Network slice allocation methods and devices, network slice application methods, electronic devices
By introducing machine learning models into 5G systems to predict network slice occupancy status, the problem of duplicate user device registration is solved, enabling intelligent communication and resource saving, and improving communication efficiency and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- IPLOOK NETWORKS CO LTD
- Filing Date
- 2023-03-31
- Publication Date
- 2026-07-31
AI Technical Summary
In existing technologies, 5GS cannot control the registration status of network slices according to the needs of applications, causing user devices to repeatedly register when slice resources are scarce, increasing network signaling burden and power consumption, and affecting user experience.
By introducing machine learning models to predict the occupancy status of network slices, and responding to client registration requests by rejecting or allowing registration instructions, duplicate applications can be avoided and resources can be saved.
It enables intelligent communication in 5G systems, reduces the number of repeated requests from clients, saves communication resources, and improves communication speed and user experience.
Smart Images
Figure CN116800614B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and more specifically, to a network slice allocation method and apparatus, a network slice application method, and an electronic device. Background Technology
[0002] Network slicing can provide customized and differentiated network functions and services for users with different needs. Different slices are independent and isolated from each other. Network functions are customized according to user requirements, providing end-to-end customized network services. Therefore, the network architecture has very high flexibility. End-to-end means that slicing technology involves not only the core network but also the access network, transmission network, and bearer network. Customization means managing the lifecycle of network slices according to network requirements while customizing the bearer services, connection relationships, implemented functions, capacity, and quality of service according to different needs. When providing end-to-end network slicing services in the network, the technical indicators, network capabilities, and parameters associated with each domain can be set independently without affecting each other. These can be flexibly adjusted according to customer needs, thereby solving end-to-end network bandwidth, quality of service, and security issues related to slicing.
[0003] With the rapid development of technologies such as virtual reality and augmented reality, smart cameras and industrial cameras are evolving towards ultra-high definition. The high precision requirements of industrial and outdoor inspections are pushing high-bandwidth connectivity to new heights. Although customized slicing can be provided to users based on different network needs, the increasing bandwidth demands of new technologies and the growing number of users inevitably lead to slicing resource shortages. When network slicing becomes congested, user devices may fail to register slices. In existing technologies, 5GS cannot control the slicing registration status according to application needs, causing user devices to be unable to perceive the slicing status. Therefore, user devices may repeatedly register before sufficient slicing resources are restored. This increases network signaling burden and power consumption of user devices, and may also negatively impact the user experience of those already registered to the current network slice. Summary of the Invention
[0004] In view of this, the purpose of this application is to provide a network slice allocation method and apparatus, a network slice application method, and an electronic device, which can prevent user equipment from repeatedly submitting slice application requests at the same time because slices are occupied, thereby saving resources.
[0005] In a first aspect, embodiments of this application provide a network slice allocation method, including:
[0006] In response to the first client's registration request regarding the network slice, the first client is allowed to establish a PDU session in the network slice;
[0007] Continuously predict the occupancy status of the network slices;
[0008] In response to the second client's registration request for the network slice, if the network slice is in a blocked state, a rejection message is sent to the second client;
[0009] When the network slice is in an idle state, a registration permission instruction is sent to the second client.
[0010] In the above implementation process, when a network slice is occupied, the occupancy status of the network slice is predicted. When a second client requests the network slice, if the predicted occupancy status of the network slice is blocked, a rejection message is sent to the second client. When the network slice is idle, a re-request request is sent to the second client so that the second client resends the request to establish a PDU session in the network slice. This avoids the client repeatedly submitting slice request requests after receiving the rejection message for the first time, thus avoiding wasting the client device's resources.
[0011] Furthermore, the continuous prediction of the occupancy status of the network slice includes:
[0012] Obtain working parameters;
[0013] The working parameters are input into a pre-trained machine learning model to obtain the occupancy status of the network slice.
[0014] In the above implementation process, introducing machine learning models into the 5G system to predict the occupancy status of network slices is beneficial to realizing the intelligence of the 5G system, improving communication smoothness and speed, and further saving communication resources.
[0015] Furthermore, the operating parameters include: a first operating parameter and a second operating parameter;
[0016] The acquisition of working parameters includes:
[0017] Generate a first monitoring strategy and send the first monitoring strategy to the client-side functional unit;
[0018] The client-side functional unit obtains the first operating parameters according to the first monitoring strategy;
[0019] Generate a second monitoring strategy and send the second monitoring strategy to the operation and maintenance management unit;
[0020] The operation and maintenance management unit obtains the second operating parameters according to the second monitoring strategy.
[0021] In the above implementation process, different network elements in 5GS have different functions. The working parameters of different network elements reflect the working status of different aspects of network slices. The working status of different aspects reflects the occupancy status of network slices to varying degrees. By collecting the first working parameters and the second working parameters in the client-side functional unit and the operation and maintenance management unit based on different monitoring strategies, the occupancy status of network slices can be comprehensively predicted, further reducing the number of times the client submits network slice application requests and saving communication resources.
[0022] Furthermore, the operating parameters include one or more of the following: the number of radio resource control connections in the network slice and the radio resource utilization rate;
[0023] The second operating parameter includes: transmission delay.
[0024] Furthermore, the method also includes:
[0025] When the occupancy status is blocked, the second client is added to the communication list;
[0026] When the occupancy status is unregistered, an idle information is sent to the second client so that the second client resends the request to apply for the network slice.
[0027] Furthermore, the continuous prediction of the occupancy status of the network slice includes:
[0028] When the first client establishes a PDU session on the network slice, it predicts the occupancy status of the network slice at preset intervals.
[0029] In the above implementation process, unlike the prior art which obtains the occupancy status of network slices through passive response, the embodiments of this application actively obtain the network slice status by predicting the occupancy status of the network slices at preset intervals, which can solve the problem of long response time caused by passive response.
[0030] Furthermore, the machine learning model includes: a logistic regression model and an XGboost model;
[0031] The step of inputting the working parameters into a pre-trained machine learning model to obtain the occupancy status of the network slice includes:
[0032] Input the working parameters into the pre-trained logistic regression model to obtain the first output result;
[0033] The first output result is input into the XGboost model to obtain the occupancy status of the network slice.
[0034] In the above implementation process, different working parameters have different formats and units. The logistic regression model does not need to scale the input data and has a fast training speed. It can accurately predict the network slice occupancy status while maintaining communication speed.
[0035] Secondly, embodiments of this application provide a network slicing application method, including:
[0036] Send a registration request for network slicing to the 5G system;
[0037] Upon receiving a rejection message from the 5G system, stop sending the request to establish a PDU session on the network slice;
[0038] It receives the registration permission instruction from the 5G system and resends the registration request for network slicing to the 5G system.
[0039] Thirdly, embodiments of this application provide a network slice allocation apparatus, comprising:
[0040] The receiving module is used to respond to the registration request of the first client regarding the network slice, allowing the first client to establish a PDU session in the network slice;
[0041] The prediction module is used to continuously predict the occupancy status of the network slice;
[0042] The receiving module is also used to respond to a second client's registration request regarding the network slice;
[0043] The sending module is used to send a rejection message to the second client when the network slice is in a blocked state;
[0044] The sending module is also used to send a registration permission instruction to the second client when the network slice is in an idle state.
[0045] Fourthly, an electronic device provided in this application includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects. Attached Figure Description
[0046] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0047] Figure 1 This is a first flowchart illustrating the network slice allocation method provided in an embodiment of this application;
[0048] Figure 2 This is a second flowchart illustrating the network slice allocation method provided in an embodiment of this application.
[0049] Figure 3 A schematic diagram of the third process for network slice allocation provided in an embodiment of this application;
[0050] Figure 4 A schematic diagram of the machine learning model provided in the embodiments of this application;
[0051] Figure 5 This is a schematic diagram of the network slice allocation device provided in the embodiments of this application;
[0052] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0053] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.
[0054] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0055] Network slicing can provide customized and differentiated network functions and services to clients with different needs. Different slices are independent and isolated from each other. Network functions are customized according to client requirements, providing end-to-end customized network services. Therefore, the network architecture has very high flexibility. End-to-end means that slicing technology involves not only the core network but also the access network, transmission network, and bearer network. Customization means managing the lifecycle of network slices according to network requirements while customizing the bearer services, connection relationships, implemented functions, capacity, and quality of service according to different needs. When providing end-to-end network slicing services in the network, the technical indicators, network capabilities, and parameters associated with each domain can be set independently without affecting each other. These can be flexibly adjusted according to customer needs, thereby solving end-to-end network bandwidth, quality of service, and security issues related to slicing.
[0056] With the rapid development of technologies such as virtual reality and augmented reality, smart cameras and industrial cameras are evolving towards ultra-high definition. The high precision requirements of industrial and outdoor inspections have pushed high-bandwidth connectivity to new heights. Although customized slices can be provided to clients based on different network needs, the increasing bandwidth demands of new technologies and the growing number of clients inevitably lead to slice resource shortages. When network slices become congested, client devices may fail to register slices. In existing technologies, 5GS cannot control the slice registration status according to application needs, causing client devices to be unable to perceive the slice status. Therefore, client devices may repeatedly register before sufficient slice resources are restored. This increases network signaling burden and power consumption of client devices, and may also negatively impact the experience of clients already registered to the current network slice.
[0057] In view of this, the embodiments of this application provide a network slice allocation method, which can avoid client devices repeatedly submitting slice application requests at the same time because slices are occupied, thus saving resources.
[0058] The network slicing method provided in this application is applied to a 5G system. The network elements of the 5G system include at least: Radio Access Network (RAN), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Application Function (AF), Network Exposure Function (NEF), Policy Control Function (PCF), Public Land Mobile Network (PLMN), Network Data Application Function (NWDAF), and Operation Administration and Maintenance (OAM).
[0059] Understandably, 5G systems may also include other network elements not mentioned above.
[0060] Example 1
[0061] like Figure 1As shown, this application provides a network slice allocation method, including:
[0062] S1: Respond to the first client's registration request for network slicing, allowing the first client to establish a PDU session in the network slice;
[0063] In some embodiments, network slicing is an on-demand networking approach that allows operators to separate multiple virtual end-to-end networks on a unified infrastructure. Each network slice is logically isolated from the radio access network to the bearer network and then to the core network to adapt to a wide variety of applications.
[0064] See Figure 2 The method of this application is explained in conjunction with the information interaction between network elements in a 5G system:
[0065] Step 21: The AF initiates an event request to the NWDAF. The request information includes: event flag information, specifically slice registration status control, and network slice flag information, specifically Single Network Slice Selection Assistance Information (S-NSSAI), etc. For untrusted AFs, the AF will be authorized through the NEF. After authorization, the NEF will forward the request to the NWDAF.
[0066] Step 22: NWDAF requests data from OAM; the requested data includes the time interval for reporting data, the type of data requested: throughput, number of Radio Resource Control (RRC) connections, radio resource utilization, etc.
[0067] Step 23: OAM responds to NWDAF's request;
[0068] Step 24: NWDAF initiates a Quality of Service (QoS) monitoring request to PCF;
[0069] Step 25: PCF generates a service quality monitoring policy based on the NWDAF's QoS monitoring request and sends it to SMF. The monitoring policy includes uplink and downlink monitoring rules, time intervals, etc.
[0070] In some embodiments, QoS is a technology used to address network latency and congestion, guaranteeing network transmission bandwidth, reducing network transmission latency, and improving network resource utilization. A QoS policy contains one or more rate-limiting rules and monitoring rules, and a rate-limiting rule contains one or more flow classification rules. QoS divides traffic through flow classification rules and guarantees bandwidth for traffic under higher-priority rate-limiting rules based on the configured priority of the rate-limiting rules.
[0071] Step 26: The SMF generates an uplink monitoring configuration from the received monitoring rules and sends it to the RAN via an N1 message;
[0072] In some embodiments, N1 is the transparent interface from the UE to the core AMF via the RAN. An N1 message refers to a message sent through the N1 interface.
[0073] Step 27: RAN responds to SMF;
[0074] Step 28: The SMF generates downlink monitoring configuration from the received monitoring rules and sends it to the UPF through the N4 session modification process;
[0075] In some embodiments, the N4 interface serves as a bridge between the UPF unit and the SMF unit. It is used for PDU session management and traffic redirection to the UPF & PDU.
[0076] Step 29: UPF responds to SMF;
[0077] Step 210: SMF responds to PCF;
[0078] Step 211: PCF responds to NWDAF;
[0079] Step 212: NWDAF responds to AF, or responds to AF via NEF;
[0080] Step 213: The first client UE#1 requests to establish a PDU session on the network slice, that is, the first client UE#1 sends a registration request for the network slice;
[0081] S2: Continuously predict the occupancy status of network slices;
[0082] S3: Respond to the second client's request to establish a PDU session in the network slice. When the network slice is in a blocked state, send a rejection message to the second client.
[0083] Step 219: The second client UE#2 requests to establish a PDU session on the network slice, that is, the second client UE#2 sends a registration request for the network slice;
[0084] In some embodiments, the second client UE#2 enables the 5G system to know the network slice requested by the second client by including the S-NSSAI of the network slice in the request information.
[0085] Step 220: When the AMF receives a notification from the NWDAF indicating that the network slice allows client registration, that is, allows the client to establish a PDU session on the network slice, UE#2 continues to execute the PDU session establishment process and successfully establishes a PDU session on the slice; when the AMF receives a notification from the NWDAF indicating that the network slice rejects client registration, this step is skipped and step 21 is executed directly.
[0086] Step 221: AMF returns a rejection message to UE#2, including the reason for the rejection: slice congestion.
[0087] See Figure 3 When a network slice transitions from a congested state to a normal state, the NWDAF notifies the AMF of the network slice registration status. The AMF then notifies the relevant clients based on the previously rejected communication list, enabling the clients to re-register with the network slice.
[0088] Specifically, see Figure 3 Step 31: NWDAF performs statistical analysis on the slice status and obtains the analysis results;
[0089] Step 32: When the analysis results indicate that the network slice has returned to normal, the slice registration instruction will be sent to the AMF.
[0090] Step 33: The AMF will notify UE#2, which previously rejected the PDU session establishment request, of the allow slice registration indication.
[0091] Step 34: UE#2 responds to AMF;
[0092] Step 35: UE#2 initiates a PDU session establishment request to the network slice again as needed and successfully establishes a PDU session.
[0093] S4: When the network slice is idle, send a registration permission instruction to the second client.
[0094] In some embodiments, the first client and the second client are terminal devices, which may be computers, laptops, mobile phones, tablets, or other devices with communication functions.
[0095] In the above implementation process, when a network slice is occupied, the occupancy status of that network slice is predicted. When a second client requests that network slice, if the predicted occupancy status is congested, a rejection message is sent to the second client. When the network slice status becomes idle, a re-request request is sent to the second client, causing the second client to resend the request to establish a PDU session on the network slice. This avoids the client repeatedly submitting slice request requests after receiving the initial rejection message, thus avoiding wasting client device resources. Using continuous prediction to obtain the slice occupancy status, compared to existing technologies that obtain slice status through data collection between multiple network elements, can reduce the response time of the 5G system in multiple client scenarios and improve communication efficiency.
[0096] In some embodiments, continuously predicting the occupancy status of network slices includes:
[0097] Obtain working parameters;
[0098] Input the working parameters into the pre-trained machine learning model to obtain the occupancy status of the network slices.
[0099] In the above implementation process, introducing machine learning models into the 5G system to predict the occupancy status of network slices is beneficial to realizing the intelligence of the 5G system, improving communication smoothness and speed, and further saving communication resources.
[0100] In some embodiments, the operating parameters include: a first operating parameter and a second operating parameter;
[0101] Obtain working parameters, including:
[0102] Generate the first monitoring strategy and send the first monitoring strategy to the client-side functional unit;
[0103] The client-side functional unit obtains the first operating parameters according to the first monitoring strategy;
[0104] Generate a second monitoring strategy and send the second monitoring strategy to the operation and maintenance management unit;
[0105] The operation and maintenance management unit obtains the second operating parameters according to the second monitoring strategy.
[0106] For example, see Figure 2 Within the 5G system, this corresponds to the following process:
[0107] Step 214: UPF uploads the first operating parameters to NWDAF according to the first monitoring strategy;
[0108] Step 215: OAM uploads the second working parameters to NWDAF according to the second monitoring strategy;
[0109] Step 216: NWDAF uses the collected working parameters to perform statistical analysis on the network slices and obtains the analysis results;
[0110] Step 217: NWDAF notifies AMF of the slice registration status;
[0111] Step 218: AMF responds to NWDAF.
[0112] In the above implementation process, different network elements in 5GS have different functions. The working parameters of different network elements reflect the working status of different aspects of network slices. The working status of different aspects reflects the occupancy status of network slices to varying degrees. By collecting the first working parameters and the second working parameters in the client-side functional unit and the operation and maintenance management unit based on different monitoring strategies, the occupancy status of network slices can be comprehensively predicted, further reducing the number of times the client submits network slice application requests and saving communication resources.
[0113] In some embodiments, the method further includes:
[0114] When the occupancy status is blocked, add the second client to the communication list;
[0115] When the occupancy status is unregistered, an idle information is sent to the second client so that the second client resends the request to apply for a network slice.
[0116] For example, there are a first client, a second client, and a third client. Currently, the first client establishes a session on a network slice. Although the second client and the third client sequentially send network slice allocation requests to the 5G system, the 5G system sequentially adds the second client and the third client to the communication list. When the network slice occupancy status is continuously predicted to be idle, the system first sends a registration permission instruction to the second client so that the second client can re-apply for the network slice. If no network slice application request is received from the second client within a preset time, the system then sends a network slice application request to the third client.
[0117] In some embodiments, considering that different clients have different levels of importance in communication or different communication capabilities, when the occupancy status is blocked, adding a second client to the communication list includes:
[0118] The order of clients in the communication list is determined based on pre-assigned client weights;
[0119] Clients are added to the communication list in order.
[0120] When the occupancy status is unregistered, an idle information is sent to the second client so that the second client resends its request to request a network slice, including:
[0121] Idle information is sent to the clients in the communication list according to their order.
[0122] In some embodiments, idle information can be sent to clients in the communication list at the same time, and the right to occupy the network slice can be contested based on the communication capabilities of the clients in the communication list and the communication capabilities of the communication chain they belong to.
[0123] In the above implementation process, precise control of the communication process is achieved by using a communication list and making the allocation of network slices orderly and plannable.
[0124] In some embodiments, the machine learning model includes: a logistic regression model and an XGboost model;
[0125] Input the working parameters into the pre-trained machine learning model to obtain the occupancy status of the network slices, including:
[0126] Input the working parameters into the pre-trained logistic regression model and obtain the first output result;
[0127] Input the first output result into the XGboost model to obtain the occupancy status of the network slice.
[0128] For example, see Figure 4 The network slice metrics data collected by NWDAF include throughput, number of RRC connections, wireless resource utilization, transmission latency, etc. Based on the metrics data, a label is obtained to determine whether the network slice registration status needs to be turned off, and a supervised dataset is constructed.
[0129] NWDAF is based on a supervised dataset. It first obtains the initial output through a logistic regression model, and then obtains the final output through an XGboost model. The mean squared error is used as the loss function and the gradient descent method is used for model training. To improve the generalization ability of the model, the logistic regression model is trained using the K-fold cross-validation method.
[0130] In the above implementation process, different working parameters have different formats and units. The logistic regression model does not need to scale the input data and has a fast training speed. It can accurately predict the network slice occupancy status while maintaining communication speed.
[0131] Example 2
[0132] This application also provides a network slice application method, applied to a client, including:
[0133] Send a registration request for network slicing to the 5G system;
[0134] Upon receiving a rejection message from the 5G system, stop sending the request to establish a PDU session on the network slice;
[0135] It receives the registration permission instruction from the 5G system and resends the registration request for network slicing to the 5G system.
[0136] The method executed by the client corresponds to that in Example 1, and will not be described again here.
[0137] Example 3
[0138] Figure 5 A schematic structural block diagram of a network slice allocation device provided in this application is presented. It should be understood that the method performed by this device corresponds to the method embodiments described above and is capable of performing the steps involved in the aforementioned method. The specific functions of this device can be found in the description above; detailed descriptions are omitted here to avoid repetition. The device includes at least one software functional module that can be stored in memory or embedded in the device's operating system (OS) in the form of software or firmware. Specifically, the device includes: a receiving module 1, configured to respond to a first client's registration request for a network slice and allow the first client to establish a PDU session on the network slice; a prediction module 2, configured to continuously predict the occupancy status of the network slice; the receiving module 1 is also configured to respond to a second client's request to establish a PDU session on the network slice; and a sending module 3, configured to send a rejection message to the second client when the network slice is in a blocked state; the sending module 3 is also configured to send a registration permission instruction message to the second client when the network slice is in an idle state.
[0139] This application also provides an electronic device, please refer to [link to application]. Figure 6 , Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of this application. The electronic device may include a processor 61, a communication interface 62, a memory 63, and at least one communication bus 64. The communication bus 64 is used to enable direct communication between these components. In this embodiment, the communication interface 62 of the electronic device is used for signaling or data communication with other node devices. The processor 61 may be an integrated circuit chip with signal processing capabilities.
[0140] The processor 61 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 61 can be any conventional processor.
[0141] The memory 63 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 63 stores computer-readable instructions, which, when executed by the processor 61, allow the electronic device to perform the various steps involved in the above method embodiments.
[0142] Alternatively, the electronic device may also include a storage controller and an input / output unit.
[0143] The memory 63, memory controller, processor 61, peripheral interface, and input / output unit are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses 64. The processor 61 is used to execute executable modules stored in the memory 63, such as software function modules or computer programs included in electronic devices.
[0144] Input / output units are used to enable users to create tasks and set optional start periods or preset execution times for those tasks, facilitating user-server interaction. Input / output units can be, but are not limited to, a mouse and keyboard.
[0145] Understandable. Figure 6 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown. Figure 6The components shown can be implemented using hardware, software, or a combination thereof.
[0146] This application also provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer program is executed by a processor to implement the method of the method embodiment. To avoid repetition, the details will not be repeated here.
[0147] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0148] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0149] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0150] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0151] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0152] It should be noted that, in this document, relational terms such as "first" and "second" are used merely 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 a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.
Claims
1. A network slice allocation method, characterized in that, Applied to 5G systems, including: In response to the first client's registration request regarding the network slice, the first client is allowed to establish a PDU session in the network slice; Obtain working parameters; When the first client establishes a PDU session on the network slice, it inputs the working parameters into a pre-trained machine learning model at preset intervals to predict the occupancy status of the network slice. In response to the second client's registration request for the network slice, if the predicted occupancy status of the network slice is blocked, a rejection message is sent to the second client; When the network slice is in an idle state, a registration permission instruction is sent to the second client. The method further includes: When the occupancy status is blocked, the second client is added to the communication list; When the occupancy status is unregistered, an idle information is sent to the second client so that the second client resends the request to apply for the network slice.
2. The network slice allocation method according to claim 1, characterized in that, The operating parameters include: a first operating parameter and a second operating parameter; The acquisition of working parameters includes: A first monitoring strategy is generated and sent to the user plane function unit so that the user plane function unit can obtain the first working parameters according to the first monitoring strategy. A second monitoring strategy is generated and sent to the operation and maintenance management unit so that the operation and maintenance management unit can obtain the second operating parameters according to the second monitoring strategy.
3. The network slice allocation method according to claim 2, characterized in that, The operating parameters include one or more of the following: the number of wireless resource control connections for the network slice and the wireless resource utilization rate. The second operating parameter includes: transmission delay.
4. The network slice allocation method according to claim 1, characterized in that, The machine learning models include: a logistic regression model and an XGboost model; The step of inputting the working parameters into a pre-trained machine learning model to obtain the occupancy status of the network slice includes: Input the working parameters into the pre-trained logistic regression model to obtain the first output result; The first output result is input into the XGboost model to obtain the occupancy status of the network slice.
5. A network slice allocation device, characterized in that, include: The receiving module is used to respond to the registration request of the first client regarding the network slice, allowing the first client to establish a PDU session in the network slice; The prediction module is used to continuously predict the occupancy status of the network slice; The receiving module is also used to respond to a second client's registration request regarding the network slice; The sending module is used to send a rejection message to the second client when the predicted occupancy status of the network slice is blocked; The sending module is also configured to send a registration permission instruction to the second client when the network slice is in an idle state; The network slice allocation device is further configured to add the second client to the communication list when the occupancy status is blocked; and to send idle information to the second client when the occupancy status is unregistered, so that the second client resends the request to apply for the network slice. Specifically, the prediction module is used to obtain working parameters; when the first client establishes a PDU session on the network slice, it inputs the working parameters into a pre-trained machine learning model at preset intervals to predict the occupancy status of the network slice.
6. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1-4.