CN119342565A - Method, device, electronic device and storage medium for controlling cell transmission power - Google Patents
Method, device, electronic device and storage medium for controlling cell transmission power Download PDFInfo
- Publication number
- CN119342565A CN119342565A CN202411432488.5A CN202411432488A CN119342565A CN 119342565 A CN119342565 A CN 119342565A CN 202411432488 A CN202411432488 A CN 202411432488A CN 119342565 A CN119342565 A CN 119342565A
- Authority
- CN
- China
- Prior art keywords
- cell
- user
- information
- node
- network state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. Transmission Power Control [TPC] or power classes
- H04W52/04—Transmission power control [TPC]
- H04W52/06—TPC algorithms
- H04W52/14—Separate analysis of uplink or downlink
- H04W52/143—Downlink power control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. Transmission Power Control [TPC] or power classes
- H04W52/04—Transmission power control [TPC]
- H04W52/18—TPC being performed according to specific parameters
- H04W52/22—TPC being performed according to specific parameters taking into account previous information or commands
- H04W52/223—TPC being performed according to specific parameters taking into account previous information or commands predicting future states of the transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. Transmission Power Control [TPC] or power classes
- H04W52/04—Transmission power control [TPC]
- H04W52/18—TPC being performed according to specific parameters
- H04W52/24—TPC being performed according to specific parameters using SIR [Signal to Interference Ratio] or other wireless path parameters
- H04W52/245—TPC being performed according to specific parameters using SIR [Signal to Interference Ratio] or other wireless path parameters taking into account received signal strength
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
本发明提供一种小区发射功率的控制方法、装置、电子设备及存储介质，涉及通信技术领域。其中，方法包括：获取第一时段的小区网络状态数据集；其中，小区网络状态数据集包括各个小区之间的邻区关系信息、各个小区在第一时段内每个时刻的第一网络状态信息和与用户终端之间的连接关系信息，以及每个时刻的各个已连接用户终端的第二网络状态信息；根据小区网络状态数据集，确定每个小区的发射功率预测结果，以用于对每个小区的发射功率进行控制。本发明充分利用各个小区之间的邻区关系，各个小区与用户终端的连接关系，以及各个小区和各个已接入用户终端的网络状态信息，来预测每个小区的发射功率。
The present invention provides a method, device, electronic device and storage medium for controlling cell transmission power, and relates to the field of communication technology. The method comprises: obtaining a cell network status data set of a first time period; wherein the cell network status data set comprises neighboring relationship information between each cell, first network status information of each cell at each moment in the first time period and connection relationship information with a user terminal, and second network status information of each connected user terminal at each moment; according to the cell network status data set, determining the transmission power prediction result of each cell, so as to control the transmission power of each cell. The present invention makes full use of the neighboring relationship between each cell, the connection relationship between each cell and the user terminal, and the network status information of each cell and each connected user terminal to predict the transmission power of each cell.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and apparatus for controlling cell transmit power, an electronic device, and a storage medium.
Background
The downlink power control in the 5G system is a key and fundamental problem, on one hand, if the base station transmission power is low, the path loss and shadow fading cannot be compensated sufficiently, so that the problem of weak coverage and even coverage blind areas is caused, and on the other hand, if the base station transmission power is high, the problem of cross-zone coverage is caused, more energy is required to be consumed, and the problems of strong interference and high energy consumption are caused. The states of the base station cell and the user in the current network can change along with time, the downlink power needs to be dynamically controlled, and the transmitting power of the base station is correspondingly adjusted to be a proper value according to the network change.
In the related art, the downlink power is mainly dynamically controlled according to the parameter setting at the cell side of the base station and the uplink feedback of the user, for example, the transmission power of the PDCCH dedicated to the edge user is adaptively adjusted based on the aggregation level of the CCE (Control CHANNEL ELEMENT, physical downlink Control channel) of the PDCCH (Physical Downlink Control Channel, physical uplink Control channel) and the feedback condition of the PUCCH (Physical Uplink Control Channel), and the PDSCH power spectrum density is adaptively adjusted based on the scheduling MCS (Modulation and Coding Scheme ), bandwidth and estimated user received signal strength of the PDSCH (Physical Downlink SHARED CHANNEL ), but the effect of power Control is poor, and there is still a problem that the downlink power of the base station is not matched with the actual demand.
Disclosure of Invention
The embodiment of the invention provides a method, a device, electronic equipment and a storage medium for controlling cell transmitting power, which are used for solving the problem that the downlink power of a base station is not matched with actual requirements in a power control strategy in the prior art.
In a first aspect, an embodiment of the present invention provides a method for controlling cell transmit power, including obtaining a cell network state data set of a first period, where the cell network state data set includes neighbor relation information between cells, first network state information of each time of each cell in the first period, connection relation information between the cells and a user terminal, and second network state information of each connected user terminal at each time, and determining, according to the cell network state data set, a transmit power prediction result of each cell, for controlling transmit power of each cell.
In some embodiments, determining the transmission power prediction result of each cell according to the cell network state data set includes constructing a first cell user graph according to the cell network state data set, wherein the first cell user graph is an information expression of network state relations between the cells and the connected user terminals at each time, inputting the first cell user graph into a first power prediction model to obtain the transmission power prediction result of each cell, and the first power prediction model is obtained based on a first cell user graph sample and cell transmission power label training corresponding to the first cell user graph sample.
The method includes the steps of determining each cell as a cell node according to a cell network state data set, determining first edge characteristic information among the cell nodes based on neighbor relation information among the cells, determining each connected user terminal at the first moment as a user node according to a connection relation of the first moment for the first moment, determining second edge characteristic information among the cell nodes and the cell nodes, determining initial characteristic information of each cell node based on the first network state information of each cell at the first moment, determining initial characteristic information of each user node based on the second network state information of each connected user terminal at the first moment, determining initial characteristic information of each user node based on the cell nodes, the first edge characteristic information, the second edge characteristic information, the initial characteristic information of each connected user terminal and the first moment, and determining a user slice of each cell graph.
In some embodiments, the first power prediction model includes a spatial fusion layer, a time domain fusion layer and a linear mapping layer, the inputting the first cell user graph to the first power prediction model to obtain a transmission power prediction result of each cell includes sending the first cell user graph to the spatial fusion layer to obtain a spatial fusion feature set of each cell node output by the spatial fusion layer, wherein each spatial fusion feature set includes spatial fusion feature information of a corresponding cell node at each time, the spatial fusion layer is used for performing fusion processing on initial feature information of each cell node and initial feature information of its neighbor node based on the first cell user graph, inputting the spatial fusion feature set of each cell node to the time domain fusion layer to obtain spatial fusion feature information of each cell node output by the time domain fusion layer, and the time domain fusion layer is used for performing linear mapping processing on the spatial fusion feature information of each cell node at each time within each time period to obtain the linear prediction result of each cell node.
In some embodiments, the determining a transmission power prediction result of each cell according to the cell network state data set includes constructing a plurality of second cell user graphs according to the divided plurality of cell subgraphs, the first network state information, the connection relation information and the second network state information, wherein the plurality of cell subgraphs are divided based on neighbor relation information of each cell, the plurality of second cell user graphs are in one-to-one correspondence with the plurality of cell subgraphs, each second cell user graph is between each cell in a corresponding cell subgraph, and information about a network state relation between each cell in the corresponding cell subgraph and each connected user terminal at each time, and inputting the plurality of second cell user graphs into a second power prediction model to obtain a transmission power prediction result of each cell, wherein the second power prediction model is based on a training sample of a transmission power sample of each cell in the second cell user graph and the second cell user graph.
As an example, the plurality of cell subgraphs are divided by constructing a cell topological graph based on the neighbor relation of each cell, and dividing the cell topological graph based on a spectral clustering algorithm to obtain each cell subgraph.
The invention provides a control device of cell transmitting power, which comprises an acquisition module and a prediction module, wherein the acquisition module is used for acquiring a cell network state data set of a first time period, the cell network state data set comprises neighbor relation information among cells, first network state information of each time of each cell in the first time period and connection relation information between the cells and a user terminal, and second network state information of each connected user terminal at each time, and the prediction module is used for determining a transmitting power prediction result of each cell according to the cell network state data set so as to control the transmitting power of each cell.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory storing a computer program, where the processor implements the method for controlling cell transmit power according to the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the method for controlling cell transmit power according to the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, where the computer program when executed by a processor implements the method for controlling the cell transmit power according to the first aspect.
The method, the device, the electronic equipment and the storage medium for controlling the cell transmitting power acquire a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor cell relation information among cells, first network state information of each time of each cell in the first time period, connection relation information between the cells and a user terminal, and second network state information of each connected user terminal at each time, and a transmitting power prediction result of each cell is determined according to the cell network state data set and used for controlling the transmitting power of each cell. The invention fully utilizes the neighbor relation among cells, the connection relation between the cells and the user terminals, and the network state information of the cells and the accessed user terminals to predict the transmitting power of each cell, and takes the predicted transmitting power of each cell as the decision basis for controlling the transmitting power of the cell, thereby improving the accuracy of power control, further improving the signal coverage and strength of the cells covered by the base station to meet the requirements and improving the network coverage performance.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for controlling cell transmit power according to an embodiment of the present invention;
fig. 2 is a second flowchart of a method for controlling cell transmit power according to an embodiment of the present invention;
fig. 3 is a third flowchart of a method for controlling cell transmit power according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a first cell user diagram in an embodiment of the present invention;
fig. 5 is a flow chart of a method for controlling cell transmit power according to an embodiment of the present invention;
fig. 6 is a flowchart of a method for controlling cell transmit power according to an embodiment of the present invention;
Fig. 7 is a schematic diagram of cell sub-division provided in an embodiment of the present invention;
Fig. 8 is a schematic structural diagram of a device for controlling cell transmit power according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The downlink power control in the 5G system is a key and fundamental problem, on one hand, if the base station transmission power is low, the path loss and shadow fading cannot be compensated sufficiently, so that the problem of weak coverage and even coverage blind areas is caused, and on the other hand, if the base station transmission power is high, the problem of cross-zone coverage is caused, more energy is required to be consumed, and the problems of strong interference and high energy consumption are caused. The states of the base station cell and the user in the current network can change along with time, the downlink power needs to be dynamically controlled, and the transmitting power of the base station is correspondingly adjusted to be a proper value according to the network change.
In the related art, the downlink power is mainly dynamically controlled according to the parameter setting at the cell side of the base station and the uplink feedback of the user, for example, the transmission power of the PDCCH special for the edge user is adaptively adjusted based on the CCE aggregation level of the PDCCH and the feedback condition of the PUCCH, and the PDSCH power spectral density is adaptively adjusted based on the dispatching MCS, the bandwidth and the estimated received signal strength of the user of the PDSCH, but the effect of power control is poor, and the problem that the downlink power of the base station is not matched with the actual demand still exists.
In order to solve the problems, the invention provides a method, a device, an electronic device and a storage medium for controlling cell transmitting power.
Fig. 1 is a flow chart of a method for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 1, the method may include the following steps.
And step 101, acquiring a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor relation information among cells, first network state information of each time of each cell in the first time period and connection relation information between the cells and user terminals, and second network state information of each connected user terminal at each time.
In some embodiments, the first period may be a continuous period including the current time and a period before, or may be a continuous period that is relatively close to the current network state in the past, for a scenario in which the transmission power of each cell at the current time is predicted. For the scenario of transmit power prediction of a cell for a future period, the first period may be a past period that is close to the network state for the future period.
In some embodiments of the present invention, the transmission power of all cells of the whole network may be predicted, where each cell is all cells of the whole network, and the transmission power of cells in the target area may also be predicted, where each cell is all cells in the target area.
In some embodiments, neighbor relation information of each cell may be obtained from a network management data platform. The first network state information of each cell at each time in the first period may include a maximum number of users, a downlink average PRB utilization, downlink data throughput, interference strength, and the like, and these data may also be obtained from the network management data platform. The connection relationship information between each cell and the ue at each time in the first period refers to information of the ue to which each cell is connected in each period, for example, if a certain cell and a certain ue are in an RRC (Radio Resource Control ) connected state, it is determined that a connection relationship exists between the cell and the ue. The second network state information may include measurement information of each connected ue on the serving cell, for example, RSRP (REFERENCE SIGNAL RECEIVING Power, reference signal received Power), RSRQ (REFERENCE SIGNAL RECEIVING Quality, reference signal received Quality), SINR (Signal to Interference plus Noise Ratio ), and may further include measurement information of each connected ue on the neighbor cell, for example, RSRP, RSRQ, SINR, and the above data may be obtained from the network management data platform.
Step 102, determining the predicted result of the transmitting power of each cell according to the data set of the cell network state, so as to control the transmitting power of each cell.
It may be appreciated that the cell network state data set includes neighbor cell relations between cells in the first period, network state information of each cell and each accessed user terminal at each time in the first period, and data such as interrelation between each cell and each user terminal, and the like, which all interact with cell transmission power, so that interrelation between the above data can be fully considered to predict the transmission power of each cell.
In some embodiments, the transmission power prediction result of each cell may include a cell transmission power prediction result of each cell at each time in a second period, where the second period may be a future period in which a network state of the first period is close, and a duration of the second period may be consistent with or less than a duration of the first period.
In other embodiments, if the application scenario is to predict the transmission power of the current cell, and the first period is a continuous period including the current time and a period of time before the current time, the transmission power prediction result of each cell may include the transmission power prediction value of the corresponding cell at the current time.
In some embodiments, determining the transmit power predictions for each cell based on the cell network state data set may include inputting the cell network state data set into a trained neural network model to obtain the transmit power predictions for each cell. The neural network model may be trained based on a plurality of past time period cell network state data samples and their corresponding cell transmit power tags.
In other embodiments, the method may include performing fusion processing on first network state information of each cell and first network state information of a neighboring cell of the cell based on a neighboring cell relationship of each cell, performing fusion processing on second network state information of connected user terminals and second network state information of all connected user terminals connected to the cell to obtain second fusion state information of the cell, performing fusion processing on the first fusion state information and the second fusion state information of the cell to obtain third fusion state information of the cell, performing fusion processing on information of each moment in the third fusion state information to obtain fourth fusion state information, and determining a transmission power prediction result of the cell based on a mapping relationship between the preset fourth fusion state information and the transmission power of the cell. The fusion weight value in each fusion processing process can be obtained based on the respective network state information, or each fusion processing process can be realized by constructing a multi-layer attention network.
In some embodiments, the obtained transmission power prediction result of each cell may be directly used for controlling the transmission power of the cell, or the transmission power of each cell may be controlled based on the corrected result after the correction process.
As an implementation manner, the method for controlling the cell transmitting power of the present invention can be applied to a network management platform side, executed by the network management platform side, and sends a control instruction of the cell transmitting power to a base station side based on the transmitting power prediction result of each cell.
As another implementation manner, the execution body of the cell transmitting power control method of the present invention may be any electronic device, where the electronic device establishes communication connection with the network management platform side, and sends the obtained transmitting power prediction result of each cell to the network management platform side, so that the network management platform side sends a control instruction of the cell transmitting power to the base station side based on the transmitting power prediction result of the cell.
As still another implementation manner, the execution body of the cell transmit power control method of the present invention may be any electronic device, where the electronic device establishes a communication connection with a base station side, and sends the obtained transmit power prediction result of each cell to a corresponding base station, so as to send the result to a network management platform side, so that the base station side controls the transmit power of the cell based on the transmit power prediction result of the cell.
The method for controlling the cell transmitting power comprises the steps of obtaining a cell network state data set of a first period, wherein the cell network state data set comprises neighbor relation information among cells, first network state information of each time of each cell in the first period, connection relation information between the cells and user terminals, and second network state information of each connected user terminal at each time, and determining a transmitting power prediction result of each cell according to the cell network state data set so as to control the transmitting power of each cell. The invention fully utilizes the neighbor relation among cells, the connection relation between the cells and the user terminals, and the network state information of the cells and the accessed user terminals to predict the transmitting power of each cell, and takes the predicted transmitting power of each cell as the decision basis for controlling the transmitting power of the cell, thereby improving the accuracy of power control, further improving the signal coverage and strength of the cells covered by the base station to meet the requirements and improving the network coverage performance.
Fig. 2 is a second flowchart of a method for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 2, based on the above embodiment, the implementation procedure of step 102 in fig. 1 may include the following steps.
Step 201, constructing a first cell user graph according to the cell network state data set, wherein the first cell user graph is an information expression of network state relations between cells and between the cells and connected user terminals at each time.
In some embodiments, the first cell user graph is graph data constructed based on a cell network state dataset. The first cell user map is a dynamic iso-map including a first cell user map slice at various times during a first period. Because the cell network state data set contains a large amount of relation data, the information is expressed through the cell user graph, and the relation among the nodes can be expressed more intuitively.
In some embodiments, for each moment, each cell may be used as a cell node, each connected user terminal may be used as a user node, the cell-to-cell neighbor relation may be expressed by an edge connected between the cell nodes, the connection relation between the cell and the user terminal may be expressed by an edge connected between the cell nodes and the user node, the first network state information of each cell may be used as the first network state information of the corresponding cell node, and the second state information of each connected user terminal may be used as the second network state information of the corresponding user node.
As an example, the first cell user graph g= { G t}t=1,T1, where G t represents the first cell user graph slice at time T within T1, T1 being the first period. G t includes a plurality of cell nodes, a plurality of user nodes, first network state information of each cell node, second network state information of each user node, edges between cell nodes, and edges between cell nodes and user nodes.
Step 202, a first cell user graph is input to a first power prediction model to obtain a transmission power prediction result of each cell, wherein the first power prediction model is obtained based on a first cell user graph sample and a cell transmission power label training corresponding to the first cell user graph sample.
In some embodiments, the first power prediction model may be a graph neural network model that has been learned for its ability to predict the transmit power of a cell based on a first cell user graph.
In some embodiments, the first cell user map sample may be constructed based on a set of cell network state data over a large number of historical periods. For example, a cell network state data set of a plurality of time periods in the past and a transmitting power label of each cell corresponding to each time period are obtained, the duration of each time period is consistent with the duration of a first time period, a first cell user graph is built based on the cell network state data set of each time period to obtain a first cell user graph sample, the first cell user graph sample and a corresponding cell transmitting power label value are input into an initial first power prediction model for training, and a trained first power prediction model is obtained.
It should be noted that, the cell transmit power tag corresponding to the first cell user map sample may be determined based on actual requirements, for example, if it is required to predict the transmit power of each cell at the current time based on the cell network state data set of the continuous time period formed by the current time and the previous time period, the transmit power set value at the last time in each historical time period may be used as the corresponding cell transmit power tag value. For another example, if the transmission power of each cell in the future period is predicted based on the cell network state data set in the past period, the cell transmission power set value at each time in each history period may be used as the corresponding cell transmission power tag value in the training process.
According to the method for controlling the cell transmitting power, a first cell user graph is constructed according to a cell network state data set, the first cell user graph is information expression of network state relations between cells and between the cells and connected user terminals at each moment, the first cell user graph is input into a first power prediction model to obtain a transmitting power prediction result of each cell, and the first power prediction model is obtained through training based on a first cell user graph sample and a cell transmitting power label corresponding to the first cell user graph sample. By constructing the first cell user graph, the network state relation between cells and between the cells and users is fully utilized, and the prediction of the cell transmitting power is realized through the first power prediction model to be used as the decision basis for controlling the cell transmitting power, so that the accuracy of power control can be improved.
Fig. 3 is a third flowchart of a method for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 3, the implementation process of constructing the first cell user graph from the cell network state data set may include the following steps.
Step 301, determining each cell as a cell node, and determining first edge characteristic information between the cell nodes based on neighbor relation information between the cells.
That is, each cell is taken as a node in the first cell user graph, the neighbor relation between cells is taken as an edge, if the two cells are in neighbor relation, the edge weight between the two cell nodes is 1, and if the two cells are not in neighbor relation, the edge weight between the two cell nodes is 0. The first edge characteristic information among the cell nodes is edge weight.
Step 302, for a first time in the first period, determining each connected user terminal at the first time as a user node based on connection relation information at the first time, and determining second side characteristic information between each user node and each cell node.
In some embodiments, the connected user terminals at the first moment may be determined based on the connection relationship information between each cell and the user terminal at the first moment, and each connected user terminal at the first moment is also used as a node in the user graph of the first cell, that is, a user node. And taking the connection relation between each cell and the user terminal as an edge between the cell node and the user node. If the connected user terminal A and the cell B are in a connection state at the first moment, the side weight between the user node corresponding to the connected user terminal A and the cell node corresponding to the cell B at the first moment is reset to be 1, otherwise, the side weight is set to be 0. And the second side characteristic information between each user node and each cell node is the side weight between each user node and each cell node.
Step 303, determining initial characteristic information of each cell node based on the first network state information of each cell at the first moment, and determining initial characteristic information of each user node based on the second signal state information of each connected user terminal at the first moment.
In some embodiments, for each cell, initial characteristic information of a cell node corresponding to the cell may be determined based on first network state information of the cell at a first time.
As an example, initial characteristic information of a cell node may be defined asAnd (3) for each cell, the column vector of the dimension carries out code conversion on the first network state information of the cell at the first moment to obtain the initial characteristic information of the cell node corresponding to the cell. For example, if the first network state information includes the maximum number of users, the utilization rate of downlink average PRBs (Physical Resource Block, physical resource blocks), the downlink data throughput, and the like, the above information may be spliced, and the spliced data may be subjected to code conversion, so as to obtain initial feature information of the corresponding cell node.
Step 304, determining a first cell user graph slice at a first time based on the cell nodes, the user nodes, the first edge feature information, the second edge feature information, the initial feature information of each cell node, and the initial feature information of each user node.
In some embodiments, each cell node, the first edge feature information, the plurality of user nodes determined at the first time, the second edge feature information, the initial feature information of each cell node, and the initial feature information of each user node are formed into a first cell user graph slice at the first time.
Step 305, determining a first cell user map based on the first cell user map slices at each time instant in the first period.
In some embodiments, the first cell user map includes a first cell user map slice at each time in the first period, so the first cell user map slice at each time in the first period is sequentially constructed according to steps 302 to 304, and finally the first cell user map of the first period is obtained.
As shown in fig. 4, the first cell user graph may be a dynamic heterogram, where the graph includes first cell user graph slices at each time in the first period, and each first cell user graph slice includes a cell node, a user node, initial feature information of the cell node, initial feature information of the user node, an edge between the cell nodes, and an edge between the cell node and the user node.
According to the method for controlling the cell transmitting power, the first cell user graph slices of each time interval in the first time interval are sequentially constructed to obtain the first cell user graph of the first time interval, so that the network state relations among cells and between the cells and the user terminals are intuitively expressed, the information is fully utilized when the cell transmitting power is predicted, the accuracy of the cell transmitting power prediction is improved, and the effect of cell power control can be further improved.
Fig. 5 is a flowchart illustrating a method for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 5, based on the above embodiment, the implementation process of inputting the first cell user map into the first power prediction model to obtain the transmission power prediction result of each cell may include the following steps.
Step 501, a first cell user graph is sent to an airspace fusion layer to obtain an airspace fusion feature set of each cell node output by the airspace fusion layer, wherein each airspace fusion feature set comprises airspace fusion feature information of a corresponding cell node at each moment, and the airspace fusion layer is used for carrying out fusion processing on initial feature information of each cell node and initial feature information of neighbor nodes of the corresponding cell node based on the first cell user graph.
In some embodiments, the first power model may be a hierarchical attention network model including a spatial fusion layer, a temporal fusion layer, and a linear mapping layer. The airspace fusion layer is used for determining neighbor nodes of each cell node at each moment based on the first cell user graph, wherein the neighbor nodes can comprise neighbor cell nodes of the corresponding cell nodes and user nodes connected with the corresponding cell nodes. The airspace fusion layer can also perform fusion processing on the initial characteristic information of the cell node, the initial characteristic information of the adjacent cell and the initial characteristic information of the connected user node aiming at each cell node, and the obtained airspace fusion characteristics of the cell are combined.
In some embodiments, the implementation process of the airspace fusion layer for carrying out fusion processing on the initial characteristic information of each cell node and the initial characteristic information of the neighbor nodes of the same can comprise the steps of determining the fusion characteristics of the neighbor cell nodes of the Ai according to the initial characteristic information of the Ai and the initial characteristic information of the neighbor cell nodes of the ith time for the i-th cell node Ai, determining the fusion characteristics of the neighbor cell nodes of the Ai according to the first cell user graph, determining the first fusion weight coefficient of the neighbor cell nodes of the Ai according to the initial characteristic information of the Ai and the initial characteristic information of the neighbor cell nodes, determining the second fusion weight coefficient of the neighbor cell nodes of the Ai according to the initial characteristic information of the Ai, determining the fusion characteristics of the neighbor cell nodes of the Ai according to the first fusion weight coefficient and the initial characteristic information of the neighbor users, and the fusion characteristics of the neighbor user nodes of the Ai, and carrying out fusion processing on the fusion characteristics of the neighbor cell nodes of the Ai and the neighbor user nodes of the Ai according to the initial characteristic information of the Ai, and obtaining the fusion characteristics of the airspace at the time t. The first fusion weight coefficient and the second fusion weight coefficient both represent the characteristic contribution degree of the neighbor node to the Ai node.
As an example, the process of determining the first fusion weight coefficient of each neighbor cell node pair Ai based on the initial characteristic information of Ai and the initial characteristic information of each neighbor cell node may be implemented as the following formula (1).
(1);
Wherein, A first fusion weight coefficient of the jth neighbor cell node Aj to the ith cell node Ai is the t moment; a neighbor cell node set representing a cell node Ai at a t-th time; Initial characteristic information of the cell node Ai at the t-th moment; is an activation function; For the attention factor, a trainable column vector may be used, and the dimension may be 2 ;Is a trainable weight matrix with dimensions of,The dimension of the initial characteristic information of the Ai node; Representing the column vectors being stitched by row.
Based on the first fusion weight coefficient and the initial feature information of each neighbor cell, an implementation manner of determining the fusion feature of the Ai neighbor cell node may be as shown in formula (2).
(2);
Wherein, Is the fusion characteristic of Ai neighbor cell nodes.
Based on the initial characteristic information of Ai and the initial characteristic information of each neighbor user node, the implementation process of determining the second fusion weight coefficient of each neighbor user node to Ai is shown in the following formula (3).
(3);
Wherein, A second fusion weight coefficient of the jth user cell node Bj to the ith cell node Ai is the t moment; a neighbor cell user node set representing a cell node Ai at a t-th moment; Initial characteristic information of the cell node Ai at the t-th moment; is an activation function; For the attention factor, a trainable column vector may be used, and the dimension may be 2 ;AndAs a matrix of weights that can be trained,The dimension is,Is of the dimension of,Is the dimension of the initial characteristic information of the user node.
Based on the second fusion weight coefficient and the initial feature information of each neighbor user, the implementation process of determining the fusion feature of the Ai neighbor user node can be shown in the following formula (4).
(4);
Wherein, Fusion characteristics of Ai neighbor cell users.
Finally, the initial characteristic information of Ai, the fusion characteristic of the Ai neighbor cell node and the fusion characteristic of the Ai neighbor user node are subjected to fusion processing, and the implementation mode of obtaining the airspace fusion characteristic information of Ai at the t-th moment can be shown in the following formula (5).
(5);
Wherein, therein、AndRespectively representing corresponding weighting coefficient matrixes, and obtaining the weighting coefficient matrixes through training; The dimension is ,Is of the dimension of,Is of the dimension of,Is one ofColumn vector of dimensions.
Step 502, inputting the spatial fusion feature set of each cell node to a time domain fusion layer to obtain the spatial fusion feature information of each cell node output by the time domain fusion layer, wherein the time domain fusion layer is used for carrying out fusion processing on the spatial fusion feature information of each cell node at each moment in a first period based on the spatial fusion feature set of each cell node.
In some embodiments, the time domain fusion layer may perform fusion processing on the spatial domain fusion characteristic information of each cell node at each time in the first period based on the scale dot product attention mechanism.
In some embodiments, forThe airspace fusion characteristic set of the node is {The sets may be combined into a matrix,The dimension is. Calculation of,,Wherein、AndAll of the dimensions of (a),Is one dimension ofFor the purpose of aggregating only spatial aggregation features from the t-th time and from the t-th time onward in time domain aggregation of cell nodes at the t-th time, thusElements of (a)Is defined as the following equation (6).
(6);
The final spatiotemporal fusion characteristic information of the node Ai can be obtained based on the following formula (7). It should be noted that, the final spatio-temporal fusion feature information of Ai may be a spatio-temporal fusion feature information set of each time, or may be the spatio-temporal fusion feature information of the last time in the first period, which may be set based on actual requirements.
(7);
Wherein, A time-space fusion characteristic information set for the node Ai; Is one dimension of Is a matrix of the (c) in the matrix,Is the first of (2)Individual row vectorsNamely, isAnd (5) fusing the characteristic information in time and space at the t time.
And step 503, the space-time fusion characteristic information of each cell node is input into the linear mapping layer, and the transmission power prediction result of each cell output by the linear mapping layer is obtained.
According to the method for controlling the cell transmitting power, disclosed by the embodiment of the invention, the spatial domain information and the time domain information contained in the first cell user graph are subjected to deep fusion through the first power prediction model comprising the spatial domain fusion layer, the time domain fusion layer and the linear mapping layer, so that deep feature extraction is performed on the first cell user graph, the accuracy of the transmitting power prediction of each cell can be further improved, and the accuracy and the effect of the cell power control can be further improved.
In order to further improve the calculation efficiency, the invention also provides another embodiment.
Fig. 6 is a flowchart of a method for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 6, based on the above embodiment, the implementation process of determining the transmission power prediction result of each cell according to the cell network state data set may include the following steps.
And 601, constructing a plurality of second cell user graphs according to the divided plurality of cell subgraphs, the first network state information, the connection relation information and the second network state information, wherein the plurality of cell subgraphs are divided based on neighbor relation information of each cell, the plurality of second cell user graphs are in one-to-one correspondence with the plurality of cell subgraphs, and each second cell user graph is an information expression of the network state relation at each moment between each cell in the corresponding cell subgraph and each connected user terminal.
It can be understood that the number of cells and the number of user terminals in the whole network are huge, the data volume involved in the first cell user graph constructed based on the cell network state data set in the first period is large, and the calculation resources required in model prediction and training are large and the time consumption is long. In order to improve the calculation efficiency, the embodiment of the invention builds the second cell user graph based on the divided cell subgraphs, and each obtained second cell user graph only relates to the information of the cell nodes in the corresponding cell subgraphs and the information of the user nodes connected with the cell nodes, and the calculation efficiency can be greatly improved by distributed parallel calculation when the second cell user graph is built and the cell transmitting power is predicted.
In some embodiments, the cell subgraphs are divided based on neighbor relation information among the cell nodes, each cell subgraph can include a plurality of cells with closer association, and the association among the cells among different subgraphs is sparse, so that efficient information interaction can be performed on the cells in the same cell subgraph, and the calculation efficiency can be improved.
In some embodiments, each cell sub-graph may include a plurality of cell nodes and edges between the cell nodes, and the adjacent cell relationship between the cells is taken as an edge, if the adjacent cell relationship exists between the two cells, the edge weight between the corresponding cell nodes is reset to 1, otherwise, the edge weight between the corresponding cell nodes is set to 0. That is, the first edge characteristic information between the cell nodes may be included in the cell subgraph.
In some embodiments, the process of constructing a plurality of second cell user graphs is consistent with the process of constructing the first cell user graph based on the divided plurality of cell subgraphs, the first network state information, the connection relationship information and the second network state information, except that the second cell user graph is constructed based on the cell nodes included in each cell subgraph, not all the cell nodes. As an example, if a second cell user graph corresponding to the cell sub-graph a is constructed, for each moment, based on the cell node in the cell sub-graph a, the connected user terminal at the moment is obtained, and is determined as a user node, and second side feature information between the user nodes, based on the first network state information at the moment, initial feature information of the cell node in the cell sub-graph a is determined, based on the second network state information at the moment, initial feature information of the user node is obtained, and based on the above information, a second cell user graph slice in the second cell user graph corresponding to the cell sub-graph a is determined.
In some embodiments, the cell subgraphs can be divided by constructing a cell topological graph based on the neighbor relation of each cell, and dividing the cell topological graph based on a spectral clustering algorithm to obtain each cell subgraph.
Specifically, when the cell topological graph is constructed, the cells are taken as nodes, the adjacent cell relationship between the cells is taken as an edge, namely if the adjacent cell relationship exists between the two cells, the corresponding edge weight is reset to be 1, otherwise, the corresponding edge weight is set to be 0, and an undirected weighted graph is obtained. Suppose that cell topology is commonEach node, the corresponding adjacent matrix is set asFrom the adjacency matrix, a degree matrix can be calculated,Is a diagonal matrix, the elements on the diagonalThus a corresponding Laplace matrix。
According to a spectral clustering algorithm, neighbor cells which are closely related with each other and possibly have overlapping coverage and mutual influence are divided into the same subgraph. First, a representation matrix is calculatedThen by calculationA kind of electronic deviceThe feature values and corresponding feature vectors will be defined byThe matrix formed by the characteristic vectors is standardized according to the rows to obtain the characteristic matrixWill beAs samples, a total ofSamples are then clustered using a k-means, etc. clustering algorithmClustering the samples, and setting the dimension of the clusters asFinally, dividing the cell topological graph intoAnd a cell subgraph. Fig. 7 is a schematic diagram of dividing a cell topology into a plurality of cell subgraphs.
Therefore, the cell topological graph formed by the whole network cells is divided into different cell subgraphs through the division of the cell topological graph in the step, and the subsequent processing is respectively carried out on each cell subgraph, so that the information interaction cost is reduced, and the data processing efficiency is improved.
Step 602, inputting a plurality of second cell user graphs into a second power prediction model to obtain a transmission power prediction result of each cell, wherein the second power prediction model is obtained based on a second cell user graph sample and cell transmission power labels corresponding to the second cell user graph sample.
It should be noted that the second power prediction model is different from the first power prediction model in that the second power prediction model is obtained by training based on the second cell user graph sample and the cell transmit power label corresponding to the second cell user graph sample, and the first power prediction model is obtained by training based on the first cell user graph sample. The second cell user graph sample is constructed according to a plurality of cell network state data sets of historical time periods based on a plurality of divided cell subgraphs.
In some embodiments, the second power prediction model may also include a spatial fusion layer, a temporal fusion layer, and a linear mapping layer, and the implementation process and principle are consistent with those of the first power prediction model, except that the second cell user map contains a small amount of data, and the prediction needs to be performed based on the data in the second cell user map when the second power prediction model predicts. The prediction of the cell transmit power by the different second cell user patterns can be accomplished by distributed parallel computation.
According to the method for controlling the cell transmitting power, a plurality of second cell user graphs are constructed according to the divided plurality of cell subgraphs, the first network state information, the connection relation information and the second network state information, the plurality of second cell user graphs are input into a second power prediction model, and the transmitting power prediction result of each cell is obtained. The invention divides the whole network cell into a plurality of cell subgraphs, and can greatly improve the calculation efficiency by distributed parallel calculation when constructing the cell user graph and predicting the cell transmitting power.
The following describes a device for controlling cell transmit power provided by an embodiment of the present invention, where the device for controlling cell transmit power described below and the method for controlling cell transmit power described above may be referred to correspondingly.
Fig. 8 is a schematic structural diagram of a device for controlling cell transmit power according to an embodiment of the present invention. As shown in fig. 8, the apparatus may include an acquisition module 810 and a prediction module 820.
An obtaining module 810, configured to obtain a cell network state data set of a first period, where the cell network state data set includes neighbor cell relationship information between cells, first network state information of each time of each cell in the first period, connection relationship information between each time and a user terminal, and second network state information of each connected user terminal at each time;
a prediction module 820, configured to determine a transmission power prediction result of each cell according to the cell network status data set, so as to control the transmission power of each cell.
In some embodiments, the prediction module 820 includes a construction unit 821 and a prediction unit 822, where the construction unit 821 is configured to construct a first cell user graph according to a cell network state data set, the first cell user graph is an information expression of a network state relationship between each cell and each connected user terminal at each time, and the prediction unit 822 is configured to input the first cell user graph into a first power prediction model to obtain a transmission power prediction result of each cell, where the first power prediction model is obtained by training based on a first cell user graph sample and a cell transmission power label corresponding to the first cell user graph sample.
In some embodiments, the construction unit 821 is specifically configured to determine each cell as a cell node, determine first edge feature information between the cell nodes based on neighbor relation information between the cells, determine, for a first time in a first period, each connected user terminal at the first time as a user node based on connection relation information at the first time, and determine second edge feature information between the user node and the cell node, determine initial feature information of each cell node based on first network state information of the cell at the first time, determine initial feature information of each user node based on second signal state information of each connected user terminal at the first time, determine a first cell user map at the first time based on the cell node, the user node, the first edge feature information, the initial feature information of each cell node, and the initial feature information of each user node, and determine a first cell user map at the first time based on the first cell user map at the first time and the first cell user map at the first time.
In some embodiments, the first power prediction model comprises an airspace fusion layer, a time domain fusion layer and a linear mapping layer, the prediction unit 822 is further configured to send a first cell user graph to the airspace fusion layer to obtain an airspace fusion feature set of each cell node output by the airspace fusion layer, wherein each airspace fusion feature set comprises airspace fusion feature information of a corresponding cell node at each moment, the airspace fusion layer is configured to fuse initial feature information of each cell node with initial feature information of a neighbor node based on the first cell user graph, input the airspace fusion feature set of each cell node to the time domain fusion layer to obtain spatial-temporal fusion feature information of each cell node output by the time domain fusion layer, and the time domain fusion layer is configured to fuse the airspace fusion feature information of each cell node at each moment in a first period based on the airspace fusion feature set of each cell node, input the spatial-temporal fusion feature information of each cell node to the linear mapping layer to obtain a transmission power prediction result of each cell output by the linear mapping layer.
In some embodiments, the construction unit 821 is further configured to construct a plurality of second cell user graphs according to the partitioned plurality of cell subgraphs, the first network state information, the connection relationship information and the second network state information, wherein the plurality of cell subgraphs are partitioned based on neighbor relationship information of each cell, the plurality of second cell user graphs are in one-to-one correspondence with the plurality of cell subgraphs, each second cell user graph is obtained by training a cell transmission power label corresponding to a second cell user graph sample and a second cell user graph sample, and the information of the network state relationship at each time between each cell in the corresponding cell subgraph and each connected user terminal is expressed, and the prediction unit 822 is further configured to input the plurality of second cell user graphs into a second power prediction model to obtain a transmission power prediction result of each cell.
In some embodiments, the apparatus further includes a partitioning module 830 configured to construct a cell topology map based on a neighboring cell relationship of each cell, and perform a partitioning process on the cell topology map based on a spectral clustering algorithm to obtain each cell subgraph.
It should be noted that the explanation of the above embodiment of the method for controlling the cell transmit power may be applied to the device for controlling the cell transmit power according to the embodiment of the present invention, which is not described herein again.
Fig. 9 illustrates a physical schematic diagram of an electronic device, which may include a processor (processor) 910, a communication interface (Communication Interface) 920, a memory 930, and a communication bus 940, where the processor 910, the communication interface 920, and the memory 930 perform communication with each other through the communication bus 940, as shown in fig. 9. The processor 910 may invoke computer programs in the memory 930 to perform the steps of the control method of the cell transmit power.
The method comprises the steps of obtaining a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor relation information among cells, first network state information of each time point of each cell in the first time period and connection relation information between the cells and user terminals, and second network state information of each connected user terminal of each time point, and determining a transmission power prediction result of each cell according to the cell network state data set, wherein the transmission power prediction result of each cell is used for controlling the transmission power of each cell.
Further, the logic instructions in the memory 930 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention further provide a computer program product, where the computer program product includes a computer program, where the computer program may be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer program is capable of executing the steps of the method for controlling cell transmit power provided by the foregoing embodiments.
The method comprises the steps of obtaining a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor relation information among cells, first network state information of each time of each cell in the first time period, connection relation information between each time of each cell and a user terminal, and second network state information of each connected user terminal of each time, and determining a transmission power prediction result of each cell according to the cell network state data set so as to control the transmission power of each cell.
In another aspect, an embodiment of the present invention further provides a processor readable storage medium, where a computer program is stored, where the computer program is configured to cause a processor to execute the steps of the method for controlling cell transmit power provided in the foregoing embodiments.
The method comprises the steps of obtaining a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor relation information among cells, first network state information of each time point of each cell in the first time period and connection relation information between the cells and user terminals, and second network state information of each connected user terminal of each time point, and determining a transmission power prediction result of each cell according to the cell network state data set, wherein the transmission power prediction result of each cell is used for controlling the transmission power of each cell.
The processor-readable storage medium may be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, non-volatile storage (NAND FLASH), solid State Disk (SSD)), etc.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.
Claims (10)
1. A method for controlling cell transmit power, comprising:
The method comprises the steps of acquiring a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor cell relation information among cells, first network state information of each time of each cell in the first time period, connection relation information between each time and a user terminal, and second network state information of each connected user terminal at each time;
and determining a transmission power prediction result of each cell according to the cell network state data set, wherein the transmission power prediction result is used for controlling the transmission power of each cell.
2. The method for controlling the transmission power of a cell according to claim 1, wherein said determining the transmission power prediction result of each of said cells based on said cell network status data set comprises:
Constructing a first cell user graph according to the cell network state data set, wherein the first cell user graph is an information expression of network state relations between the cells and the connected user terminals at each moment;
And inputting the first cell user graph into a first power prediction model to obtain a transmission power prediction result of each cell, wherein the first power prediction model is obtained based on a first cell user graph sample and cell transmission power labels corresponding to the first cell user graph sample.
3. The method for controlling cell transmit power according to claim 2, wherein said constructing a first cell user map from said cell network status data set comprises:
Determining each cell as a cell node, and determining first edge characteristic information among the cell nodes based on neighbor relation information among the cells;
For a first moment in the first period, based on connection relation information of the first moment, each connected user terminal at the first moment is respectively determined to be a user node, and second side characteristic information between each user node and each cell node is determined;
Determining initial characteristic information of each cell node based on first network state information of each cell at the first moment, and determining initial characteristic information of each user node based on second signal state information of each connected user terminal at the first moment;
determining a first cell user graph slice at the first moment based on the cell nodes, the user nodes and the first side characteristic information, the second side characteristic information, initial characteristic information of each cell node and initial characteristic information of each user node;
And determining the first cell user graph based on the first cell user graph slices at each moment in the first period.
4. The method for controlling cell transmit power according to claim 3, wherein the first power prediction model includes a spatial domain fusion layer, a temporal domain fusion layer, and a linear mapping layer, and the inputting the first cell user map into the first power prediction model to obtain the transmit power prediction result of each cell includes:
The method comprises the steps of sending a first cell user graph to an airspace fusion layer to obtain airspace fusion feature sets of each cell node output by the airspace fusion layer, wherein each airspace fusion feature set comprises airspace fusion feature information of a corresponding cell node at each moment;
Inputting the space-time fusion feature set of each cell node to the time-domain fusion layer to obtain space-time fusion feature information of each cell node output by the time-domain fusion layer; the time domain fusion layer is used for carrying out fusion processing on the airspace fusion characteristic information of each cell node at each moment in the first period based on the airspace fusion characteristic set of each cell node;
And inputting the space-time fusion characteristic information of each cell node to the linear mapping layer to obtain a transmission power prediction result of each cell output by the linear mapping layer.
5. The method for controlling the transmission power of a cell according to claim 1, wherein said determining the transmission power prediction result of each of said cells based on said cell network status data set comprises:
Constructing a plurality of second cell user graphs according to the divided cell subgraphs, the first network state information, the connection relation information and the second network state information, wherein the cell subgraphs are divided based on neighbor relation information of each cell, the cell user graphs are in one-to-one correspondence with the cell subgraphs, each cell user graph is in a corresponding cell subgraph, and the information of the network state relation at each time is expressed between each cell in the corresponding cell subgraph and each connected user terminal;
and inputting the plurality of second cell user graphs into a second power prediction model to obtain a transmission power prediction result of each cell, wherein the second power prediction model is obtained based on a second cell user graph sample and cell transmission power labels corresponding to the second cell user graph sample.
6. The method for controlling cell transmit power according to claim 5, wherein the plurality of cell subgraphs are divided by:
constructing a cell topological graph based on the neighbor cell relation of each cell;
And based on a spectral clustering algorithm, carrying out segmentation processing on the cell topological graph to obtain each cell subgraph.
7. A control apparatus for cell transmit power, comprising:
The system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a cell network state data set of a first time period, wherein the cell network state data set comprises neighbor cell relation information among cells, first network state information of each time of each cell in the first time period and connection relation information between the cells and user terminals, and second network state information of each connected user terminal of each time;
And the prediction module is used for determining a transmission power prediction result of each cell according to the cell network state data set, and controlling the transmission power of each cell.
8. An electronic device comprising a processor and a memory storing a computer program, characterized in that the processor implements the method of controlling cell transmit power according to any one of claims 1 to 6 when executing the computer program.
9. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the method of controlling cell transmit power according to any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the method of controlling the cell transmit power of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411432488.5A CN119342565A (en) | 2024-10-14 | 2024-10-14 | Method, device, electronic device and storage medium for controlling cell transmission power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411432488.5A CN119342565A (en) | 2024-10-14 | 2024-10-14 | Method, device, electronic device and storage medium for controlling cell transmission power |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119342565A true CN119342565A (en) | 2025-01-21 |
Family
ID=94261479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411432488.5A Pending CN119342565A (en) | 2024-10-14 | 2024-10-14 | Method, device, electronic device and storage medium for controlling cell transmission power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119342565A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1400805A (en) * | 2001-07-31 | 2003-03-05 | 株式会社Ntt都科摩 | Movable communication system, base station equipment and movable communication system controlling method |
| US20110250881A1 (en) * | 2008-09-29 | 2011-10-13 | Juergen Michel | Apparatus, Method, System and Program for Power Control or Power Setting |
| CN104185212A (en) * | 2014-08-14 | 2014-12-03 | 京信通信系统（中国）有限公司 | Method and system for uplink interference coordination of long term evolution (LTE) system |
| CN112929892A (en) * | 2021-02-24 | 2021-06-08 | 中国联合网络通信集团有限公司 | Power resource configuration method, device and storage medium |
| CN114980282A (en) * | 2021-02-24 | 2022-08-30 | 上海华为技术有限公司 | Power adjustment method and network management server |
-
2024
- 2024-10-14 CN CN202411432488.5A patent/CN119342565A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1400805A (en) * | 2001-07-31 | 2003-03-05 | 株式会社Ntt都科摩 | Movable communication system, base station equipment and movable communication system controlling method |
| US20110250881A1 (en) * | 2008-09-29 | 2011-10-13 | Juergen Michel | Apparatus, Method, System and Program for Power Control or Power Setting |
| CN104185212A (en) * | 2014-08-14 | 2014-12-03 | 京信通信系统（中国）有限公司 | Method and system for uplink interference coordination of long term evolution (LTE) system |
| CN112929892A (en) * | 2021-02-24 | 2021-06-08 | 中国联合网络通信集团有限公司 | Power resource configuration method, device and storage medium |
| CN114980282A (en) * | 2021-02-24 | 2022-08-30 | 上海华为技术有限公司 | Power adjustment method and network management server |
| US20230388941A1 (en) * | 2021-02-24 | 2023-11-30 | Huawei Technologies Co., Ltd. | Power adjustment method and network management server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nguyen et al. | Enabling AI in future wireless networks: A data life cycle perspective | |
| Challita et al. | Proactive resource management for LTE in unlicensed spectrum: A deep learning perspective | |
| EP3742669B1 (en) | Machine learning in radio access networks | |
| EP3790303A1 (en) | Predicting a radio spectrum usage | |
| Challita et al. | Deep learning for proactive resource allocation in LTE-U networks | |
| CN114641076A (en) | Edge computing unloading method based on dynamic user satisfaction in ultra-dense network | |
| US20240086715A1 (en) | Training and using a neural network for managing an environment in a communication network | |
| US20220021587A1 (en) | A method and an apparatus for fault prediction in network management | |
| Moysen et al. | A mobile network planning tool based on data analytics | |
| WO2019080771A1 (en) | Electronic device and method for wireless communication | |
| CN117896779B (en) | Load balancing method, device and equipment based on 5.5G autonomous network | |
| Lotfi et al. | Open RAN LSTM traffic prediction and slice management using deep reinforcement learning | |
| Sun et al. | Joint DDPG and unsupervised learning for channel allocation and power control in centralized wireless cellular networks | |
| WO2022214191A1 (en) | Methods and nodes in a communications network | |
| CN118802594A (en) | Communication network load prediction method, device, terminal and electronic equipment | |
| CN119342565A (en) | Method, device, electronic device and storage medium for controlling cell transmission power | |
| EP4195791A1 (en) | Selection of power control parameters | |
| Fernandes et al. | Reducing Unnecessary Handovers Using Logistic Regression in 5G Networks | |
| Assarian et al. | An efficient resource allocation scheme in a dense RFID network based on cellular learning automata | |
| Nieto et al. | Deep Reinforcement Learning-based Task Offloading in MEC for energy and resource-constrained devices | |
| Perera et al. | Dynamic spectrum fusion: An adaptive learning approach for hybrid NOMA/OMA in evolving wireless networks | |
| CN117580107B (en) | GNN base station association method and system for green wireless mesh network traffic field | |
| Mehrabi et al. | Neighbor auto-grouping graph neural networks for handover parameter configuration in cellular network | |
| Mohan et al. | Predicting the throughput of next generation ieee 802.11 wlans in dense deployments | |
| EP4604023A1 (en) | Collaborative training of a machine learning model considering estimated energy consumption |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |