CN112512057B - Network slicing abnormality identification method, device, equipment and computer storage medium - Google Patents

Abstract

The embodiment of the invention relates to the technical field of business support, and discloses a method, a device, equipment and a computer storage medium for identifying network slice abnormity, wherein the method comprises the following steps: acquiring the bearing information of the target network slice at the current moment; acquiring bearing information of the next moment of the adjacent network slice of the target network slice; calculating the bearing variation of the target network slice according to the bearing information at the current moment and the bearing information at the next moment; and determining whether the target network slice is abnormal or not according to the bearing variation and a preset error value. Through the mode, the abnormal network slice can be more accurately identified.

Description

Network slicing exception identification method, device, equipment and computer storage medium

technical field

Embodiments of the present invention relate to the technical field of business support, and in particular to a method, device, device, and computer storage medium for identifying abnormalities in network slices.

Background technique

In a 5G (5th-Generation, fifth-generation mobile communication technology) network, since different network application scenarios correspond to different service qualities, a physical network can be divided into multiple logical networks that support different network application scenarios. A network The application scenario supports a class of services, and a logical network is a network slice.

In the process of implementing the embodiment of the present invention, the inventors found that: the current way of identifying network slices is mainly to monitor the abnormality of the hardware in the network, and when the traffic volume is large and other situations will also cause network Slicing is abnormal, so the accuracy of existing 5G network slice anomaly identification is low.

Contents of the invention

In view of the above problems, embodiments of the present invention provide a network slice anomaly identification method, device, device, and computer storage medium, which overcome the above problems or at least partially solve the above problems.

According to an aspect of an embodiment of the present invention, there is provided a network slice anomaly identification method, the method comprising: obtaining bearer information of a target network slice at a current moment; acquiring bearer information of a network slice adjacent to the target network slice at a next moment ; Calculate the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment; determine whether the target network slice is abnormal according to the bearer variation and a preset error value .

In an optional manner, the preset error value is determined by machine learning.

In an optional manner, after acquiring the bearer information of the network slice adjacent to the target network slice at the next moment, the method further includes: determining the target network slice according to the bearer information at the current moment access users; obtain the reported data of the access users; determine the actual outgoing users among the access users according to the reported data; wherein, the actual outgoing users are located in the target network at the current moment An access user within the coverage of the slice but outside the coverage of the target network slice at the next moment; associating the bearer information at the current moment and the bearer information at the next moment with the actual outgoing user The bearer information is removed.

In an optional manner, the calculating the bearer change amount of the target network slice according to the bearer information at the current moment and the bearer information at the next moment is specifically: according to the bearer information at the current moment information, determine the current carrying capacity of the target network slice; calculate the migration from the target network slice to the adjacent network slice of the target network slice at the next time according to the carrying information at the next moment and the current carrying capacity The load variation of .

In an optional manner, the determining whether the target network slice is abnormal according to the bearer variation and the preset error value is specifically: when the bearer variation exceeds the preset error value , it is determined that the target network slice is abnormal, and a migration overrun warning is sent.

In an optional manner, the current bearer amount includes a current user access amount, the bearer change amount includes a user migration amount, and the preset error value includes a preset user error value; and/or, the The current load includes a current CPU resource usage, the load change includes a CPU resource migration, and the preset error value includes a preset CPU error value; and/or, the current load includes a current memory usage, so The load change amount includes a memory migration amount, and the preset error value includes a preset memory error value; and/or, the current load amount includes a current storage usage amount, the load change amount includes a storage migration amount, and the preset The set error value includes a preset stored error value.

In an optional manner, the determining whether the target network slice is abnormal according to the bearer change amount and the preset error value is specifically: combining the user migration amount in the bearer change amount with the preset The product of the user weight value, the product of the CPU resource migration amount in the load variation and the preset CPU weight value, the product of the memory resource migration in the load variation and the preset memory weight value, and the load The product of the storage resource migration amount in the variation and the preset storage weight value is summed to obtain the total amount of parameter variation; when the total amount of parameter variation exceeds a preset error value, it is determined that the network slice is abnormal.

According to another aspect of the embodiments of the present invention, there is provided a network slice anomaly identification device, including: a first acquisition module, configured to acquire the bearer information of the target network slice at the current moment; a second acquisition module, configured to acquire the target The bearer information of the network slice adjacent to the network slice at the next moment; the calculation module is used to calculate the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment; the first determination A module, configured to determine whether the target network slice is abnormal according to the bearer variation and a preset error value.

According to another aspect of the embodiments of the present invention, there is provided a network slice anomaly identification device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface communicate through the The bus completes mutual communication; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the above-mentioned network slice exception identification method.

According to yet another aspect of the embodiments of the present invention, a computer storage medium is provided, and at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to execute the above-mentioned network slice anomaly identification method corresponding operation.

In the embodiment of the present invention, by obtaining the bearer information of the target network slice at the current moment and the bearer information of its adjacent network slice at the next moment, calculate the bearer change amount of the target network slice migrating to its adjacent network slice, and compare the bearer change amount with the preset The size of the error value is used to determine whether the target network slice is abnormal. Compared with the prior art, the embodiment of the present invention judges whether the target network slice is abnormal by the magnitude of the bearer variation of the target network slice migrating to its adjacent network slices, instead of judging whether the target network slice is abnormal by monitoring the fault condition of the hardware. Anomalies, which can identify network slice anomalies caused by other situations such as large traffic volumes, so the identification accuracy is higher.

The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and The advantages can be more obvious and understandable, and the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same parts. In the attached picture:

FIG. 1 shows a flow chart of a network slice anomaly identification method provided by an embodiment of the present invention;

FIG. 2 shows a flow chart of a network slice anomaly identification method provided by another embodiment of the present invention;

FIG. 3 shows a flow chart of sub-steps for calculating the bearer variation of a target network slice in an embodiment of the present invention;

FIG. 4 shows a flow chart of sub-steps for determining whether a target network slice is abnormal in an embodiment of the present invention;

Fig. 5 shows a schematic structural diagram of a network slice anomaly identification device provided by an embodiment of the present invention;

FIG. 6 shows a schematic structural diagram of a network slice anomaly identification device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

In a 5G network, network services are rich and diverse, and different network services have different requirements on the network. For example, network services such as autonomous driving and remote control require the network to have ultra-low latency and ultra-high reliability; network services such as augmented reality/virtual reality require the network to have ultra-high bandwidth; Income and ultra-low power saving; network services such as drones and high-speed rail require high mobility of the network. In order to meet the needs of these different types of network services, the 5G network introduces network slicing technology, which combines a large number of physical network infrastructures into virtual logical network resources and divides them into small virtual logical network units according to each application scenario of the 5G network. Information interaction and transmission are realized through API interfaces and other means. The types of network slicing usually include eMBB (Enhanced MobileBroadband, enhanced mobile broadband), mMTC (Massive Machine Type Communication, large-scale machine-type communication) and uRLLC (Ultra-reliable and Low Latency Communication, ultra-reliable and low-latency communication) These three types. A user can access network slices corresponding to different network services through a UE (User Equipment, user equipment), so as to perform different network services. The UE may be a wireless terminal, such as a mobile phone, computer, tablet computer, personal digital assistant (personal digital assistant, PDA), mobile Internet device (mobile Internet device, MID), wearable device, Internet protocol (Internet Protocol, IP) Telephones, network printers and e-book readers (e-book readers), etc. Network slicing can be managed by a management device, which can be any device with network slicing management functions, such as a slice management system, policy control center, and intelligent analysis center. Among them, the slice management system can be a functional module in a certain server, or it can be a separate server. The network administrator can create network slices, delete network slices, and transfer some user equipment in a certain network slice through the slice management system. Migrating to another network slice etc. Network slicing includes RAN slicing, core network slicing and transmission slicing. Wherein, the RAN slice is equivalent to an overlay network of one or more base stations, which is used for connecting the UE to the network.

Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

Please refer to FIG. 1. FIG. 1 shows a flow chart of a network slicing anomaly identification method provided by an embodiment of the present invention. The method includes the following steps:

Step S110: Obtain bearer information of the target network slice at the current moment.

In this step, the target network slice refers to a network slice that needs to be identified abnormally, and the bearer information can be obtained through the above-mentioned slice management system, which includes information of access users of the target network slice. The information of the access user includes the IMSI (International Mobile Subscriber Identity, International Mobile Subscriber Identity) information of the access user and the CPU (Central Processing Unit, central processing unit) resource amount, memory resource amount and Amount of storage resources. Wherein, the amount of memory resources refers to the resource amount of the memory bar of the server occupied by the access user, and the amount of storage resource refers to the amount of hard disk resource of the server occupied by the access user.

Step S120: Obtain bearer information of a network slice adjacent to the target network slice at a next moment.

In this step, the network slice adjacent to the target network slice refers to a network slice adjacent to the coverage area of the target network slice, which can be determined by the above-mentioned slice management system. If the target network slice is a RAN slice, the RAN slice is the network coverage area of the base station, and the base station includes multiple cells. Each cell has its neighboring cells, and the RAN slice corresponding to the base station of the neighboring cell of the cell corresponding to the target network slice is the adjacent network slice of the target network slice. The next moment refers to a moment after the current moment mentioned in step S110, if the current moment is tk, the next moment is usually t(k+1). Both the bearer information of the target network slice and the bearer information of adjacent network slices of the target network slice will be periodically updated, that is, the target network slice and its adjacent network slices will have a set of bearer information at the current tk. There is also a set of bearer information at the time t(k+1), t(k+2)...t(k+n) thereafter.

Step S170: Calculate the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment.

In this step, the user’s IMSI information in the bearer information of the target network slice at the current moment and the bearer information of the adjacent network slice of the target network slice at the next moment can be used to determine whether to migrate from the target network slice to its adjacent network slice. The user migration amount of the network slice. For example, the IMSI information of the access users of the target network slice at the current time tk are S1, S2, S3 and S4 respectively, while the IMSI information of the access users of the adjacent network slices of the target network slice at the next time t(k+1) are respectively are S1, S2, S3, and S5, which means that the target network slice will migrate to its adjacent network slices at the next moment to access users S1, S2, and S3. Therefore, the user migration amount of the target network slice is 3. At the same time, the amount of CPU resources, memory resources, and storage resources occupied by access users S1, S2, and S3 at the current moment can be regarded as the CPU resource migration amount, memory migration amount, and storage migration amount of the target network slice, respectively. The user migration amount and/or the CPU resource migration amount and/or the memory migration amount and/or the storage migration amount may be regarded as the load change amount in this step.

Step S180: Determine whether the target network slice is abnormal according to the bearer variation and a preset error value.

Usually, a network slice occasionally migrates out users to its adjacent network slices when there is no abnormality, and the preset error value is the allowable number of user migrations and/or the amount of CPU resource migration and/or Memory migration and/or storage migration. Therefore, the preset error value can also be divided into a preset user error value, a preset CPU error value, a preset memory error value, and a preset storage error value. And when the bearer variation of the target network slice exceeds these error values, it can be explained that the user migration of the target network slice is not an accidental event, and then it can be determined that the target network slice is abnormal.

In some embodiments, the preset error value may be determined by machine learning. Specifically, the predicted anomaly identification result can be obtained by comparing the amount of change in load capacity of the network slices that already have anomalies and those without anomalies migrating to their adjacent network slices with a preset error value. Then compare the predicted abnormality recognition result with the actual abnormality of the network slice, and adjust the preset error value according to the result to make all the predicted abnormality recognition results consistent with the actual abnormality, so as to obtain the predicted Set the error value. In addition, in the process of actually applying the embodiment of the present invention to identify the abnormality of the target network slice, it is also possible to compare the identification results obtained in the embodiment of the present method with the results of manual verification by the operation and maintenance personnel to compare the preset The error value is continuously optimized and adjusted to ensure the recognition accuracy of the embodiment of the present invention.

It should be noted that if the input load change amount is one or more of user migration amount, CPU resource migration amount, memory migration amount, and storage migration amount, the preset error value obtained through machine learning also includes the preset error value correspondingly. One or more items of user error value, preset CPU error value, preset memory error value and preset storage error value are set.

In the embodiment of the present invention, by obtaining the bearer information of the target network slice at the current moment and the bearer information of its adjacent network slice at the next moment, calculate the bearer change amount of the target network slice migrating to its adjacent network slice, and compare the bearer change amount with the preset The size of the error value is used to determine whether the target network slice is abnormal. Compared with the prior art, the embodiment of the present invention judges whether the target network slice is abnormal by the magnitude of the bearer variation of the target network slice migrating to its adjacent network slices, instead of judging whether the target network slice is abnormal by monitoring the fault condition of the hardware. Anomalies, which can identify network slice anomalies caused by other situations such as large traffic volumes, so the identification accuracy is higher.

In some embodiments, the migration of the access users in the target network slice to its adjacent network slice may also be caused by changes in the actual locations of the access users, rather than due to abnormality of the target network slice. Therefore, as shown in FIG. 2 , it shows a flow chart of a method for identifying network slice anomalies provided by another embodiment of the present invention. In this embodiment, the method further includes after step S120:

Step S130: Determine the access users of the target network slice according to the bearer information at the current moment.

As described in step S110, the bearer information of the target network slice includes the IMSI information of the access users of the target network slice, and the access users of the target network slice can be determined through the IMSI information in the bearer information.

Step S140: Obtain the reported data of the access user.

Step S150: According to the reported data, determine the actual moving-out user among the access users; wherein, the actual moving-out user is located within the coverage of the target network slice at the current moment but located at the Access users outside the coverage of the target network slice.

Wherein, the reported data may be the MR data reported by the user equipment of the access user or the latitude and longitude data reported by the mobile phone business hall APP on the user equipment, and the position of the access user at each moment can be located according to these data. After that, the coverage of the target network slice and the base stations contained in the adjacent network slices can be determined by obtaining the engineering parameters from the basic data of the base station. By combining the location of the access user at the current moment and the next moment and the coverage of the target network slice and its adjacent network slices, it can be determined whether the access user of the target network slice is located at the current moment of the target network slice. In the coverage area, but outside the coverage area of the target network slice at the next moment, such an access user can be determined as the actual outgoing user, indicating that it has moved out of the coverage area of the target network slice.

Step S160: Remove the bearer information associated with the actual outgoing user from the bearer information at the current moment and the bearer information at the next moment.

Since the actual migrating user is not within the coverage of the target network slice at the next moment, it must not be able to access the target network slice, but can only access other network slices. Therefore, the user migration in this situation is not caused by the abnormality of the target network slice, so it is necessary to remove the bearer information associated with the actual outgoing user to improve the accuracy of abnormality identification in the embodiment of the present invention. Specifically, the IMSI information, occupied CPU resources, occupied memory resources, and occupied storage resources of the actually migrated user in the bearer information of the target network slice and its adjacent network slices will all be eliminated, that is, the subsequent step S170 calculates The data of these actually migrated users is no longer considered when bearing the amount of change.

In the embodiment of the present invention, by adding the step of determining the actual moving-out user and removing the bearer information associated with the actual moving-out user, the bearer change of the target network slice caused by the access user actually moving out of the coverage of the target network slice Exclusion improves the accuracy of determining whether the target network is abnormal by comparing the bearer variation of the target network slice with the preset error value.

For the above step S170, it can be implemented in many ways. As shown in FIG. 3, it shows a flow chart of the sub-steps for calculating the bearer variation of the target network slice in the embodiment of the present invention. The implementation of step S170 is specifically as follows:

Step S171: Determine the current bearer capacity of the target network slice according to the bearer information at the current moment.

As described in step S110, the bearer information of the target network slice includes the IMSI information of the access user and the amount of CPU resources, memory resources, and storage resources occupied by each access user. Thus, the current bearer capacity can be obtained by summing the number of access users of the target network slice at the current moment and the amount of resources occupied by each access user. For example, the current access users of the target network slice are [S1, S2, S3, and S4], and the amount of CPU resources, memory resources, and storage resources occupied by them are [C1, C2, C3, and C4], [M1 . They are 4, C1+C2+C3+C4, M1+M2+M3+M4 and N1+N2+N3+N4, respectively. In addition, the current bearer amount also includes the IMSI information of each access user at the current moment, so as to calculate the bearer change amount subsequently.

Step S172: According to the bearer information at the next moment and the current bearer amount, calculate the bearer change amount for migrating from the target network slice to an adjacent network slice of the target network slice at the next moment.

In this step, the load change amount can be divided into one or more of user migration amount, CPU resource migration amount, memory migration amount, and storage migration amount. User access and/or CPU resource usage and/or memory usage and/or storage usage of the network slice, or a ratio between them and the current carrying capacity of the target network slice. If the current access users of the target network slice are [S1, S2, S3, and S4]; and there are two adjacent network slices of the target network slice, their access users at the next moment are [S1, S5, S6] respectively. and S7] and [S2, S8, S9 and S10]. From this, it can be determined that the users of the target network slice to migrate to the adjacent network slice at the next moment are S1 and S2, so the user migration amount of the target network slice is 2 or 2/4. In addition, according to the amount of CPU resources, memory resources, and storage resources occupied by users S1 and S2 at the current moment, the CPU resource migration amount, memory migration amount, and storage migration amount of the target network slice can also be calculated. For example, if the current CPU resource usage, current memory usage, and current storage usage are respectively C1+C2+C3+C4, M1+M2+M3+M4, and N1+N2+N3+N4, among them, users S1 and S2 The corresponding amounts of CPU resources, memory resources, and storage resources occupied at the current moment are respectively C1 and C2, M1 and M2, and N1 and N2. At this time, the amount of CPU resource migration, memory migration, and storage migration of the target network slice are respectively C1+C2 or (C1+C2)/(C1+C2+C3+C4), M1+M2 or (M1+M2)/(M1+M2+M3+M4) and N1+N2 or (N1+N2) /(N1+N2+N3+N4).

It can be understood that: in other embodiments, the bearer change amount is not limited to the above description, it may also be other parameters representing the bearer change state of the target network slice, for example, the bearer change amount may also be The sum of the carrying capacity of adjacent network slices and the carrying capacity migrated from its adjacent network slices to the target network slice. If the current access users of the target network slice are [S1, S2, S3 and S4], the current access users of the adjacent network slices of the target network slice are [S5, S6, S7 and S8], and the next target network slice is [S5, S6, S7 and S8]. The network slice and its adjacent network slices are [S5, S6, S3, and S4] and [S1, S2, S7, and S8] respectively. It can be shown that the users who migrate out of the target network slice at the next moment are S1 and S2, and The users migrating into the target network slice are S5 and S6. Therefore, the user migration amount in the bearer variation of the target network slice is 4 at this time.

For the above step S180, there may be multiple implementations. In some embodiments, the implementation of step S180 is specifically: when the bearer variation exceeds the preset error value, determine that the target network slice is abnormal, And send migration limit warning.

In this step, it is possible to judge whether the target network slice is abnormal based on the amount of bearer variation of the target network slice, and decide whether to send a migration overrun warning to notify the operation and maintenance personnel to troubleshoot.

Specifically, when the current bearer amount includes the current user access amount, and the bearer change amount includes the user migration amount, and the preset error value includes a preset user error value, step S180 is: when the user migration amount When the preset user error value is exceeded, it is determined that the target network slice is abnormal, and a user migration exceeding limit warning is sent.

When the current load includes the current CPU resource occupancy, and the load change includes CPU resource migration, the preset error value includes a preset CPU error value. Step S180 is: when the CPU resource migration exceeds When the preset CPU error value is determined, it is determined that the target network slice is abnormal, and a CPU resource migration overrun warning is sent.

When the current carrying amount includes the current memory resource occupancy, and the carrying change includes the memory resource migration amount, the preset error value includes a preset memory error value, and step S180 is: when the memory resource migration amount exceeds When the preset memory error value is determined, it is determined that the target network slice is abnormal, and a memory resource migration overrun warning is sent.

When the current carrying amount includes the current storage resource occupancy, and the carrying change includes the storage resource migration amount, the preset error value includes the preset storage error value, step S180 is: when the storage resource migration amount exceeds When the preset storage error value is determined, it is determined that the target network slice is abnormal, and a storage resource migration overrun warning is sent.

According to the different types of load capacity of the input target network slice, the embodiment of the present invention performs different types of abnormal identification and sends different types of early warnings, so that the operation and maintenance personnel can troubleshoot the cause of the fault of the target network slice according to the type of early warning. .

In some other embodiments, the above step S180 may also be implemented in other ways, as shown in FIG. 4 , which shows a flow chart of sub-steps for determining whether the target network slice is abnormal in the embodiment of the present invention. Step S180 is specifically:

Step S181: Calculate the product of the user migration amount in the load change amount and the preset user weight value, the product of the CPU resource migration amount in the load change amount and the preset CPU weight value, and the user migration amount in the load change amount The product of the memory resource migration amount and the preset memory weight value and the product of the storage resource migration amount and the preset storage weight value in the load variation amount are summed to obtain the total amount of parameter changes.

Step S182: When the total amount of parameter changes exceeds a preset error value, determine that the network slice is abnormal.

When the bearer variation includes user migration, CPU resource migration, memory migration, and storage migration, the embodiment of the present invention configures different weight values for them respectively, and compares the sum of them with the preset error value, Therefore, it is comprehensively judged whether the target network slice is abnormal from the four dimensions of the target network slice. Specifically, if the user migration amount, CPU resource migration amount, memory migration amount, and storage migration amount of the target network slice are respectively a, b, c, and d, and the preset user weight value, preset CPU weight value, preset memory The weight value and preset storage weight value are k1, k2, k3 and k4 respectively, and the total amount of parameter change is a*k1+b*k2+c*k3+d*k4. If the load variation only includes part of user migration, CPU resource migration, memory migration, and storage migration, you can set the weight value corresponding to the migration not included in the load variation to 0. For example, if If the load variation does not include the CPU resource migration, the default CPU weight is 0.

In the embodiment of the present invention, by obtaining the bearer information of the target network slice at the current moment and the bearer information of its adjacent network slice at the next moment, calculate the bearer change amount of the target network slice migrating to its adjacent network slice, and compare the bearer change amount with the preset The size of the error value is used to determine whether the target network slice is abnormal. Compared with the prior art, the embodiment of the present invention judges whether the target network slice is abnormal by the magnitude of the bearer variation of the target network slice migrating to its adjacent network slices, instead of judging whether the target network slice is abnormal by monitoring the fault condition of the hardware. Anomalies, which can identify network slice anomalies caused by other situations such as large traffic volumes, so the identification accuracy is higher.

FIG. 5 shows a schematic structural diagram of an apparatus for identifying anomalies in network slices according to an embodiment of the present invention. As shown in FIG. 5 , the apparatus 100 includes a first acquisition module 10 , a second acquisition module 20 , a calculation module 30 and a first determination module 40 .

The first obtaining module 10 is used to obtain the bearer information of the target network slice at the current moment; the second obtainment module 20 is used to obtain the bearer information of the adjacent network slice of the target network slice at the next moment; the calculation module 30 is used to obtain the bearer information according to The bearer information at the current moment and the bearer information at the next moment calculate the bearer variation of the target network slice; the first determining module 40 is configured to determine the bearer variation according to the bearer variation and a preset error value. Whether the target network slice is abnormal.

In an optional manner, the preset error value is determined by machine learning.

In an optional manner, the apparatus 100 further includes a second determination module 50 , a third acquisition module 60 , a third determination module 70 and a rejection module 80 .

The second determination module 50 is configured to determine the access user of the target network slice according to the bearer information at the current moment; the third acquisition module 60 is configured to acquire the reported data of the access user; the third determination module 70. Determine, according to the reported data, an actual outgoing user among the access users; wherein, the actual outgoing user is located within the coverage of the target network slice at the current moment but located at the target network slice at the next moment. The access user outside the coverage of the target network slice; the removing module 80 is configured to remove the bearer information associated with the actual outgoing user from the bearer information at the current moment and the bearer information at the next moment.

In an optional manner, the calculation module 30 is specifically: according to the bearer information at the current moment, determine the current bearer capacity of the target network slice; according to the bearer information at the next moment and the current The bearer amount is used to calculate the change amount of the bearer migrating from the target network slice to an adjacent network slice of the target network slice at the next moment.

In an optional manner, the first determination module 40 is specifically: when the bearer variation exceeds the preset error value, determine that the target network slice is abnormal, and send a migration overrun warning.

In an optional manner, the current bearer amount includes a current user access amount, the bearer change amount includes a user migration amount, and the preset error value includes a preset user error value; and/or, the The current load includes a current CPU resource usage, the load change includes a CPU resource migration, and the preset error value includes a preset CPU error value; and/or, the current load includes a current memory usage, so The load change amount includes a memory migration amount, and the preset error value includes a preset memory error value; and/or, the current load amount includes a current storage usage amount, the load change amount includes a storage migration amount, and the preset The set error value includes a preset stored error value.

In an optional manner, the first determination module 40 is specifically: the product of the user migration amount in the bearer variation and the preset user weight value, the CPU resource migration amount in the bearer variation and the product of the preset CPU weight value, the product of the memory resource migration amount in the load variation amount and the preset memory weight value, and the product of the storage resource migration amount in the load variation amount and the preset storage weight value are summed , to obtain a total amount of parameter changes; when the total amount of parameter changes exceeds a preset error value, it is determined that the network slice is abnormal.

In the embodiment of the present invention, the first acquisition module 10 and the second acquisition module 20 respectively acquire the bearer information of the target network slice at the current moment and its adjacent network slice at the next moment, and then use the calculation module 30 to calculate the migration of the target network slice to its corresponding Adjacent to the bearer variation of the network slice, and determine whether the target network slice is abnormal by comparing the bearer variation with a preset error value through the first determining module 40 . Compared with the prior art, the embodiment of the present invention judges whether the target network slice is abnormal by the magnitude of the bearer variation of the target network slice migrating to its adjacent network slices, instead of judging whether the target network slice is abnormal by monitoring the fault condition of the hardware. Anomalies, which can identify network slice anomalies caused by other situations such as large traffic volumes, so the identification accuracy is higher.

An embodiment of the present invention provides a non-volatile computer storage medium, the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the network slice anomaly identification method in any of the above method embodiments.

FIG. 6 shows a schematic structural diagram of a network slice anomaly identification device provided by an embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the network slicing anomaly identification device.

As shown in FIG. 6 , the network slice anomaly identification device may include: a processor (processor) 202 , a communication interface (Communications Interface) 204 , a memory (memory) 206 , and a communication bus 208 .

Wherein: the processor 202 , the communication interface 204 , and the memory 206 communicate with each other through the communication bus 208 . The communication interface 204 is used to communicate with network elements of other devices such as clients or other servers. The processor 202 is configured to execute the program 210, and specifically, may execute relevant steps in the above embodiments of the method for identifying anomalies in network slices.

Specifically, the program 210 may include program codes including computer operation instructions.

The processor 202 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the network slicing exception identification device can be the same type of processor, such as one or more CPUs; or different types of processors, such as one or more CPUs and one or more ASICs .

The memory 206 is used to store the program 210 . The memory 206 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 210 can specifically be used to make the processor 202 perform the following operations:

Obtain the bearer information of the target network slice at the current moment;

Acquiring the bearer information of the adjacent network slice of the target network slice at the next moment;

calculating the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment;

Determine whether the target network slice is abnormal according to the bearer variation and a preset error value.

In an optional manner, the program 210 may be further specifically configured to enable the processor 202 to perform the following operations:

Determine the access users of the target network slice according to the bearer information at the current moment;

Obtain the reported data of the access user;

According to the reported data, determine the actual outgoing user among the access users; wherein, the actual outgoing user is located within the coverage of the target network slice at the current moment but located in the target network slice at the next moment Access users outside the coverage area;

The bearer information associated with the actual moving-out user is removed from the bearer information at the current moment and the bearer information at the next moment.

In an optional manner, the program 210 may be further specifically configured to enable the processor 202 to perform the following operations:

Determine the current bearer capacity of the target network slice according to the bearer information at the current moment;

According to the bearer information at the next moment and the current bearer capacity, calculate the bearer change amount for migrating from the target network slice to an adjacent network slice of the target network slice at the next moment.

In an optional manner, the program 210 may be further specifically configured to enable the processor 202 to perform the following operations:

When the bearer variation exceeds the preset error value, it is determined that the target network slice is abnormal, and a migration exceeding limit warning is sent.

In an optional manner, the program 210 may be further specifically configured to enable the processor 202 to perform the following operations:

The product of the user migration amount in the bearer variation and a preset user weight value, the product of the CPU resource migration in the bearer variation and a preset CPU weight value, and the memory resource migration in the bearer variation The product of the amount and the preset memory weight value and the product of the storage resource migration amount in the load variation and the preset storage weight value are summed to obtain the total amount of parameter changes;

When the total amount of parameter changes exceeds a preset error value, it is determined that the network slice is abnormal.

In the embodiment of the present invention, by obtaining the bearer information of the target network slice at the current moment and the bearer information of its adjacent network slice at the next moment, calculate the bearer change amount of the target network slice migrating to its adjacent network slice, and compare the bearer change amount with the preset The size of the error value is used to determine whether the target network slice is abnormal. Compared with the prior art, the embodiment of the present invention judges whether the target network slice is abnormal based on the magnitude of the bearer variation of the target network slice migrating to its adjacent network slices, instead of judging whether the target network slice is abnormal by monitoring hardware failures. Anomalies, which can identify network slice anomalies caused by other situations such as large traffic volumes, so the identification accuracy is higher.

An embodiment of the present invention provides an executable program, and the executable program can execute the network slice anomaly identification method in any of the above method embodiments.

The algorithms or programs presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present invention are not directed to any particular programming language. It should be understood that various programming languages can be used to implement the contents of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline the present disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the embodiments of the invention are sometimes grouped together into a single implementation examples, figures, or descriptions thereof. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims (9)

1. A network slicing abnormal identification method, characterized in that, comprising: Obtain the bearer information of the target network slice at the current moment; Acquiring the bearer information of the adjacent network slice of the target network slice at the next moment; Determine the access users of the target network slice according to the bearer information at the current moment; Obtain the reported data of the access user; According to the reported data, determine the actual outgoing user among the access users; wherein, the actual outgoing user is located within the coverage of the target network slice at the current moment but located in the target network slice at the next moment Access users outside the coverage area; removing the bearer information associated with the actual moving-out user from the bearer information at the current moment and the bearer information at the next moment; calculating the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment; Determine whether the target network slice is abnormal according to the bearer variation and a preset error value. 2. The method according to claim 1, wherein the preset error value is determined by machine learning. 3. The method according to any one of claims 1-2, wherein the bearer change of the target network slice is calculated according to the bearer information at the current moment and the bearer information at the next moment amount, specifically: Determine the current bearer capacity of the target network slice according to the bearer information at the current moment; According to the bearer information at the next moment and the current bearer capacity, calculate the bearer change amount for migrating from the target network slice to an adjacent network slice of the target network slice at the next moment. 4. The method according to claim 3, wherein the determining whether the target network slice is abnormal according to the bearer variation and the preset error value is specifically: When the bearer variation exceeds the preset error value, it is determined that the target network slice is abnormal, and a migration exceeding limit warning is sent. 5. The method according to claim 4, wherein the current bearer amount includes a current user access amount, the bearer change amount includes a user migration amount, and the preset error value includes a preset user error value; And/or, the current load includes a current CPU resource occupation, the load change includes a CPU resource migration, and the preset error value includes a preset CPU error value; and/or, the current load includes The current memory usage, the load variation includes memory migration, and the preset error value includes a preset memory error value; and/or, the current load includes the current storage usage, and the load variation includes storage Migration amount, the preset error value includes a preset storage error value. 6. The method according to claim 3, wherein the determining whether the target network slice is abnormal according to the bearer variation and the preset error value is specifically: The product of the user migration amount in the bearer variation and a preset user weight value, the product of the CPU resource migration in the bearer variation and a preset CPU weight value, and the memory resource migration in the bearer variation The product of the amount and the preset memory weight value and the product of the storage resource migration amount in the load variation and the preset storage weight value are summed to obtain the total amount of parameter changes; When the total amount of parameter changes exceeds a preset error value, it is determined that the network slice is abnormal. 7. A network slicing anomaly identification device, characterized in that, comprising: The first obtaining module is used to obtain the bearer information of the target network slice at the current moment; The second obtaining module is used to obtain the bearer information of the adjacent network slice of the target network slice at the next moment; The second determination module is configured to determine the access users of the target network slice according to the bearer information at the current moment; A third acquiring module, configured to acquire the reported data of the access user; The third determining module is configured to determine the actual moving-out user among the access users according to the reported data; wherein, the actual moving-out user is located within the coverage of the target network slice at the current moment but in the next access users located outside the coverage of the target network slice at all times; A removing module, configured to remove the bearer information associated with the actual outgoing user from the bearer information at the current moment and the bearer information at the next moment; A calculation module, configured to calculate the bearer variation of the target network slice according to the bearer information at the current moment and the bearer information at the next moment; The first determining module is configured to determine whether the target network slice is abnormal according to the bearer variation and a preset error value. 8. A network slice anomaly identification device, characterized in that it includes: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete mutual communication through the communication bus ; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the network slice exception identification method according to any one of claims 1-6. 9. A computer storage medium, characterized in that at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to perform the network slice exception identification according to any one of claims 1-6 method.

Images