5g network slice access control method, system and device based on access prediction
By using an access prediction method, the latency and resource parameters of network slices are calculated. Combined with the probability of new services, slice resources are dynamically adjusted, which solves the problem of high access failure rate in existing technologies and achieves efficient network resource utilization and high service access success rate.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUAXIN CONSULTATING CO LTD
- Filing Date
- 2026-03-26
- Publication Date
- 2026-06-16
AI Technical Summary
Existing 5G network slicing access control methods lack adaptability and flexibility, resulting in a high probability of access failure in heterogeneous networks. They are unable to effectively cope with time-varying and random user behavior, especially with the possibility of service collisions increasing significantly under diversified user needs.
By using access prediction methods, parameters such as latency margin, resource factor, and throughput of network slices are calculated. Combined with the arrival probability of new services and slice blocking rate, network slice resources are dynamically adjusted to optimize access decisions and select the optimal slice for new service access.
It enables precise control of network slice resources, improves access success rate and network resource utilization efficiency, avoids local congestion, and enhances network stability and service access success rate.
Smart Images
Figure CN122227352A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of 5G network technology, specifically to a 5G network slicing access control method, system, and device based on access prediction. Background Technology
[0002] With the widespread application of numerous emerging vertical industries such as smart cities and mobile edge computing, user needs have become more diversified. To meet the massive growth in mobile traffic and diverse user demands, emerging technologies such as heterogeneous cellular networks and network slicing have been introduced into 5G and next-generation mobile communication network architectures. While these technologies improve network performance, they also make wireless networks more complex and heterogeneous. Therefore, ensuring efficient network management and data transmission in different scenarios, and effectively carrying multiple services in heterogeneously interconnected converged networks, will be a hot research topic in the future. The first step in this process is effective access, especially network slicing access adapted to different 5G scenarios.
[0003] To address the aforementioned issues, an existing patent (patent number: 202211365786.8) proposes a 5G network slicing access control method based on service type. This method first determines the service type and then selects different principles for network slice access control based on whether the service is latency-sensitive. While simple and efficient, this approach lacks adaptability and generalization capabilities, and it lacks flexibility and adaptability in the face of time-varying heterogeneous networks and the randomness of user behavior. With increasing access volume, the probability of service collisions rises significantly, and the probability of access failure also increases dramatically. Therefore, this invention proposes a 5G network slicing access control method, system, and device based on access prediction. Summary of the Invention
[0004] The purpose of this invention is to provide a 5G network slicing access control method, system, and device based on access prediction, so as to solve the problems mentioned in the background art.
[0005] According to a first aspect of the present invention, in order to achieve the above-mentioned objective, the present invention provides the following technical solution: a 5G network slicing access control method based on access prediction, comprising the following steps: Receive network slice data, calculate the latency margin of existing services in each network slice, and calculate the latency factor of each network slice based on the latency margin to evaluate the current service latency status of the network slice. Calculate the total amount of resources occupied by existing services in each network slice, calculate the resource factor of each network slice based on the total amount of resources and the latency factor, and calculate the resource weight of each network slice based on the coupling relationship between the resource factor and the latency factor. Calculate the throughput of existing services within each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value for existing services for each network slice based on the resource weight, the latency margin, and the particle performance. The arrival probability and access request probability of a new service in each network slice are preset. The slice blocking rate of each network slice is calculated based on the blocking rate of existing services in each network slice. Based on the arrival probability, access request probability and slice blocking rate, the access probability of each network slice for the new service is calculated. Based on the preset new service weights, the access probability and access prediction value are weighted and fused to calculate the comprehensive prediction value of each slice. The slice with the largest comprehensive prediction value is selected as the target access slice for the newly arriving service, so as to realize the dynamic adjustment and control of network slice resources.
[0006] Furthermore, the network slice data specifically includes: Network slices Network slicing Total number of physical resource blocks (RBs) , It already contains Business ; Any business within Current waiting time Delay tolerance Blocking rate Occupying RB number Business throughput New arrivals currently Number of RB applications .
[0007] Furthermore, network slice data is received, the latency margin of existing services within each network slice is calculated, and the latency factor of each network slice is calculated based on the latency margin to assess the current service latency status of the network slice, as detailed below: (3-1): For any network slice All businesses within Calculate its time delay margin. ( Based on this, network slices are calculated. delay margin ; (3-2): Calculate the latency factor for all services. ,in, This represents an exponential function with the natural constant as its base; based on this, network slices are calculated. Delay factor .
[0008] Furthermore, the total resources occupied by existing services within each network slice are calculated. Based on the total resources and latency factor, the resource factor of each network slice is calculated. And based on the coupling relationship between the resource factor and latency factor, the resource weight of each network slice is calculated, as follows: (4-1): Calculating arbitrary network slices Total RB resources used by all internal services Calculate network slices resource factors ; (4-2): Calculate arbitrary network slices Resource weight .
[0009] Furthermore, the throughput of existing services within each network slice is calculated, and the particle performance of each network slice is calculated based on the throughput and total resources. Then, based on the resource weight, the latency margin, and the particle performance, the access prediction value for existing services in each network slice is calculated, as follows: (5-1): Calculate arbitrary network slices Throughput and value of all services within ; Calculate slices particle efficiency Calculate the particle efficiency and value for all slices. ; (5-2): Calculate each network slice particle relative efficiency ; Calculate the current time for the network slice Forecast value of access to existing services .
[0010] Furthermore, the arrival probability and access request probability of a newly arriving service are preset in each network slice. The slice blocking rate of each network slice is calculated based on the blocking rate of existing services within each network slice. Based on the arrival probability, access request probability, and slice blocking rate, the access probability of each network slice for the newly arriving service is calculated, as follows: Set new business at the current time Reaching the slice probability The probability of new business applications being accepted ; Calculate arbitrary network slices blocking rate Computational network slicing Access probability at the current moment .
[0011] Furthermore, based on the preset new service weights, the access probability and access prediction value are weighted and fused to calculate the comprehensive prediction value of each slice. The slice with the highest comprehensive prediction value is selected as the target access slice for the newly arriving service, thereby realizing dynamic adjustment and control of network slice resources, as follows: (7-1): Setting weights for new businesses ; Calculate the comprehensive predicted value of service access at the current moment. ; (7-2): Select the one with the largest composite forecast value slices As a new arrival service The target access slice.
[0012] According to a second aspect of the present invention, the present invention provides a 5G network slicing access control system based on access prediction, for implementing the 5G network slicing access control method based on access prediction described in the first aspect, comprising: The service latency monitoring module is used to receive network slice data, calculate the latency margin of existing services in each network slice, and calculate the latency factor of each network slice based on the latency margin in order to evaluate the current service latency status of the network slice. The resource occupancy assessment module is used to calculate the total amount of resources occupied by existing services in each network slice, calculate the resource factor of each network slice based on the total amount of resources and the latency factor, and calculate the resource weight of each network slice based on the coupling relationship between the resource factor and the latency factor. The existing service prediction module is used to calculate the throughput of existing services in each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value of each network slice for existing services based on the resource weight, the latency margin and the particle performance. The new service prediction module is used to preset the arrival probability and access request probability of new services in each network slice, calculate the slice blocking rate of each network slice based on the blocking rate of existing services in each network slice, and calculate the access probability of each network slice for new services based on the arrival probability, access request probability and slice blocking rate. The service access comprehensive prediction module is used to calculate the comprehensive prediction value of each slice by weighting and fusing the access probability and access prediction value according to the preset new service weight, and select the slice with the largest comprehensive prediction value as the target access slice for the newly arrived service, so as to realize the dynamic adjustment and control of network slice resources.
[0013] According to a third aspect of the present invention, a terminal device is provided, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor, and when the processor loads and executes the computer program, it employs the 5G network slicing access control method based on access prediction described in the first aspect.
[0014] According to a fourth aspect of the present invention, a computer-readable storage medium stores a computer program that, when loaded and executed by a processor, employs the 5G network slicing access control method based on access prediction described in the first aspect.
[0015] The present invention has at least the following beneficial effects: 1. This invention deeply monitors the latency status of services and comprehensively evaluates the physical resource occupancy of slices. By quantifying and integrating key parameters such as latency margin, latency factor, and resource factor, it can reflect the real carrying capacity and operational quality of the current network slice in real time and accurately, providing a comprehensive and reliable data foundation for subsequent access decisions.
[0016] 2. This invention evaluates the throughput efficiency of services within a slice by calculating particle efficiency and relative efficiency. It also innovatively introduces a prediction step for new services. By comprehensively considering the arrival probability, access probability, and current slice blocking rate of new services, it can predict access behavior, thereby effectively avoiding resource overload and performance degradation caused by sudden service access. This reflects a technological leap from passive response to proactive prediction.
[0017] 3. This invention calculates a comprehensive predicted value that includes both existing and new services, and dynamically selects the optimal target slice based on this value. This allows new services to be precisely guided to the slice with the best overall performance. This intelligent access control strategy can maximize the acceptance of new services while ensuring that the service quality of existing services is not affected. It effectively balances the load between slices, avoids local congestion, and thus improves the overall efficiency of network resource utilization and the success rate of service access.
[0018] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description
[0019] Figure 1 This is a flowchart illustrating the method described in this invention; Figure 2 This is a comparison chart of the average service access latency between the present invention and existing algorithms; Figure 3 This is a comparison chart of the successful slice access probabilities of the present invention and existing algorithms. Detailed Implementation
[0020] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.
[0021] Please see Figures 1-3 This invention provides a technical solution: a 5G network slicing access control method based on access prediction, comprising the following steps: S1. Receive network slice data, calculate the latency margin of existing services within each network slice, and calculate the latency factor of each network slice based on the latency margin to assess the current service latency status of the network slice, as follows: The network slice data includes: Network slices Network slicing Total number of physical resource blocks (RBs) , It already contains Business ; Any business within Current waiting time Delay tolerance Blocking rate Occupying RB number Business throughput New arrivals currently Number of RB applications ; Step 1-1: For any slice All businesses within Calculate its time delay margin. ( Based on this, calculate the slice. delay margin ; Step 1-2: Calculate the latency factor for all services. ,in, This represents an exponential function with the natural constant as its base; based on this, slices are calculated. Delay factor ; S2. Calculate the total resources occupied by existing services within each network slice. Based on the total resources and latency factor, calculate the resource factor of each network slice. Then, calculate the resource weight of each network slice based on the coupling relationship between the resource factor and latency factor, as follows: Step 2-1: Calculate any slice Total RB resources used by all internal services Calculate slices resource factors ; Step 2-2: Calculate any slice Resource weight ; S3. Calculate the throughput of existing services within each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value for existing services for each network slice based on the resource weight, the latency margin, and the particle performance, as follows: Step 3-1: Calculate any slice Throughput and value of all services within ; Calculate slices particle efficiency Calculate the particle efficiency and value for all slices. ; Step 3-2: Calculate each slice particle relative efficiency ; Calculate the current time for the slice Forecast value of access to existing services ; S4. Preset the arrival probability and access request probability of the newly arriving service in each network slice. Calculate the slice blocking rate of each network slice based on the blocking rate of existing services within each network slice. Based on the arrival probability, access request probability, and slice blocking rate, calculate the access probability of each network slice for the newly arriving service, as follows: Set new business at the current time Reaching the slice probability The probability of new business applications being accepted ; Calculate any slice blocking rate ; Calculate slices Access probability at the current moment ; S5. Based on the preset new service weights, the access probability and access prediction value are weighted and fused to calculate the comprehensive prediction value of each slice. The slice with the highest comprehensive prediction value is selected as the target access slice for the newly arriving service, so as to realize the dynamic adjustment and control of network slice resources, as follows: Step 5-1: Set the weight of new business ; Calculate the comprehensive predicted value of service access at the current moment. ; Step 5-2: Select the one with the largest overall predicted value slices As a new arrival service The target access slice.
[0022] The technical solution of the present invention will be further described below with reference to specific embodiments: Below, m This embodiment will be explained in detail using an example. The network slice configurations for each 5G network are shown in Table 1: Table 1. Services Existing in Each 5G Network Slice The basic data is shown in Table 2: Table 2 Basic Data This example describes a 5G network slicing access control method based on access prediction, which includes the following steps: service latency monitoring, resource usage assessment, prediction based on existing services, prediction based on new services, and comprehensive prediction of service access. Step 1: Service latency monitoring; Step 1-1: For any slice All businesses within Calculate its time delay margin. ( Based on this, calculate the slice. delay margin ; Step 1-2: Calculate the latency factor for all services. Based on this, calculate the slice. Delay factor ; Step 2: Resource utilization assessment; Step 2-1: Calculate any slice Total RB resources used by all internal services Calculate slices resource factors ; Step 2-2: Calculate any slice Resource weight ; Step 3: Forecasting based on existing business; Step 3-1: Calculate any slice Throughput and value of all services within ; Calculate slices particle efficiency Calculate the particle efficiency and value for all slices. ; Step 3-2: Calculate each slice particle relative efficiency ; Calculate the current time for the slice Forecast value of access to existing services ; Step 4: Forecasting based on new business; Calculate arbitrary slices blocking rate ; Calculate slices Access probability at the current moment ; Step 5: Comprehensive prediction of business access; Step 5-1: Calculate the comprehensive predicted value of service access at the current moment. ; Step 5-2: Select the one with the largest overall predicted value slices As a new arrival service The target access slice; Simulation experiment: The AP-NSAC 5G network slicing access control method based on access prediction in this embodiment is simulated on a MATLAB platform with the 5G network slicing access control method based on service type (existing algorithm) with application number 202211365786.8. Network and service configurations are performed according to the above table. The obtained average access latency and access success rate are shown in the appendix. Figures 2 to 3 As shown.
[0023] like Figure 2 As shown, the access latency of the two algorithms is similar at the beginning of the simulation because the slice load is low and the possibility of service collisions is not high in the early stage of access. However, as the number of access services increases, the slice link becomes more and more congested, and the access latency of both algorithms increases. However, because this AP-NSAC combines the congestion status of existing services and the probability of new services requesting access to make predictions, it allocates the resources required for access in advance, thereby avoiding service access failures as much as possible and further reducing service access latency. Therefore, reflected in the curve, after crossing the critical line, the access latency of the existing algorithm will exceed that of AP-NSAC and climb. like Figure 3As shown, the access success rate is related to the number of available RBs in the slice, the degree of congestion, and the severity of service timeouts. Existing algorithms only adjust scheduling based on latency metrics, without evaluating slice load and access success rate. This significantly increases the probability of service collisions, leading to increased slice load and decreased access success rate in the later stages of service access, thus reducing the robustness of the slice network. In contrast, while the access success rate of this AP-NSAC also decreases with the increase in access services, the decrease is more gradual and contributes more to system stability.
[0024] In summary, this invention designs a 5G network slicing access control method based on access prediction. First, it monitors service latency and calculates the latency margin and latency factor for all services and their respective slices. Then, it measures the physical resources and resource factors occupied by all slices, thereby calculating their resource weights. Based on the throughput capacity of existing services, it calculates particle efficiency and relative efficiency, and predicts the access evaluation value for existing services at the current moment. Based on the arrival probability and access probability of new services, it predicts the access evaluation value for new services. Finally, it calculates the comprehensive prediction value for service access and selects the slice with the highest comprehensive prediction value for access. Thus, dynamic adjustment and control of services can be implemented based on the slice status.
[0025] Example 2: This embodiment provides a 5G network slicing access control system based on access prediction, used to implement the 5G network slicing access control method based on access prediction described in Embodiment 1, including: The service latency monitoring module is used to receive network slice data, calculate the latency margin of existing services in each network slice, and calculate the latency factor of each network slice based on the latency margin in order to evaluate the current service latency status of the network slice. The resource occupancy assessment module is used to calculate the total amount of resources occupied by existing services in each network slice, calculate the resource factor of each network slice based on the total amount of resources and the latency factor, and calculate the resource weight of each network slice based on the coupling relationship between the resource factor and the latency factor. The existing service prediction module is used to calculate the throughput of existing services in each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value of each network slice for existing services based on the resource weight, the latency margin and the particle performance. The new service prediction module is used to preset the arrival probability and access request probability of new services in each network slice, calculate the slice blocking rate of each network slice based on the blocking rate of existing services in each network slice, and calculate the access probability of each network slice for new services based on the arrival probability, access request probability and slice blocking rate. The service access comprehensive prediction module is used to calculate the comprehensive prediction value of each slice by weighting and fusing the access probability and access prediction value according to the preset new service weight, and select the slice with the largest comprehensive prediction value as the target access slice for the newly arrived service, so as to realize the dynamic adjustment and control of network slice resources.
[0026] Example 3: The present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it adopts the 5G network slicing access control method based on access prediction described in Embodiment 1.
[0027] It should be noted that the terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.
[0028] Furthermore, the processor can be a central processing unit (CPU). Of course, depending on the actual use, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be used. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.
[0029] Example 4: The present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the 5G network slicing access control method based on access prediction described in Embodiment 1.
[0030] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.
[0031] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0032] For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on," "mounted on," "fixed to," or "set on" another element, it may be directly on the other element or there may be an intermediate element present. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible embodiments.
[0033] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
[0034] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
Claims
1. A 5G network slicing access control method based on access prediction, characterized in that, Includes the following steps: Receive network slice data, calculate the latency margin of existing services in each network slice, and calculate the latency factor of each network slice based on the latency margin to evaluate the current service latency status of the network slice. Calculate the total amount of resources occupied by existing services in each network slice, calculate the resource factor of each network slice based on the total amount of resources and the latency factor, and calculate the resource weight of each network slice based on the coupling relationship between the resource factor and the latency factor. Calculate the throughput of existing services within each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value for existing services for each network slice based on the resource weight, the latency margin, and the particle performance. The arrival probability and access request probability of a new service in each network slice are preset. The slice blocking rate of each network slice is calculated based on the blocking rate of existing services in each network slice. Based on the arrival probability, access request probability and slice blocking rate, the access probability of each network slice for the new service is calculated. Based on the preset new service weights, the access probability and access prediction value are weighted and fused to calculate the comprehensive prediction value of each slice. The slice with the largest comprehensive prediction value is selected as the target access slice for the newly arriving service, so as to realize the dynamic adjustment and control of network slice resources.
2. The 5G network slicing access control method based on access prediction according to claim 1, characterized in that: The network slice data specifically includes: Network slices Network slicing Total number of physical resource blocks (RBs) , It already contains Business ; Any business within Current waiting time Delay tolerance Blocking rate Occupying RB number Business throughput New arrivals currently Number of RB applications .
3. The 5G network slicing access control method based on access prediction according to claim 2, characterized in that: Receive network slice data, calculate the latency margin of existing services within each network slice, and calculate the latency factor of each network slice based on the latency margin to assess the current service latency status of the network slice, as follows: (3-1): For any network slice All businesses within Calculate its time delay margin. ( Based on this, network slices are calculated. delay margin ; (3-2): Calculate the latency factor for all services. ,in, This represents an exponential function with the natural constant as its base; based on this, network slices are calculated. Delay factor .
4. The 5G network slicing access control method based on access prediction according to claim 3, characterized in that: Calculate the total resources occupied by existing services within each network slice. Based on the total resources and latency factor, calculate the resource factor for each network slice. Then, calculate the resource weight for each network slice based on the coupling relationship between the resource factor and latency factor, as follows: (4-1): Calculating arbitrary network slices Total RB resources used by all internal services Calculate network slices resource factors ; (4-2): Calculate arbitrary network slices Resource weight .
5. The 5G network slicing access control method based on access prediction according to claim 4, characterized in that: Calculate the throughput of existing services within each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value for existing services for each network slice based on the resource weight, the latency margin, and the particle performance, as follows: (5-1): Calculate arbitrary network slices Throughput and value of all services within ; Calculate slices particle efficiency Calculate the particle efficiency and value for all slices. ; (5-2): Calculate each network slice particle relative efficiency ; Calculate the current time for the network slice Forecast value of access to existing services .
6. The 5G network slicing access control method based on access prediction according to claim 5, characterized in that: The arrival probability and access request probability of a newly arriving service are preset in each network slice. The slice blocking rate of each network slice is calculated based on the blocking rate of existing services within each network slice. Based on the arrival probability, access request probability, and slice blocking rate, the access probability of each network slice for the newly arriving service is calculated, as follows: Set new business at the current time Reaching the slice probability The probability of new business applications being accepted ; Calculate arbitrary network slices blocking rate Computational network slicing Access probability at the current moment .
7. The 5G network slicing access control method based on access prediction according to claim 5, characterized in that: Based on the preset new service weights, the access probability and access prediction value are weighted and fused to calculate the comprehensive prediction value of each slice. The slice with the highest comprehensive prediction value is selected as the target access slice for the newly arriving service, so as to realize the dynamic adjustment and control of network slice resources, as follows: (7-1): Setting weights for new businesses ; Calculate the comprehensive predicted value of service access at the current moment. ; (7-2): Select the one with the largest composite forecast value slices As a new arrival service The target access slice.
8. A 5G network slice access control system based on access prediction, used to implement the 5G network slice access control method based on access prediction as described in any one of claims 1 to 7, characterized in that, include: The service latency monitoring module is used to receive network slice data, calculate the latency margin of existing services in each network slice, and calculate the latency factor of each network slice based on the latency margin in order to evaluate the current service latency status of the network slice. The resource occupancy assessment module is used to calculate the total amount of resources occupied by existing services in each network slice, calculate the resource factor of each network slice based on the total amount of resources and the latency factor, and calculate the resource weight of each network slice based on the coupling relationship between the resource factor and the latency factor. The existing service prediction module is used to calculate the throughput of existing services in each network slice, calculate the particle performance of each network slice based on the throughput and total resources, and calculate the access prediction value of each network slice for existing services based on the resource weight, the latency margin and the particle performance. The new service prediction module is used to preset the arrival probability and access request probability of new services in each network slice, calculate the slice blocking rate of each network slice based on the blocking rate of existing services in each network slice, and calculate the access probability of each network slice for new services based on the arrival probability, access request probability and slice blocking rate. The service access comprehensive prediction module is used to calculate the comprehensive prediction value of each slice by weighting and fusing the access probability and access prediction value according to the preset new service weight, and select the slice with the largest comprehensive prediction value as the target access slice for the newly arrived service, so as to realize the dynamic adjustment and control of network slice resources.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on a processor. When the processor loads and executes the computer program, it employs the 5G network slicing access control method based on access prediction as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs the 5G network slicing access control method based on access prediction as described in any one of claims 1 to 7.