps:

firstly, determining a large-scale fading coefficient between the access terminal and a plurality of access terminals, determining the access terminal with the largest large-scale fading coefficient as a first access terminal, and sending an association request;

Under the condition that the user end receives the message of accepting association sent by the first access end, the first access end is determined to be a first target access end, wherein the first access end can determine whether to provide association service for the user end according to the maximum number of serviceable users, the number of unassociated users and a competition mechanism (as shown in the embodiment, the trigger operation of the competition mechanism may be included);

then, the user end establishes service association with the first target access end and is determined by the first target access end as a user which can not be in the association;

determining an access terminal with the large-scale fading coefficient larger than or equal to the service demand information of the access terminal as a second access terminal;

sending association requests to all second access terminals;

Under the condition that an association-allowed message sent by a second access terminal is received, the second access terminal is determined to be a second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of unassociated users and a competition mechanism (as shown in the embodiment, the triggering operation of the competition mechanism may be included);

Establishing service association with a second target access terminal and determining the service association as a user capable of being disassociated by the second target access terminal;

In an exemplary embodiment, when a user newly joins a communication network, the user may first measure large-scale fading information between the user and surrounding access points, and then send an association request to the largest large-scale fading information, after determining to perform association, the user may further expand the number of access points served by the user to the number of access points, that is, may send association requests to a plurality of stations meeting service requirements, and when receiving agreement to associate, the plurality of access points provide communication services for the user, so as to improve service quality of the user.

According to the embodiment of the application, the service cluster consisting of the limited access points is constructed for each user through the user association method, so that the forwarding requirement and the calculation complexity of the system are effectively reduced, and the expandable cellular system is constructed.

The application also provides a communication method based on the extensible cellular MIMO system, which is applied to the access terminal.

The communication method based on the scalable cellular MIMO system applied to the access terminal comprises the following steps:

Firstly, receiving an association request sent by a user terminal, wherein the association request comprises a corresponding large-scale fading coefficient;

determining whether to provide associated service for the user side according to the large-scale fading coefficient, the maximum number of serviceable users, the number of unassociated users and the competition mechanism;

Determining downlink transmission power based on the total transmission power and the downlink power allocation;

In an actual communication system, the access point locally calculates a large-scale fading coefficient for each user based on the received signal strength. Users of access point services can be divided into two types, one of which is a non-cancelable service user type and the other is a cancelable service user type.

When the access point receives the association request sent by the user, the access point firstly inquires whether the number of the users served by the access point is the maximum number of the users, if the maximum number of the users is not reached yet, the access point receives the association request of the users, if the association request is the first association request after the users access the network, the access point classifies the users into the non-cancelable service types, and if the association request is not the first association request after the users access the network, the access point classifies the users into the cancelable service types.

When the access point receives an association request sent by a user, the access point firstly inquires whether the number of users served by the access point is the maximum number of users, if the maximum number of users is reached and the access point has the user which can be disassociated at the moment, a competition mechanism is started or triggered, and when the large-scale fading information (which can be the large-scale fading coefficient) between the request user and the access point is larger than the user which can be disassociated and has the minimum large-scale fading coefficient, the access point cancels the association with the user which can be disassociated and has the minimum large-scale fading coefficient, and establishes the association with the request user. At this point, the contention mechanism may ensure that each access point will select users with better channel conditions to provide service. If this is the first association request after the user has accessed the network, the access point classifies the user as a non-cancelable service type, and if this is not the first association request after the user has accessed the network, the access point classifies the user as a cancelable service type.

When the access point receives the association request sent by the user, the access point firstly inquires whether the number of users served by the access point is the maximum number of users, and if the maximum number of users is reached and no user which can be de-associated exists at the access point, the access point refuses the association request of the request user.

The access point can also jointly optimize the total transmission power and downlink power distribution of the access point through a power optimization model according to the acquired large-scale fading information between the access point and the associated user terminal. It should be appreciated that in order to conserve and balance computing power resources, power optimization is typically done by the edge processor on the access side to achieve distributed computing.

Each edge processor can complete the task of power distribution to the access terminal side connected with the edge processor only by relying on the locally collected large-scale fading information. Meanwhile, each access terminal performs a power allocation operation only for users served by the access terminal. The power control algorithm takes the maximized downlink communication rate as an optimization target, has instantaneity and robustness, and can flexibly adapt to system scenes of different associated user numbers.

The power control is mainly implemented by a power optimization model, wherein, the training method of the power optimization model can be referred to in the foregoing, and will not be described herein.

After the total transmission power and the downlink power allocation output by the power optimization model are obtained, the downlink transmission power can be determined in combination with the maximum transmission power of each access point, and the specific determination method can refer to the foregoing, which will not be repeated here.

The embodiment of the application creatively introduces double consideration of a competition mechanism and user service requirements in a user association method, combines the workload limitation of the access points, comprehensively analyzes the user requirements and the resource condition of the access points, selects the most suitable access point for each user, constructs a high-efficiency service cluster, cooperatively optimizes the total transmission power of the access points and downlink power distribution through a power optimization model to realize targeted power control, and the trained power optimization model can completely based on locally collected large-scale fading information without additional communication interaction, and can independently complete the operation of associating the users and distributing the power through localized processing by distributed nodes.

The following describes and illustrates the embodiments of the present invention in detail with reference to specific application examples:

Referring to fig. 5, fig. 5 is a schematic diagram of a communication flow based on a scalable cellular MIMO system according to some embodiments of the present application. In fig. 5, when a user k just accesses to a communication network, first sends an association request to a nearby access point with maximum fading information, the access point determines whether to provide an association service for a requesting user according to the condition of its own service user (whether the number of service users reaches the maximum number of service users, whether there are users capable of canceling the service, etc.), if there is an access point providing a service for the requesting user, at this time, an edge processor located at the access point side will perform power control calculation on the access point, and the access point controls its downlink transmission power according to a power control policy and performs channel estimation and coding to provide a communication service for the requesting user. It should be understood that the arrows in fig. 5 represent only a single communication flow direction and do not illustrate the communication flow direction at both ends of the communication. That is, even though the communication flow direction is clarified in fig. 5, signal transmission can be performed in the exactly opposite direction depending on the sender of the signal in the actual communication process.

The implementation of the communication device based on the scalable cellular MIMO system according to the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

For the communication method based on the scalable de-cellular MIMO system provided by the foregoing embodiment, the embodiment of the present application further provides a communication device (may be a user side) based on the scalable de-cellular MIMO system, for implementing the foregoing method, as shown in fig. 6, fig. 6 is a block schematic diagram of a communication device based on the scalable de-cellular MIMO system according to the embodiment of the present application, where the communication device based on the scalable de-cellular MIMO system includes:

The first determining module is used for determining a first target access terminal according to the large-scale fading information between the first determining module and the plurality of access terminals;

the first service association establishing module is used for establishing service association with the first target access terminal, and the user terminal is determined by the first target access terminal to be a user which cannot be in association with the first target access terminal;

the second determining module is used for determining a second target access terminal according to the self service demand information;

The second service association establishing module is used for establishing service association with the second target access terminal, and the user terminal is determined by the second target access terminal to be a user capable of being disassociated;

It can be understood that the content in the above method embodiment is applicable to the embodiment of the present device, and the specific functions implemented by the embodiment of the present device are the same as those of the embodiment of the above method, and the achieved beneficial effects are the same as those of the embodiment of the above method.

For the communication method based on the scalable cellular MIMO system provided by the foregoing embodiment, another communication device (may be an access terminal) based on the scalable cellular MIMO system is further provided in the embodiment of the present application, for implementing the foregoing method, as shown in fig. 7, fig. 7 is a schematic block diagram of another communication device based on the scalable cellular MIMO system according to the embodiment of the present application, where the another communication device based on the scalable cellular MIMO system includes:

The receiving module is used for receiving an association request sent by the user terminal, wherein the association request comprises a corresponding large-scale fading coefficient;

The determining module is used for determining whether to provide associated service for the user terminal according to the large-scale fading coefficient, the maximum number of the users which can be served, the number of the users which can be disassociated and the competition mechanism;

The joint optimization module is used for jointly optimizing the total transmission power and downlink power distribution of the joint optimization module through a power optimization model according to the acquired large-scale fading information between the joint optimization module and the associated user terminal;

a power control module for determining downlink transmission power based on the total transmission power and the downlink power allocation;

Referring to fig. 8, an embodiment of the application also provides an electronic device 800, the electronic device 800 comprising a memory 801, one or more processors 802 (only 1 shown in fig. 8) and a computer program stored on the memory and executable on the processor. The memory 801 is used for storing software programs and units, and the processor 802 executes various functional applications and data processing by running the software programs and units stored in the memory to obtain resources corresponding to the preset events. Optionally, the processor implements the communication method based on the scalable cellular MIMO system by running the computer program stored in the memory.

The memory, as a non-transitory computer readable medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network.

It can be understood that the content in the above method embodiment is applicable to the present electronic device embodiment, and the functions specifically implemented by the present electronic device embodiment are the same as those of the above method embodiment, and the achieved beneficial effects are the same as those of the above method embodiment.

The embodiment of the application also provides a computer readable storage medium, which stores a computer program, and the computer program realizes the communication method based on the scalable cellular MIMO system when being executed by a processor.

It can be understood that the content of the above method embodiment is applicable to the present storage medium embodiment, and the functions of the present storage medium embodiment are the same as those of the above method embodiment, and the achieved beneficial effects are the same as those of the above method embodiment.

Embodiments of the present application also provide a computer program product comprising a computer program capable of implementing the steps of a communication method based on the scalable cellular MIMO system as described above when executed by one or more processors.

It will be appreciated that the foregoing method embodiments are applicable to the computer program product, and the functions of the computer program product embodiment are the same as those of the foregoing method embodiments, and the advantages achieved by the foregoing method embodiments are the same as those achieved by the foregoing method embodiments.

The communication method, the device, the electronic equipment, the medium and the computer program product based on the extensible cellular MIMO system provided by the embodiment of the application are characterized in that the first target access end is determined through large-scale fading information between the user end and a plurality of access ends, then the user end and the first target access end establish service association, the user end is determined to be an irrevocable user by the first target access end, on the basis, the user end establishes service association with the second target access end according to self service demand information, the user end is determined to be a user capable of canceling the association by the second target access end, wherein the number of the first target access ends is 1, the number of the second target access ends is 1 or more, and therefore, the user end can select the service access end on the macro-scale fading characteristic of signals through the large-scale fading information, the service stability of the user end is ensured, on the basis that the user end establishes service association with the first target access end and is determined to be an irrevocable user by the first target access end, the user end is determined to be a plurality of service points which can be a plurality of access points which can be connected with each other, the service point is ensured to be a plurality of service points which can be continued, the service points can be dynamically connected with the user end or the user end, the user can be stably connected to the user end, the user can be provided with the service points, and the service points can be stably on the basis the user demand of the user is ensured, and the user can be dynamically and the user can be stably realized.

The communication method, the device, the electronic equipment, the medium and the computer program product based on the extensible cellular MIMO system provided by the embodiment of the application provide a two-stage user association strategy by introducing a competition mechanism and comprehensively considering the working load of the access point and the user service requirement. In the first stage, a preferred access point is allocated to each user according to the channel quality to ensure that the user obtains basic service, in the second stage, the service cluster is expanded based on the service requirement of the user, meanwhile, the most suitable access point is dynamically selected for the user in the two stages by combining a competition mechanism, and finally, the efficient service cluster is constructed. The method effectively improves the service quality of the user and the resource utilization efficiency of the system. In addition, existing downlink power control methods fail to cooperatively optimize the total transmission power of the access point and the downlink power allocation, and cannot accommodate dynamic changes in the number of associated users in the system. Therefore, the embodiment of the application provides a downlink power control algorithm based on a convolutional neural network. By designing two parallel output networks, the algorithm can optimize both the total transmission power and the downlink power allocation of the access point. More importantly, the application innovatively designs a neural network structure with fixed input/output layer dimension, so that a single neural network can flexibly adapt to system scenes with different associated user numbers under the condition of only one training, and in addition, the method provided by the application is completely based on locally collected large-scale fading information without additional communication interaction. Through the localization process, the distributed node can independently complete the joint user association and power distribution operation.

The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and/or processing capabilities described in connection with a particular device or component may be performed by any other device or component. In addition, while various exemplary implementations and architectures have been described in terms of embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

Certain aspects of the present disclosure are described above with reference to block diagrams and flowchart illustrations of systems, methods, systems and/or computer program products according to example embodiments. It will be understood that one or more blocks of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by executing computer-executable program instructions. Also, some of the blocks in the block diagrams and flowcharts may not need to be performed in the order shown, or may not need to be performed in their entirety, according to some embodiments. In addition, additional components and/or operations beyond those shown in blocks of the block diagrams and flowcharts may be present in some embodiments.

Accordingly, blocks of the block diagrams and flowchart illustrations support combinations of means for performing the specified functions, combinations of elements or steps for performing the specified functions and program instruction means for performing the specified functions. It will also be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, can be implemented by special purpose hardware-based computer systems that perform the specified functions, elements or steps, or combinations of special purpose hardware and computer instructions.

Program modules, applications, etc. described herein may include one or more software components including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functions described herein (e.g., one or more operations of the exemplary methods described herein) to be performed.

The software components may be encoded in any of a variety of programming languages. An exemplary programming language may be a low-level programming language, such as an assembly language associated with a particular hardware architecture and/or operating system platform. Software components including assembly language instructions may need to be converted into executable machine code by an assembler prior to execution by a hardware architecture and/or platform. Another exemplary programming language may be a higher level programming language that may be portable across a variety of architectures. Software components, including higher-level programming languages, may need to be converted to an intermediate representation by an interpreter or compiler before execution. Other examples of programming languages include, but are not limited to, a macro language, a shell or command language, a job control language, a scripting language, a database query or search language, or a report writing language. In one or more exemplary embodiments, a software component containing instructions of one of the programming language examples described above may be executed directly by an operating system or other software component without first converting to another form.

The software components may be stored as files or other data storage constructs. Software components having similar types or related functionality may be stored together, such as in a particular directory, folder, or library. The software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

The embodiments of the present application have been described in detail with reference to the accompanying drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present application.

Claims

1. A communication method based on a scalable decellularized MIMO system, characterized by comprising the following steps:

The user end determines a first target access end according to large-scale fading information between the user end and the plurality of access ends;

The user terminal establishes a service association with the first target access terminal, and the user terminal is determined by the first target access terminal as a user that cannot cancel the association;

The user end determines the second target access end according to its own service demand information;

The user terminal establishes a service association with the second target access terminal, and the user terminal is determined by the second target access terminal as a user from which the association can be cancelled;

2. The communication method based on the scalable decellularized MIMO system according to claim 1, characterized in that the method further comprises:

The access end jointly optimizes its own total transmission power and downlink power allocation through a power optimization model according to the acquired large-scale fading information between the access end and the served user end;

Determining a downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation;

The access end includes the first target access end and/or the second target access end, and the power optimization model is obtained through training based on a convolutional neural network.

3. The communication method based on a scalable decellularized MIMO system according to claim 2, characterized in that the power optimization model comprises a stackable feature extraction network based on a residual network and two parallel output networks, and the training step of the power optimization model comprises:

Determine an input tensor by using the acquired large-scale fading information, wherein the dimension of the input tensor is determined by the maximum number of service users of the communication system and the number of access terminals connected to the edge processor;

Inputting the large-scale fading information feature into the convolutional neural network, and obtaining the total transmission power decision tensor and the downlink power allocation decision tensor of the access terminal itself through the parallel output network;

Based on the large-scale fading information characteristics, the total transmission power decision tensor and the downlink power allocation decision tensor, the model parameters are optimized to complete the training.

4. The communication method based on the scalable decellularized MIMO system according to claim 3, characterized in that the determining the downlink transmission power of the access terminal according to the total transmission power and the downlink power allocation comprises:

The downlink transmission power of the access end is determined by the total transmission power decision tensor, the downlink power allocation decision tensor, and the maximum transmission power of the access end.

5. The communication method based on the scalable decellularized MIMO system according to claim 1, wherein the access terminal includes a user whose association can be cancelled, and the user terminal determines the first target access terminal according to large-scale fading information between the user terminal and multiple access terminals, comprising:

The user end determines the large-scale fading coefficients between itself and the plurality of access ends, determines the access end with the largest large-scale fading coefficient as the first access end and sends an association request;

If the number of user terminals served by the first access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the first access terminal as a first target access terminal;

If the number of user terminals served by the first access terminal is equal to the maximum number of serviceable users and the user whose association can be cancelled exists on the first access terminal, then, if the large-scale fading coefficient between the user terminal and the first access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, control the first access terminal to cancel the association of the associated user corresponding to the minimum large-scale fading coefficient, receive an association request sent by the user terminal, and determine the first access terminal as a first target access terminal;

If there is no user whose association can be cancelled at the first access terminal, the user terminal determines the access terminal with the second largest large-scale fading coefficient as a new first access terminal and sends an association request.

6. The communication method based on the scalable decellularized MIMO system according to claim 1, characterized in that the user terminal determines the second target access terminal according to its own service demand information, comprising:

The user end determines a large-scale fading coefficient between itself and a plurality of access ends, and determines an access end whose large-scale fading coefficient is greater than or equal to its own service demand information as a second access end;

If the number of user terminals served by the second access terminal is less than the maximum number of serviceable users, receiving an association request sent by the user terminal and determining the second access terminal as a second target access terminal;

If the number of user terminals served by the second access terminal is equal to the maximum number of serviceable users and there are users whose association can be cancelled on the second access terminal, then when the large-scale fading coefficient between the user terminal and the second access terminal is greater than the minimum large-scale fading coefficient among the users whose association can be cancelled, the second access terminal is controlled to cancel the association with the associated user corresponding to the minimum large-scale fading coefficient, and an association request sent by the user terminal is received, and the second access terminal is determined as a second target access terminal.

7. A communication method based on a scalable decellularized MIMO system, characterized in that it is applied to a user end, and the communication method based on a scalable decellularized MIMO system comprises the following steps:

Determine a large-scale fading coefficient between itself and a plurality of access terminals, determine the access terminal having the largest large-scale fading coefficient as a first access terminal and send an association request;

In the case of receiving the association permission message sent by the first access terminal, determining the first access terminal as a first target access terminal, wherein the first access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and a competition mechanism;

A user who has established a service association with the first target access terminal and is determined by the first target access terminal as a user who cannot cancel the association;

Determine the access terminal whose large-scale fading coefficient is greater than or equal to its own service demand information as the second access terminal;

Sending an association request to all of the second access terminals;

In the case of receiving the association permission message sent by the second access terminal, determining the second access terminal as the second target access terminal, wherein the second access terminal determines whether to provide association service for the user terminal according to the maximum number of serviceable users, the number of users that can cancel association, and the competition mechanism;

A user who has established a service association with the second target access terminal and is determined by the second target access terminal as a user whose association can be cancelled;

8. A communication method based on a scalable decellularized MIMO system, characterized in that it is applied to an access terminal, and the communication method based on a scalable decellularized MIMO system comprises the following steps:

receiving an association request sent by a user terminal, wherein the association request includes a corresponding large-scale fading coefficient;

Determining whether to provide association service for the user terminal according to the large-scale fading coefficient, the maximum number of serviceable users, the number of users that can be disassociated, and a competition mechanism;

Based on the large-scale fading information obtained between the associated user terminals, the total transmission power and downlink power allocation of the system are jointly optimized through the power optimization model;

determining a downlink transmission power based on the total transmission power and the downlink power allocation;

Among them, the access end includes a first target access end and/or a second target access end, the number of the first target access end is 1, the number of the second target access end is 1 or more, and the power optimization model is obtained through training based on a convolutional neural network.

9. An electronic device, characterized in that the electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the communication method based on a scalable de-cellularized MIMO system as described in any one of claims 1 to 6, 7 or 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the communication method based on the scalable de-cellularized MIMO system as described in any one of claims 1 to 6, 7 or 8.