Resource configuration method for network slice, and base station and storage medium

By obtaining and updating the quality evaluation indicators of wireless resource management strategies and dynamically adjusting network slice resources, the waste and low utilization rate caused by the fixed resources in the existing technology is solved, and the utilization rate of network resources and the number of connected users are improved.

WO2024234878A1PCT designated stage expired Publication Date: 2024-11-21ZTE CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/086959
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-18
Filing Date
2024-04-10
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

The wireless resource management strategy of existing network slices remains fixed after configuration, resulting in unchanged resources that cannot be dynamically adjusted, resulting in waste of network resources, low RRC connection users and low DRB utilization.

Method used

By obtaining the quality evaluation indicators of the wireless resource management strategy, predicting its attribute information, and reconfiguring the network resources of the network slice according to the updated strategy, dynamic adjustment of resources is achieved.

Benefits of technology

The network resource utilization rate, RRC connection number and DRB utilization rate of network slices are improved, and the problems of waste of resources and low utilization rate are solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024086959_21112024_PF_FP_ABST
    Figure CN2024086959_21112024_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the embodiments of the present disclosure are a resource configuration method for a network slice, and a base station and a computer storage medium. The method comprises: acquiring a quality evaluation index of each radio resource management policy; determining predicted attribute information of each radio resource management policy according to the quality evaluation index of each radio resource management policy; and updating the corresponding radio resource management policy according to the predicted attribute information, and reconfiguring a network resource for each network slice according to each updated radio resource management policy.
Need to check novelty before this filing date? Find Prior Art

Description

Resource configuration method, base station and storage medium for network slicing

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202310568346.0 filed on May 18, 2023, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present disclosure relates to the field of communication technologies, and in particular to a resource configuration method, base station, and storage medium for network slicing. Background Art

[0004] As one of the key technologies of the fifth generation mobile communication technology (5G), network slicing can create and maintain multiple dedicated, virtualized, and isolated logical networks based on shared physical network infrastructure to meet the differentiated network capability requirements of different customers. Resource isolation is one of the application values ​​of network slicing. It means that the network resources between different network slices can be isolated from each other. Resource isolation can be achieved through Radio Resource Management (RRM) policies and protection mechanisms. Through RRM policies, network resources can be allocated to each network slice according to different service level agreements, thereby configuring different network resources of different sizes for different network slices.

[0005] At present, the RRM policy is fixed after configuration, that is, the ratio of dedicated resources, priority resources and shared resources allocated to the network slice is fixed. The network resources allocated to the network slice by the RRM policy include dedicated resources, priority resources and shared resources. Since the dedicated resources configured for the network slice by the RRM policy can only be used exclusively by the configured network slice, when the configured network slice is not in use, other network slices cannot share this part of the resources, which will lead to problems such as waste of network resources, low number of Radio Resource Control (RRC) connected users, and low utilization of Data Radio Bearer (DRB).

[0006] Summary of the Invention

[0007] In a first aspect, an embodiment of the present disclosure provides a resource configuration method for a network slice, comprising: obtaining a quality evaluation indicator for each wireless resource management strategy, the quality evaluation indicator including at least one of a physical resource block utilization rate, a block error rate, a signal to interference plus noise ratio, a number of user accesses, and a resource saturation corresponding to the wireless resource management strategy; determining predicted attribute information of each wireless resource management strategy based on the quality evaluation indicator of each wireless resource management strategy; updating the corresponding wireless resource management strategy based on the predicted attribute information, and reconfiguring the network resources of each network slice based on each updated wireless resource management strategy.

[0008] In a second aspect, an embodiment of the present disclosure also provides a base station, comprising a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for realizing connection communication between the processor and the memory, wherein the computer program is executed by the processor so that the processor implements the resource configuration method for network slicing as described in the first aspect.

[0009] In a third aspect, an embodiment of the present disclosure further provides a computer storage medium for computer-readable storage, wherein the storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors, so that the one or more processors implement the resource configuration method for network slicing as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] FIG1 is a schematic block diagram of the structure of a base station provided by an embodiment of the present disclosure;

[0012] FIG2 is a flow chart of a resource configuration method for a network slice provided by an embodiment of the present disclosure;

[0013] FIG3 is a schematic diagram of a sub-step flow chart of the resource configuration method of the network slice in FIG2 ;

[0014] FIG4 is a schematic diagram of another sub-step flow chart of the resource configuration method for the network slice in FIG2 ;

[0015] FIG5 is a schematic diagram of a scenario for training a machine learning model in an embodiment of the present disclosure;

[0016] FIG6 is a schematic diagram of the configuration process of the RRM policy in an embodiment of the present disclosure; and

[0017] Figure 7 is a flow chart of another resource configuration method for network slicing provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0019] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all contents and operations / steps, nor do they have to be executed in the order described. For example, some operations /

[0020] The steps can also be decomposed, combined or partially merged, so the actual execution order may change according to the actual situation.

[0021] It should be understood that the terms used in this disclosure are only for the purpose of describing particular embodiments and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] Currently, the RRM policy is fixed after configuration, that is, the ratio of dedicated resources, priority resources and shared resources allocated to the network slice is fixed. The network resources allocated to the network slice by the RRM policy include dedicated resources, priority resources and shared resources. Since the dedicated resources configured for the network slice by the RRM policy can only be used exclusively by the configured network slice, when the configured network slice is not in use, other network slices cannot share this part of the resources, which will lead to problems such as waste of network resources, low number of RRC connected users, and low DRB utilization.

[0023] To solve the above problems, the embodiments of the present disclosure provide a resource configuration method, a base station and a storage medium for a network slice. The resource configuration method obtains the quality evaluation index of each wireless resource management policy, and based on the quality evaluation index of each wireless resource management policy, predicts the predicted attribute information of each wireless resource management policy, and then updates the corresponding wireless resource management policy according to the predicted attribute information, and reconfigures the network resources of each network slice according to each updated wireless resource management policy to realize dynamic adjustment of the network resources of the network slice, thereby greatly improving the utilization rate of the network resources of the network slice, the number of RRC connected users and the DRB utilization rate.

[0024] The following embodiments of the present disclosure are described in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0025] Please refer to FIG1 , which is a schematic block diagram of the structure of a base station provided by an embodiment of the present disclosure.

[0026] As shown in FIG1 , a base station 100 includes a processor 101 and a memory 102 . The processor 101 and the memory 102 are connected via a bus 103 , such as an I 2 C (Inter-Integrated Circuit) bus.

[0027] Specifically, processor 101 is used to provide computing and control capabilities to support the operation of the entire base station. Processor 101 can be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0028] Specifically, the memory 102 may be a Flash chip, a read-only memory (ROM), a magnetic disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0029] Those skilled in the art will understand that the structure shown in Figure 1 is merely a block diagram of a partial structure related to the embodiment of the present disclosure, and does not constitute a limitation on the base station to which the embodiment of the present disclosure is applied. A specific base station may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0030] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and implement any one of the network slice resource configuration methods provided in the embodiments of the present disclosure when executing the computer program.

[0031] In some embodiments, the processor 101 is configured to run a computer program stored in a memory, and when executing the computer program, the processor 101 implements the following steps: obtaining a quality evaluation indicator for each wireless resource management strategy, the quality evaluation indicator including at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to the wireless resource management strategy; determining predicted attribute information of each wireless resource management strategy based on the quality evaluation indicator of each wireless resource management strategy; updating the corresponding wireless resource management strategy based on the predicted attribute information, and reconfiguring the network resources of each network slice based on each updated wireless resource management strategy.

[0032] In some embodiments, when the processor 101 implements obtaining the quality evaluation index of each wireless resource management strategy, it is configured to implement the following steps: obtaining the resource configuration impact index of each of the network slices, the resource configuration impact index including at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses and resource saturation of the network slice; determining the quality evaluation index of each of the wireless resource management strategies based on the resource configuration impact index of one or more of the network slices corresponding to each of the wireless resource management strategies.

[0033] In some embodiments, the predicted attribute information includes first attribute information or second attribute information, the first attribute information includes a wireless resource management policy ratio group, the wireless resource management policy ratio group includes a wireless resource management policy dedicated ratio, a wireless resource management policy minimum ratio and a wireless resource management policy maximum ratio; the second attribute information includes one or more wireless resource management policy ratio groups and the effective time information corresponding to each of the wireless resource management policy ratio groups, the effective time information is used to indicate the time period in which the corresponding wireless resource management policy ratio group is effective, the wireless resource management policy ratio group includes a wireless resource management policy dedicated ratio, a wireless resource management policy minimum ratio and a wireless resource management policy maximum ratio.

[0034] In some embodiments, when the wireless resource management policy includes second attribute information, the processor 101 is further configured to implement the following steps: determining a target wireless resource management policy ratio group based on clock information and the second attribute information, and enabling the target wireless resource management policy ratio group.

[0035] In some embodiments, when the processor 101 determines the target wireless resource management policy ratio group based on the clock information and the second attribute information, it is configured to implement the following steps: when there is effective time information matching the clock information in the second attribute information, the wireless resource management policy ratio group corresponding to the matching effective time information is determined as the target wireless resource management policy ratio group.

[0036] In some embodiments, when the processor 101 determines the target wireless resource management policy ratio group based on the clock information and the second attribute information, it is also configured to implement the following steps: when there is no effective time information matching the clock information in the second attribute information, the preset wireless resource management policy ratio group is determined as the target wireless resource management policy ratio group.

[0037] In some embodiments, when the processor 101 determines the predicted attribute information of each wireless resource management policy based on the quality evaluation index of each wireless resource management policy, it is configured to implement the following steps: run a pre-trained policy attribute prediction model, perform policy attribute prediction processing based on the quality evaluation index of each wireless resource management policy, and obtain the predicted attribute information of each wireless resource management policy; in some embodiments, the policy attribute prediction model is obtained by iteratively training a preset machine learning model based on multiple sample data, and the sample data includes the quality evaluation index of the wireless resource management policy and the annotated attribute information.

[0038] In some embodiments, the network resources include physical resource block resources of the network slice.

[0039] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the base station described above can refer to the corresponding process in the following network slicing resource configuration method embodiment, which will not be repeated here.

[0040] Below, the resource configuration method for network slicing provided by the embodiment of the present disclosure will be described in detail with reference to the base station in Figure 1. It should be noted that the base station in Figure 1 is only used to explain the resource configuration method for network slicing provided by the embodiment of the present disclosure, but does not constitute a limitation on the application scenario of the resource configuration method for network slicing provided by the embodiment of the present disclosure.

[0041] Please refer to Figure 2, which is a flow chart of a resource configuration method for a network slice provided by an embodiment of the present disclosure. The resource configuration method is applied to a base station to improve the utilization rate of network resources, the number of RRC connected users, and the DRB utilization rate of the network slice.

[0042] As shown in Figure 2, the resource configuration method of the network slice includes steps S101 to S103.

[0043] In step S101, a quality evaluation index of each radio resource management strategy is obtained.

[0044] In this embodiment, the quality evaluation index of the radio resource management RRM strategy includes at least one of the physical resource block (PRB) utilization, block error rate (BLER), signal to interference plus noise ratio (SINR), number of user accesses and resource saturation corresponding to the RRM strategy. In some embodiments, the number of user accesses corresponding to the RRM strategy is the total number, average number or maximum number of user equipment (UE) carried by all network slices in the RRM strategy. The resource saturation corresponding to the RRM strategy is the saturation of the network resources configured in the RRM strategy.

[0045] In some embodiments, the RRM policy defines an RRMPolicy_ parameter, which includes resource type information (Resource Type), an RRM policy member list (rRMPolicyMemberList) and target attribute information, etc. The target attribute information includes an RRM policy ratio group or the target attribute information includes one or more RRM policy ratio groups and the corresponding effective time information of each RRM policy ratio group. The RRM policy ratio group includes an RRM policy dedicated ratio (rRMPolicyDedicatedRatio), an RRM policy minimum ratio (rRMPolicyMinRatio) and an RRM policy maximum ratio (rRMPolicyMaxRatio). The effective time information is used to indicate the time period in which the corresponding RRM policy ratio group is effective. It can be understood that if the attribute information of the RRM policy does not include effective time information, the RRM policy ratio group in the attribute information of the RRM policy is effective 24 hours a day until the RRM policy is updated.

[0046] In some embodiments, the resource type information defines the resource types constrained by the RRM policy, and the resource types include PRB resources, the number of RRC connected users, DRB utilization, etc. The RRM policy member list defines the RRM policy members (RRMPolicyMember) constrained by the RRM policy, and the RRM policy members can be defined by the Public Land Mobile Network (PLMNId) and the Single Network Slice Selection Assistance Information (S-NSSAI). PRB resources include dedicated resources, priority resources, and shared resources. The RRM policy dedicated ratio defines the ratio of dedicated resources. The RRM policy dedicated ratio and the RRM policy minimum ratio define the ratio of priority resources, which can be specifically expressed by the RRM policy minimum ratio minus the RRM policy dedicated ratio. The RRM policy maximum ratio and the RRM policy minimum ratio define the ratio of shared resources, which can be specifically expressed by the RRM policy maximum ratio minus the RRM policy minimum ratio.

[0047] It should be noted that the sum of the RRM policy-specific ratios defined by multiple RRM policies corresponding to the carriers of the base station is less than or equal to 100% at the same time. The sum of the RRM policy minimum ratios defined by multiple RRM policies corresponding to the carriers of the base station is less than or equal to 100% at the same time. The RRM policy-specific ratio, RRM policy minimum ratio, and RRM policy maximum ratio defined by the RRM policy must meet the following conditions: the RRM policy-specific ratio is less than or equal to the RRM policy minimum ratio, and the RRM policy minimum ratio is less than or equal to the RRM policy maximum ratio.

[0048] In some embodiments, the effective time information includes a repetition type and calendar information of the repetition type, the repetition type includes non-repetition, monthly repetition, or weekly repetition, and the calendar information includes one or more dates and one or more time periods in each date. When the repetition type is non-repetition, it means that the corresponding RRM policy ratio group is effective only in one or more time periods configured on the day; when the repetition type is monthly repetition, it means that the corresponding RRM policy ratio group is effective in one or more time periods on one or more days of the configured month; when the repetition type is weekly repetition, it means that the corresponding RRM policy ratio group is effective in one or more time periods on one or more days of the configured week.

[0049] For example, if the repetition type in the effective time information T1 is non-repetition, the date on which the effective time information is configured is May 10, 2023, and the configured time period is 13:31-17:30, then the RRM policy ratio group corresponding to the effective time information T1 is effective only during the time period 13:31-17:30 on May 10, 2023. For another example, if the repetition type in the effective time information T2 is monthly, the calendar information includes the dates 10th, 15th, and 20th, and the time periods corresponding to the 10th, 15th, and 20th are 9:01-12:00 am and 13:31-17:30 pm, then the RRM policy ratio group corresponding to the effective time information T2 is effective during the time periods 9:01-12:00 am and 13:31-17:30 pm on the 10th, 15th, and 20th of each month. The repetition type in the effective time information T3 is weekly repetition, and the dates included in the calendar information are Saturday and Sunday, and the time periods corresponding to Saturday and Sunday are both am07:00-pm23:00, then the RRM policy ratio group corresponding to the effective time information T3 is effective in the time periods of am07:00-pm23:00 on Saturday and Sunday every week.

[0050] In some embodiments, as shown in FIG3 , step S101 includes sub-steps S1011 to S1012 .

[0051] In sub-step S1011, the resource configuration impact index of each network slice is obtained.

[0052] In this embodiment, the resource configuration influencing index of the network slice includes at least one of the physical resource block utilization rate, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation of the network slice. In some embodiments, the number of user accesses of the network slice is the number of user devices carried by the network slice, and the resource saturation of the network slice is the saturation of the network resources configured for the network slice.

[0053] In sub-step S1012, the quality evaluation index of each wireless resource management strategy is determined based on the resource configuration impact index of one or more network slices corresponding to each wireless resource management strategy.

[0054] In this embodiment, since the RRM policy defines the resource configuration of one or more network slices, the quality evaluation index of the RRM policy can be accurately estimated through the resource configuration impact index of one or more network slices defined by the RRM policy.

[0055] In some embodiments, the method for determining the quality evaluation index of the wireless resource management policy based on the resource configuration impact index of one or more network slices corresponding to the wireless resource management policy can be: when the RRM policy defines the resource configuration of a network slice, the resource configuration impact index of the network slice is used as the quality evaluation index of the RRM policy; or, when the RRM policy defines the resource configuration of multiple network slices, the resource configuration impact index of each network slice is compared to determine the maximum resource configuration impact index, and the maximum resource configuration impact index is used as the quality evaluation index of the RRM policy; or, when the RRM policy defines the resource configuration of multiple network slices, the average value of the resource configuration impact index is calculated based on the resource configuration impact index of each network slice, and the average value of the resource configuration impact index is used as the quality evaluation index of the RRM policy; or, when the RRM policy defines the resource configuration of multiple network slices, the resource configuration impact index of each network slice is accumulated, and the accumulated result is used as the quality evaluation index of the RRM policy.

[0056] For example, if an RRM strategy defines the resource configuration of network slices A, B, and C, then the resource configuration impact indicators of network slices A, B, and C can be obtained, and the resource configuration impact indicators of network slices A, B, and C can be accumulated and averaged to obtain the quality evaluation index of this RRM strategy. Alternatively, if it is found through comparison that the resource configuration impact indicator of network slice B is the largest, then the resource configuration impact indicator of network slice B can be used as the quality evaluation index of this RRM strategy.

[0057] For example, if the physical resource block utilization rates of network slice A, network slice B, and network slice C are 80%, 85%, and 96%, respectively, then the average value of the three physical resource block utilization rates of 80%, 85%, and 96% can be calculated to be 87%, so 87% can be used as the physical resource block utilization rate of the RRM policy corresponding to network slices A, network slice B, and network slice C. Alternatively, if the maximum value of the three physical resource block utilization rates of 80%, 85%, and 96% is 96%, then 96% can be used as the physical resource block utilization rate of the RRM policy corresponding to network slices A, network slice B, and network slice C.

[0058] For another example, the number of user accesses to network slice A, network slice B, and network slice C are N1, N2, and N3 respectively, and N3 is greater than N2, and N2 is greater than N1. Then the average value of N1, N2, and N3 (N1+N2+N3) / 3 or the cumulative value of N1, N2, and N3 (N1+N2+N3) can be used as the number of user accesses for the RRM policy corresponding to network slices A, network slice B, and network slice C. Alternatively, the maximum value N3 among N1, N2, and N3 can be used as the number of user accesses for the RRM policy corresponding to network slices A, network slice B, and network slice C.

[0059] In step S102, prediction attribute information of each radio resource management policy is determined according to the quality evaluation index of each radio resource management policy.

[0060] In this embodiment, based on at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to each RRM strategy, the attribute information of each RRM strategy can be predicted and estimated, thereby obtaining the predicted attribute information of each RRM strategy, which facilitates the subsequent use of the predicted attribute information to update the RRM strategy.

[0061] In some embodiments, the method for determining the predicted attribute information of each radio resource management policy based on the quality evaluation indicator of each radio resource management policy may include: for each RRM policy, when no effective time information is included in the current attribute information of the RRM policy, determining a resource configuration score for the RRM policy based on at least one of the following: physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to the RRM policy; determining a ratio adjustment value based on the resource configuration score of the RRM policy; adjusting the RRM policy ratio group in the current attribute information of the RRM policy based on the ratio adjustment value, and using the adjusted RRM policy ratio group as the predicted attribute information of the RRM policy. In some embodiments, the resource configuration score is used to characterize the quality of the RRM policy ratio group defined by the RRM policy. A higher resource configuration score indicates a higher quality of the RRM policy ratio group defined by the RRM policy and a lower ratio adjustment value for the RRM policy. Conversely, a lower resource configuration score indicates a lower quality of the RRM policy ratio group defined by the RRM policy and a higher ratio adjustment value for the RRM policy.

[0062] In some embodiments, when there is effective time information in the current attribute information of the RRM policy, at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses and resource saturation of the RRM policy in the time period in the effective time information is obtained; based on at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses and resource saturation of the RRM policy in the time period in the effective time information, the resource configuration score of the RRM policy in the time period in the effective time information is determined; based on the resource configuration score of the RRM policy ratio group corresponding to the time period, a ratio adjustment value is determined; based on the ratio adjustment value, the RRM policy ratio group corresponding to the time period in the current attribute information of the RRM policy is adjusted, and the adjusted RRM policy ratio group is used as the predicted attribute information of the RRM policy.

[0063] In some embodiments, a preset resource configuration score determination model can be run to perform resource configuration score determination based on at least one of the physical resource block utilization, block error rate, signal to interference and noise ratio, number of accessed users, and resource saturation corresponding to the RRM policy, thereby obtaining a resource configuration score for the RRM policy. Similarly, a preset resource configuration score determination model can be run to perform resource configuration score determination based on at least one of the physical resource block utilization, block error rate, signal to interference and noise ratio, number of accessed users, and resource saturation of the RRM policy during the time period in the effective time information, thereby obtaining a resource configuration score for the RRM policy ratio group corresponding to the time period. In some embodiments, the preset resource configuration score determination model is obtained by iteratively training a neural network model based on multiple training samples, wherein the training samples include at least one of the physical resource block utilization, block error rate, signal to interference and noise ratio, number of accessed users, and resource saturation, as well as annotated resource configuration score.

[0064] In some embodiments, as shown in FIG4 , step S102 includes sub-step S1021 .

[0065] In sub-step S1021, a pre-trained policy attribute prediction model is run to perform policy attribute prediction processing based on the quality evaluation index of each radio resource management policy to obtain predicted attribute information of each radio resource management policy.

[0066] In this embodiment, the policy attribute prediction model is obtained by iteratively training a preset machine learning model based on multiple sample data, the sample data including quality evaluation indicators and annotated attribute information of the RRM policy, the multiple sample data including multiple first sample data and multiple second sample data, the attribute information annotated in the first sample data including an RRM policy ratio group, and the attribute information annotated in the second sample data including one or more RRM policy ratio groups and the effective time information corresponding to each RRM policy ratio group. By using the pre-trained policy attribute prediction model, the quality evaluation indicators of each RRM policy are subjected to policy attribute prediction processing, and the predicted attribute information of each wireless resource management policy can be accurately predicted, so that the predicted attribute information can be used to update the RRM policy later to obtain an accurate RRM policy.

[0067] In some embodiments, the preset machine learning model can be a Markov model or a neural network model, and the neural network model includes but is not limited to a convolutional neural network (CNN) model, a deep neural network (DNN) model, a recurrent neural network (RNN) model, a factorization machine supported neural network (FNN) model, a neural factorization machine (NFM) model, and an attention factorization machine (AFM) model.

[0068] In some embodiments, a pre-trained policy attribute prediction model is run, and policy attribute prediction processing is performed based on the quality evaluation index of each radio resource management policy. The method for obtaining the predicted attribute information of each radio resource management policy can be: the quality evaluation index of each RRM policy is input into the policy attribute prediction processing in sequence to obtain the predicted attribute information of each radio resource management policy. Alternatively, multiple threads are created and the multiple threads are called each time to run the pre-trained policy attribute prediction model in parallel, and policy attribute prediction processing is performed based on the quality evaluation indicators of multiple RRM policies to obtain the predicted attribute information of multiple RRM policies, until the predicted attribute information of all RRM policies is predicted.

[0069] For example, the number of RRM policies is N, the number of threads is M, and N and M are integers greater than or equal to 2. When N is less than or equal to M, N threads are called to run the pre-trained policy attribute prediction model in parallel, and policy attribute prediction processing is performed based on the quality evaluation indicators of the N RRM policies to obtain predicted attribute information of the N RRM policies. When N is greater than M, M threads are called to run the pre-trained policy attribute prediction model in parallel, and policy attribute prediction processing is performed based on the quality evaluation indicators of the M RRM policies to obtain predicted attribute information of the M RRM policies. After a thread is idle, the idle thread is called to run the pre-trained policy attribute prediction model, and policy attribute prediction processing is performed based on the quality evaluation indicators of one of the remaining NM RRM policies to obtain predicted attribute information of the corresponding RRM policy, until predicted attribute information of N RRM policies is obtained.

[0070] In some embodiments, a preset machine learning model is iteratively trained based on multiple sample data to obtain a strategy attribute prediction model in the following manner: initializing parameters of the preset machine learning model; selecting a sample data from multiple sample data as target sample data; inputting the quality evaluation index in the target sample data into the preset machine learning model for strategy attribute prediction processing to obtain predicted attribute information; calculating the model loss value based on the predicted attribute information and the attribute information marked in the target sample data; when the model loss value is greater than the preset loss value, updating the parameters of the preset machine learning model and returning to execute the step of selecting a sample data from multiple sample data as the target sample data; when the model loss value is less than or equal to the preset loss value, stopping training to obtain a strategy attribute prediction model.

[0071] In some embodiments, the quality evaluation indicators and target attribute information of each RRM strategy in the base station during the peak period, off-peak period and off-peak period of business demand can be collected in advance as sample data, and then the preset machine learning model can be iteratively trained using these sample data to obtain a more accurate strategy attribute prediction model. In some embodiments, the target attribute information includes an RRM strategy ratio group defined by the RRM strategy, or the target attribute information includes one or more RRM strategy ratio groups defined by the RRM strategy and the effective time information corresponding to each RRM strategy ratio group. For example, time periods such as am07:00-09:00, pm12:01-13:00, pm17:31-22:00 are peak periods, time periods such as am09:01-12:00, pm13:31-17:30, 22:01-00:00 are off-peak periods, and time periods such as am00:01-07:00 are off-peak periods.

[0072] It is understandable that the quality evaluation index of the RRM strategy includes at least one of the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to the RRM strategy. For example, the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to the RRM strategy, as well as the target attribute information of the RRM strategy, are used as sample data to train a machine learning model to obtain a strategy attribute prediction model. The strategy attribute prediction model is then run to comprehensively determine the predicted attribute information of the RRM strategy based on the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation corresponding to the RRM strategy.

[0073] For example, as shown in FIG5 , in the training phase: the MAC sublayer 11 in the base station obtains the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy, and passes the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy (RRM strategy 1 to RRM strategy n) to the machine learning computing power module 20; the radio resource control (RRC) sublayer 12 obtains the number of user accesses for each RRM strategy, and passes the number of user accesses for each RRM strategy to the machine learning computing power module 20; the operation and maintenance management (OMA) sublayer 12 obtains the number of user accesses for each RRM strategy, and passes the number of user accesses for each RRM strategy to the machine learning computing power module 20; Maintenance (OAM) 13 obtains the target attribute information of each RRM strategy and passes the target attribute information of each RRM strategy to the machine learning computing power module 20; the machine learning computing power module 20 stores the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy and the corresponding target attribute information as sample data; after the number of stored sample data reaches the set requirement, the machine learning computing power module 20 calls the model training module 21 to use multiple sample data to iteratively train the preset machine learning model to obtain a policy attribute prediction model 22. After the policy attribute prediction model 22 passes the accuracy verification, attribute prediction can be performed.

[0074] In the prediction stage: the MAC sublayer 11 passes the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy to the machine learning computing power module 20; the RRC sublayer 12 passes the number of user access for each RRM strategy to the machine learning computing power module 20; the machine learning computing power module 20 runs the policy attribute prediction model 22, and performs policy attribute prediction processing based on the physical resource block utilization, block error rate, signal to interference plus noise ratio, resource saturation and number of user access of each RRM strategy to obtain the predicted attribute information of each RRM strategy, and passes the predicted attribute information of each RRM strategy to OAM, which updates the corresponding wireless resource management strategy based on the predicted attribute information of each RRM strategy, and reconfigures the network resources of each network slice based on each updated wireless resource management strategy.

[0075] It is understood that the machine learning computing module 20 can be an internal module of the base station or an internal module of a computing device that is communicatively connected to the base station, and this disclosure does not specifically limit this. Alternatively, the model training module 21 in the machine learning computing module 20 is deployed in a server that is communicatively connected to the base station, and the policy attribute prediction model 22 in the machine learning computing module 20 is deployed in the base station.

[0076] In step S103, the corresponding wireless resource management policy is updated according to the predicted attribute information, and the network resources of each network slice are reconfigured according to each updated wireless resource management policy.

[0077] In this embodiment, the network resources of the network slice include the physical resource block resources of the network slice, and the predicted attribute information of the RRM policy may include first attribute information or second attribute information, the first attribute information includes an RRM policy ratio group, and the RRM policy ratio group includes an RRM policy dedicated ratio, an RRM policy minimum ratio, and an RRM policy maximum ratio. The second attribute information includes one or more RRM policy ratio groups and the effective time information corresponding to each RRM policy ratio group, and the effective time information is used to indicate the time period during which the corresponding RRM policy ratio group is effective.

[0078] In some embodiments, the corresponding wireless resource management policy is updated according to the predicted attribute information, and the network resources of each network slice are reconfigured according to each updated wireless resource management policy. The method can be: updating the target attribute information defined by each RRM policy in the OAM system to the corresponding predicted attribute information, thereby updating each RRM policy in the OAM system; generating a corresponding JavaScript Object Notation (JSON) file according to each updated RRM policy in the OAM system; passing the JSON file to the RRC; the RRC parses the JSON file to obtain and store the resource type information, RRM policy member list and target attribute information defined by each updated RRM policy; the RRC triggers a parameter reconfiguration request according to the JSON file, and sends the parameter reconfiguration request to each sublayer, and each sublayer responds according to the JSON file in the parameter reconfiguration request to reconfigure the network resources of each network slice. The sublayers include a MAC sublayer, a Packet Data Convergence Protocol (PDCP) sublayer and a Radio Link Control (RLC) sublayer.

[0079] Please refer to Figure 6, which is a schematic diagram of the configuration process of the RRM policy in an embodiment of the present disclosure. As shown in Figure 6, the configuration process of the RRM policy includes steps 1 to 11.

[0080] In step 1, RRMPolicy_ parameter configuration is performed. Specifically, RRMPolicy_ parameters are configured in the OAM of the 5G base station and the configured RRMPolicy_ parameters are activated. The RRMPolicy_ parameters include resource type information defined by the RRM policy, RRM policy member list, and target attribute information.

[0081] In step 2, the RRC sublayer performs parameter configuration. Specifically, the OAM generates a JSON file based on the configured RRMPolicy_ parameter and passes the generated JSON file to the RRC sublayer of the protocol stack. The RRC sublayer then forwards the JSON file to the PDCP sublayer, RLC sublayer, and MAC sublayer.

[0082] In step 2a, the RRMPolicy_ parameter is parsed and stored. Specifically, after receiving the JSON file delivered by OAM, the RRC sublayer parses the JSON file, obtains the RRMPolicy_ parameter, and stores the RRMPolicy_ parameter. Since the RRC sublayer performs user access control, resource isolation for RRC and DRB resource types is performed at the RRC sublayer.

[0083] In step 2b, the RRC sublayer performs a calendar clock judgment. Specifically, the RRC sublayer can make periodic judgments based on the calendar information and clock information contained in the configured RRMPolicy_ parameter, so as to determine whether the RRM policy dedicated ratio (rRMPolicyDedicatedRatio), RRM policy minimum ratio (rRMPolicyMinRatio) and RRM policy maximum ratio (rRMPolicyMaxRatio) defined by the RRM policy are effective in a specific time period. Among them, the calendar clock judgment specifically includes: determining whether there is effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy; when there is effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy, enabling the RRM policy ratio group corresponding to the matching effective time information; when there is no effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy, enabling the preset RRM policy ratio group.

[0084] In step 3, the cell establishes a configuration request / response. Specifically, the RRC sublayer triggers an RRMPolicy_parameter configuration request based on the received JSON file and sends the RRMPolicy_parameter configuration request to the PDCP sublayer, RLC sublayer, and MAC sublayer. The PDCP sublayer, RLC sublayer, and MAC sublayer respond based on the JSON file in the parameter configuration request.

[0085] In step 3a, the MAC sublayer parses and stores the RRMPolicy_ parameter. Specifically, after receiving the RRMPolicy_ parameter configuration request from the RRC sublayer, the MAC sublayer parses the JSON file in the RRMPolicy_ parameter configuration request, obtains the RRMPolicy_ parameter, and stores the RRMPolicy_ parameter. Because the MAC sublayer has resource scheduling capabilities, resource isolation for PRB resource types is performed at the MAC sublayer.

[0086] In step 3b, the MAC sublayer performs a calendar clock judgment. The MAC sublayer can make periodic judgments based on the calendar information and clock information contained in the configured RRMPolicy_ parameter to determine whether the RRM policy dedicated ratio (rRMPolicyDedicatedRatio), RRM policy minimum ratio (rRMPolicyMinRatio), and RRM policy maximum ratio (rRMPolicyMaxRatio) defined by the RRM policy are effective in a specific time period. The calendar clock judgment specifically includes: determining whether there is effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy; when there is effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy, enabling the RRM policy ratio group corresponding to the matching effective time information; when there is no effective time information that matches the clock information in the RRMPolicy_ parameter defined by the RRM policy, enabling the preset RRM policy ratio group.

[0087] In step 4, when sample data needs to be collected, the machine learning computing module sends a request to the OAM to obtain the target attribute information of the RRM policy.

[0088] In step 4a, after receiving the request for obtaining the target attribute information of the RRM policy from the machine learning computing power module, the OAM sends a response to the request for obtaining the target attribute information of the RRM policy to the machine learning computing power module. If the RRMPolicy_ parameter is configured, the response carries the target attribute information in the configured RRMPolicy_ parameter; if the RRMPolicy_ parameter is not configured, the response is null.

[0089] In step 5, when the attribute information prediction of the RRM policy is required, the machine learning computing power module proactively sends a request to the RRC sublayer to obtain the number of user accesses of the RRM policy.

[0090] In step 5a, after receiving the acquisition request, the RRC sublayer determines the number of user access for each RRM policy based on the acquisition request, and sends the number of user access for each RRM policy to the machine learning computing power module.

[0091] In step 6, when the attribute information of the RRM strategy needs to be predicted, the machine learning computing power module also actively sends a request to the MAC sublayer to obtain the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of the RRM strategy.

[0092] In step 6a, after receiving the acquisition request, the MAC sublayer determines the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy based on the acquisition request, and sends the physical resource block utilization, block error rate, signal to interference plus noise ratio and resource saturation of each RRM strategy to the machine learning computing power module.

[0093] In step 7, predicted attribute information of the RRM strategy is generated. Specifically, after obtaining the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation of each RRM strategy, the machine learning computing power module runs the strategy attribute prediction model to predict the strategy attributes based on the physical resource block utilization, block error rate, signal to interference plus noise ratio, number of user accesses, and resource saturation of each RRM strategy, and obtain the predicted attribute information of each RRM strategy.

[0094] In step 8, the machine learning computing module sends the predicted attribute information of each RRM policy to the OAM.

[0095] In step 9, after receiving the predicted attribute information of each RRM policy, the OAM reconfigures the RRMPolicy_parameter according to the predicted attribute information of each RRM policy and activates the reconfigured RRMPolicy_parameter.

[0096] In step 10, after OAM reconfigures the RRMPolicy_ parameter, the RRC sublayer reconfigures its parameters. Specifically, OAM generates a JSON file based on the reconfigured RRMPolicy_ parameter and other parameters. The generated JSON file is passed to the RRC sublayer of the protocol stack, which then forwards it to the PDCP sublayer, RLC sublayer, and MAC sublayer.

[0097] In step 11, the cell establishes a reconfiguration request / response. Specifically, the RRC sublayer triggers an RRMPolicy_parameter reconfiguration request based on the received JSON file and sends the reconfiguration request to the PDCP sublayer, RLC sublayer, and MAC sublayer. The PDCP sublayer, RLC sublayer, and MAC sublayer respond based on the JSON file in the parameter reconfiguration request.

[0098] In some embodiments, as shown in FIG7 , the resource configuration method further includes step S104 .

[0099] In step S104, when the RRM policy includes the second attribute information, a target RRM policy ratio group is determined according to the clock information and the second attribute information, and the target RRM policy ratio group is enabled.

[0100] In this embodiment, the base station may periodically determine the target RRM policy ratio group based on the clock information and the second attribute information, and enable the target RRM policy ratio group. For example, the base station may determine the target RRM policy ratio group based on the clock information and the second attribute information every two hours, and enable the target RRM policy ratio group. The clock information may be Coordinated Universal Time (UTC) clock information. It should be noted that step S104 may be executed after step S103, or before step S103, or before or after step S102 or step S101, and the embodiment of the present disclosure does not specifically limit this.

[0101] In some embodiments, if the second attribute information contains effective time information that matches the clock information, the RRM policy ratio group corresponding to the matching effective time information is determined as the target RRM policy ratio group. If the second attribute information does not contain effective time information that matches the clock information, a preset RRM policy ratio group is determined as the target RRM policy ratio group. The preset RRM policy ratio group can be set based on actual conditions and is not specifically limited in the present embodiment.

[0102] For example, the effective time information includes the date of the 10th, and the time periods corresponding to the 10th are 09:01-12:00 am and 13:31-17:30 pm. The RRM policy ratio group corresponding to the time period 09:00-12:00 am is RRM policy ratio group A, and the RRM policy ratio group corresponding to the time period 13:30-17:30 pm is RRM policy ratio group B. Therefore, if the current clock information is 10:00 am on xx / xx / xxxx, RRM policy ratio group A is used as the target RRM policy ratio group and enabled. In this way, the corresponding network slice uses the network resources of RRM policy ratio group A to carry user equipment. After a period of time, if the current clock information changes to 13:00 on xx / xx / xxxx, the preset RRM policy ratio group is enabled. In this way, the corresponding network slice uses the network resources of RRM policy ratio group B to carry user equipment. After a period of time, if the current clock information becomes 13:30 p.m. on xx / xx / xxxx, RRM policy ratio group A will be used as the target RRM policy ratio group, and RRM policy ratio group A will be enabled. In this way, the corresponding network slice uses the network resources of the preset RRM policy ratio group to carry user equipment.

[0103] In some embodiments, the UE may obtain PLMN information in the RRCConnectionSetupComplete message during the access process. The base station may use the PLMN provided in the RRC message to select the appropriate operator information, and select the appropriate network slice based on the Slice Service type (SST) and Slice Differentiator (SD) information provided in the PDUSession established by the UE. Since the network slice is subject to the constraints of the matched RRM policy, and the RRM resource defines the RRM policy ratio group and the corresponding effective time information, the isolation characteristics of the PRB, RRC or DRB resources of the network slice can be effective within the time period specified by the effective time information.

[0104] An embodiment of the present disclosure also provides a computer storage medium for computer-readable storage, wherein the computer storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors, so that the one or more processors implement any network slicing resource configuration method provided in the embodiment of the present disclosure.

[0105] In some embodiments, the computer storage medium may be an internal storage unit of the base station described in the aforementioned embodiments, such as a hard disk or memory of the base station. The computer storage medium may also be an external storage device of the base station, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, etc., equipped on the base station.

[0106] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor (such as a central processing unit, a digital signal processor, or a microprocessor), or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable, and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media generally embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0107] It should be understood that the term "and / or" as used in this disclosure and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0108] The serial numbers of the embodiments of the present disclosure are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A resource configuration method for a network slice, comprising: Acquire a quality evaluation indicator for each wireless resource management strategy, the quality evaluation indicator comprising at least one of a physical resource block utilization rate, a block error rate, a signal to interference plus noise ratio, a user access number, and a resource saturation corresponding to the wireless resource management strategy; Determining predicted attribute information of each wireless resource management strategy according to the quality evaluation index of each wireless resource management strategy; as well as According to the predicted attribute information, the corresponding wireless resource management policy is updated, and according to each updated wireless resource management policy, the network resources of each network slice are reconfigured.

2. The resource configuration method for network slicing according to claim 1, wherein: The obtaining of the quality evaluation index of each wireless resource management strategy includes: Obtaining a resource configuration impact indicator for each of the network slices, the resource configuration impact indicator comprising at least one of a physical resource block utilization rate, a block error rate, a signal to interference plus noise ratio, a number of user accesses, and a resource saturation of the network slice; and According to the resource configuration impact indicators of one or more network slices corresponding to each wireless resource management strategy, the quality evaluation indicator of each wireless resource management strategy is determined.

3. The resource configuration method for network slicing according to claim 1, wherein: The predicted attribute information includes first attribute information or second attribute information, the first attribute information includes a wireless resource management policy ratio group, the wireless resource management policy ratio group includes a wireless resource management policy dedicated ratio, a wireless resource management policy minimum ratio and a wireless resource management policy maximum ratio; The second attribute information includes one or more wireless resource management policy ratio groups and effective time information corresponding to each wireless resource management policy ratio group, and the effective time information is used to indicate the time period during which the corresponding wireless resource management policy ratio group is effective.

4. The resource configuration method for a network slice according to any one of claims 1 to 3, wherein: The wireless resource management strategy includes second attribute information, and the method further includes: A target wireless resource management policy ratio group is determined according to the clock information and the second attribute information, and the target wireless resource management policy ratio group is enabled.

5. The resource configuration method for network slicing according to claim 4, wherein: The determining, according to the clock information and the second attribute information, a target wireless resource management policy ratio group includes: If the second attribute information contains effective time information that matches the clock information, the wireless resource management policy ratio group corresponding to the matching effective time information is determined as the target wireless resource management policy ratio group.

6. The resource configuration method for network slicing according to claim 5, wherein: The determining, according to the clock information and the second attribute information, a target radio resource management strategy ratio group further includes: If the second attribute information does not contain effective time information matching the clock information, a preset wireless resource management policy ratio group is determined as the target wireless resource management policy ratio group.

7. The resource configuration method for a network slice according to any one of claims 1 to 3, wherein: The step of determining the prediction attribute information of each wireless resource management strategy according to the quality evaluation index of each wireless resource management strategy includes: Running a pre-trained policy attribute prediction model, performing policy attribute prediction processing based on the quality evaluation index of each wireless resource management policy, and obtaining prediction attribute information of each wireless resource management policy, The policy attribute prediction model is obtained by iteratively training a preset machine learning model based on multiple sample data, and the sample data includes quality evaluation indicators of the wireless resource management policy and annotated attribute information.

8. The resource configuration method for a network slice according to any one of claims 1 to 3, wherein: The network resources include physical resource block resources of the network slice.

9. A base station, comprising a processor, a memory, a computer program stored in the memory and to be executed by the processor, and a data bus for realizing connection communication between the processor and the memory, wherein: The computer program is executed by the processor so that the processor implements the resource configuration method for the network slice as described in any one of claims 1 to 8.

10. A computer storage medium for computer-readable storage, wherein: The computer storage medium stores one or more computer programs, and the one or more computer programs are executed by one or more processors, so that the one or more processors implement the method for resource configuration of the network slice described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Network slice resource management method and equipment

    CN112153700A

  • Network slice self-optimization method, base station and storage medium

    CN115460623A

  • Method and apparatus for allocating resource to network slice

    US20210084582A1

  • Radio resource planning and slice-aware scheduling for intelligent radio access network slicing

    WO2023283102A1