Policy optimization method and device, electronic equipment and storage medium

Abstract

The application provides a strategy optimization method and device, electronic equipment and a storage medium, wherein the method comprises: determining a base station level optimization strategy by optimizing an original parameter output result according to original service parameters and original resource available information; and sending the base station level optimization strategy to a base station. The strategy optimization method and device, electronic equipment and storage medium provided by the application can realize the coordination and interaction of services and air interface resources by deep integration of a wireless network intelligent control platform and a MEC system through information interaction between a strategy collaborative optimization module of the wireless network intelligent control platform and the MEC system, optimize the original parameter output result by using original service parameters and original resource available information, maximize the use of air interface resources while optimizing the strategy rules of the base station, and improve the user experience perception.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a strategy optimization method, apparatus, electronic device, and storage medium. Background Technology

[0002] Multi-Access Edge Computing (MEC) enables operators and third-party services to be hosted near the access point of user equipment (UE), thereby achieving efficient service delivery by reducing end-to-end latency and load on the transmission network. Simultaneously, the introduction of a wireless network intelligent control platform allows for comprehensive intelligent control and management of the access network, revolutionizing traditional management models, enabling more effective utilization of wireless network resources, and reducing the overall network cost investment for operators.

[0003] Leveraging 5G network MEC systems to provide cloud computing capabilities and IT service environments closer to users at the network edge offers features such as ultra-low latency, ultra-high bandwidth, localization, and high real-time performance. Combined with a wireless network intelligent control platform, this facilitates the analysis of wireless network resources, user traffic data, and behavioral operations using technologies like artificial intelligence, thereby improving the accuracy of resource allocation and enhancing user experience. However, the interaction analysis between the wireless network intelligent control platform and the MEC system is currently still in the discussion stage, lacking corresponding technologies and standards to support their interaction. Summary of the Invention

[0004] This invention provides a strategy optimization method, apparatus, electronic device, and storage medium to realize information interaction between a wireless network intelligent control platform and an MEC system.

[0005] This invention provides a strategy optimization method, comprising:

[0006] Based on the original service parameters and original resource availability information, the original parameter output results are optimized to determine the base station-level optimization strategy;

[0007] The base station-level optimization strategy is sent to the base station.

[0008] According to the strategy optimization method provided by the present invention, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0009] Receive the original service parameters sent by the multi-access edge computing system.

[0010] According to the strategy optimization method provided by the present invention, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0011] Receive the original resource availability information sent by the intelligent control middleware.

[0012] According to the strategy optimization method provided by the present invention, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0013] Receive the raw parameter output results sent by the third-party application optimization module.

[0014] According to the strategy optimization method provided by the present invention, after determining the base station-level optimization strategy, the method further includes:

[0015] The base station-level optimization strategy is sent to the multi-access edge computing system.

[0016] The present invention also provides a strategy optimization method, comprising:

[0017] Receive the base station-level optimization strategy sent by the strategy coordination optimization module;

[0018] The optimized user service parameters are determined based on the user's service level agreement and the base station-level optimization strategy.

[0019] The optimized user service parameters are sent to the core network.

[0020] According to the strategy optimization method provided by the present invention, before receiving the base station-level optimization strategy sent by the strategy collaborative optimization module, the method further includes:

[0021] The original business parameters are sent to the strategy collaborative optimization module.

[0022] The present invention also provides a strategy optimization method, comprising:

[0023] Receive optimized user service parameters sent by the multi-access edge computing system;

[0024] Determine the traffic splitting optimization strategy based on the optimized user service parameters;

[0025] The traffic splitting optimization strategy is sent to the multi-access edge computing router.

[0026] The present invention also provides a strategy optimization apparatus, comprising:

[0027] The first determining module is used to optimize the output results of the original parameters based on the original service parameters and the original resource availability information to determine the base station-level optimization strategy.

[0028] The first sending module is used to send the base station-level optimization strategy to the base station.

[0029] According to the strategy optimization apparatus provided by the present invention, the apparatus further includes a first receiving module;

[0030] The first receiving module is used to receive the original service parameters sent by the multi-access edge computing system.

[0031] According to the strategy optimization apparatus provided by the present invention, the apparatus further includes a second receiving module;

[0032] The second receiving module is used to receive the original resource availability information sent by the intelligent control middleware.

[0033] According to the strategy optimization apparatus provided by the present invention, the apparatus further includes a third receiving module;

[0034] The third receiving module is used to receive the raw parameter output results sent by the third-party application optimization module.

[0035] According to the strategy optimization apparatus provided by the present invention, the apparatus further includes a second transmission module;

[0036] The second sending module is used to send the base station-level optimization strategy to the multi-access edge computing system.

[0037] The present invention also provides a strategy optimization apparatus, comprising:

[0038] The fourth receiving module is used to receive base station-level optimization strategies sent by the strategy coordination optimization module;

[0039] The second determining module is used to determine the optimized user service parameters based on the user's service level agreement and the base station-level optimization strategy.

[0040] The third sending module is used to send the optimized user service parameters to the core network.

[0041] According to the strategy optimization apparatus provided by the present invention, the apparatus further includes a fourth transmission module;

[0042] The fourth sending module is used to send the original business parameters to the strategy collaborative optimization module.

[0043] The present invention also provides a strategy optimization apparatus, comprising:

[0044] The fifth receiving module is used to receive optimized user service parameters sent by the multi-access edge computing system;

[0045] The third determining module is used to determine the traffic splitting optimization strategy based on the optimized user service parameters.

[0046] The fifth sending module is used to send the traffic splitting optimization strategy to the multi-access edge computing router.

[0047] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the strategy optimization methods described above.

[0048] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described strategy optimization methods.

[0049] The strategy optimization method, device, electronic equipment, and storage medium provided by this invention, through information interaction between the strategy collaborative optimization module of the wireless network intelligent control platform and the MEC system, deeply integrate the wireless network intelligent control platform and the MEC system, enabling coordinated interaction between services and air interface resources. It optimizes the output results of the original parameters using the original service parameters and the original resource availability information, maximizing the utilization of air interface resources while optimizing the base station's strategy rules, thereby improving the user experience. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a schematic diagram of the interaction architecture between the wireless network intelligent control platform and the MEC system provided in this embodiment of the invention;

[0052] Figure 2 This is one of the flowcharts illustrating the strategy optimization method provided in this embodiment of the invention;

[0053] Figure 3 This is a second flowchart illustrating the strategy optimization method provided in this embodiment of the invention;

[0054] Figure 4 This is the third flowchart illustrating the strategy optimization method provided in this embodiment of the invention;

[0055] Figure 5 This is the fourth flowchart of the strategy optimization method provided in the embodiments of the present invention;

[0056] Figure 6 This is the fifth flowchart illustrating the strategy optimization method provided in this embodiment of the invention;

[0057] Figure 7This is one of the structural schematic diagrams of the strategy optimization device provided in the embodiments of the present invention;

[0058] Figure 8 This is a second schematic diagram of the strategy optimization device provided in the embodiments of the present invention;

[0059] Figure 9 This is the third schematic diagram of the strategy optimization device provided in the embodiments of the present invention;

[0060] Figure 10 This is a schematic diagram of the physical structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0062] First, some English words and abbreviations that will appear in the embodiments of this invention will be explained:

[0063] The 3rd Generation Partnership Project (3GPP)

[0064] 5G (Fifth Generation Wireless Systems) technology;

[0065] Enhanced Mobile Broadband (eMBB);

[0066] Ultra-reliable and low-latency communications (URLLC);

[0067] Massive Machine Type Communication (mMTC);

[0068] Next-Generation Radio Access Network (NG-RAN);

[0069] 5G base station (gNB);

[0070] Centralized Unit (CU);

[0071] Control Plane (CP);

[0072] User Plane (UP);

[0073] User Equipment (UE);

[0074] Multi-Access Edge Computing (MEC);

[0075] MEC System Level;

[0076] MEC Host Level;

[0077] MEC Orchestrator;

[0078] Operations Support System;

[0079] MEC Platform;

[0080] User Plane Function (UPF);

[0081] Local Area Data Network (LADN);

[0082] Application Function (AF);

[0083] Network Exposure Function (NEF);

[0084] Policy Control Function (PCF);

[0085] Unified Data Management (UDM);

[0086] Network Repository Function (NRF);

[0087] Network Slice Selection Function (NSSF);

[0088] Authentication Server Function (AUSF);

[0089] Access and Mobility Management Function (AMF);

[0090] Session Management Function (SMF);

[0091] Data Network (DN);

[0092] Network Functions (NFs);

[0093] European Telecommunications Standards Institute (ETSI)

[0094] User experience (Quality of Experience, QoE);

[0095] Service Level Agreement (SLA).

[0096] It should be noted that N1, N3, N4, N6, and Naf represent the code names of the existing interfaces. These interfaces and code names are common in current 5G technology and can be understood by those skilled in the art based on current 5G technology.

[0097] 3GPP defines three major scenarios for 5G applications: eMBB, URLLC, and mMTC. Among them, the eMBB scenario provides high-bandwidth mobile services, which puts enormous pressure on the wireless backhaul network, requiring services to be moved as far down as possible to the network edge to offload local services. The URLLC scenario provides ultra-reliable, ultra-low-latency communication, such as autonomous driving and industrial control, which also requires services to be moved down to the network edge to reduce network latency caused by network transmission.

[0098] MEC is used in 5G applications to reduce network latency caused by network transmission by being deployed at the network edge. The 5G core network separates the CP (Content Provider) and UP (Uploader), allowing the UPF (Uploader Function) to be deployed at the network edge, while control plane functions such as PCF (Precision Control Function) and SMF (Small Control Function) can be centrally deployed. MEC enables operators and third-party services to be hosted near the user terminal's access point, thereby achieving efficient service delivery by reducing end-to-end latency and load on the transport network.

[0099] The ETSI GS MEC specification defines a reference architecture for MEC systems, which include the MEC host level and the MEC system level. The MEC host level further comprises the MEC platform, MEC applications, and virtualization infrastructure. The virtualization infrastructure provides MEC applications with compute, storage, and network resources, and offers persistent storage and time-related information. It includes a data forwarding plane to enforce forwarding rules for data received by the MEC platform and to route data between various applications, services, and networks. MEC applications are virtual machine instances running on the MEC virtual infrastructure and communicate with the MEC platform.

[0100] The MEC system level comprises an operations support system and a MEC orchestrator. The MEC orchestrator is the core function of MEC system-level management, primarily responsible for maintaining an overall view of the MEC system, providing macro-level control over MEC network resources and capacity, including all deployed MEC hosts and services, available resources on each host, instantiated applications, and network topology. When selecting a target MEC host for a user's access, the MEC orchestrator weighs the user's needs and the available resources of each host to select the most suitable MEC host. When a user needs to switch MEC hosts, the MEC orchestrator triggers the switchover procedure.

[0101] From the perspective of the MEC system, the Operations Support System (OSS) is the highest-level management entity supporting system operation. OSS receives requests from the user service portal and user terminals to instantiate or terminate MEC applications, and checks the integrity and authorization information of application data packets and requests. Request data packets authenticated and authorized by OSS are forwarded to the MEC orchestrator for further processing.

[0102] The 5G core network selects a UPF (User Platform Provider) close to the UE and performs traffic control from the UPF to the local data network via the N6 interface. This can be managed based on the UE's subscription data, UE location, information from application functions, policies, or other relevant traffic.

[0103] Given the high cost of setting up a single 5G network site and the large scale of network construction, a wireless network intelligent control platform has been introduced to comprehensively and intelligently control and manage the access network, effectively utilizing wireless network resources to reduce the overall network cost investment of operators.

[0104] Figure 1 This is a schematic diagram of the interaction architecture between the wireless network intelligent control platform and the MEC system provided in this embodiment of the invention, as shown below. Figure 1As shown, the functional entities of an MEC system consist of two parts: the MEC host level and the MEC system level. The MEC host level is further divided into the MEC platform, MEC applications, and UPF. The UPF is a gateway device between mobile infrastructures, such as NG-RAN and LADN in the diagram.

[0105] The UPF provides a communication connection with the 5G core network outside the MEC system through the N4 interface. The number of 5G core networks can be one or more. The UPF receives uplink data services from the UE terminal user accessing the LADN from the N3 interface on the base station side, and receives downlink data from the N6 interface on the LADN side and hands it over to the base station. Finally, the base station forwards the data to the UE through the radio channel.

[0106] The MEC system level includes the MEC orchestrator and the operations support system. The MEC system acts as both AF (Action Functions) and DN (Network Functions) relative to the 5G core network, interacting with it. The MEC orchestrator is a functional entity within the MEC system level; it can act as an AF to interact with the NEF (Network Functions), or in some cases, it can directly interact with different network functions of the target 5G network.

[0107] For example, an untrusted AF can influence user plane policies through NEF, PCF, and SMF, with SMF distributing the policies to UPF via the N4 interface; or a trusted AF can influence user plane policies directly through PCF and SMF, with SMF distributing the policies to UPF via the N4 interface.

[0108] As a special form of AF, the MEC system can interact more with NEF or PCF, and invoke other network open capabilities of the 5G core network, such as message subscription and QoS. The 5G core network selects the UPF closest to the UE and performs flow control from the UPF to the LADN through interface N6.

[0109] The wireless network intelligent control platform comprises a data warehouse module, an AI model training module, a third-party application optimization module, a policy collaboration optimization module, and intelligent control middleware. It should be noted that the above module division and naming are merely illustrative, intended to differentiate the functions of each module.

[0110] The data warehouse module receives various types of base station-related data from the intelligent control middleware and performs preprocessing and storage. The data is categorized into near real-time (NRT) data and non-real-time data based on its real-time nature. Near real-time data refers to cached data that can only be indexed after a data segment is generated; therefore, it is near real-time data rather than real-time data.

[0111] Non-real-time data is mainly input into the AI ​​model training module for model training, while near-real-time data is mainly input into the third-party application optimization module for iterative optimization of the optimization algorithm.

[0112] After obtaining preprocessed non-real-time data from the data warehouse module, the AI ​​model training module outputs AI models in the form of functions, etc. These models will be used by various applications in the third application optimization module as needed to obtain the policy rule information of each application.

[0113] The third-party application optimization module mainly deploys various third-party applications for optimizing or managing wireless networks based on AI models, such as load balancing, QoE optimization, and RAN slicing as shown in the diagram.

[0114] The policy-coordinated optimization module connects and exchanges information with third-party applications used for wireless network optimization or management, such as load balancing, QoE optimization, and RAN slicing, through the internal interface of the wireless network intelligent control platform. The policy-coordinated optimization module receives the output results from these third-party applications, including wireless network parameters requiring optimization and traffic prediction information.

[0115] The strategy collaboration optimization module interacts with the MEC system through the interface Xc to obtain raw business parameters such as the user's business type, business resource prediction information, and user SLA.

[0116] The strategy coordination optimization module interacts with the intelligent control middleware that issues wireless network commands and collects data through the internal interface of the wireless network intelligent control platform to obtain the resource availability information of the current base station.

[0117] The strategy coordination and optimization module coordinates and optimizes strategy information, including conflict resolution and strategy adjustment, and sends the final base station-level strategy optimization results to the intelligent control middleware. The strategy optimization results include strategy rules and instructions to be executed.

[0118] Taking resource allocation as an example, policy rules refer to how much resource to allocate to different third-party applications or the priority of resource allocation, while execution instructions refer to the policy information at the user level or base station level being sent to the user or base station for execution.

[0119] The coordination of policy information mainly addresses conflict resolution. This refers to the conflict between adjustment rules obtained through different interfaces for the same parameter. For example, the resource allocation for a certain third-party application needs to be increased according to the Xc interface of the MEC system, while the resource allocation for the same third-party application needs to be reduced according to the internal interface of the wireless network intelligent control platform obtained from the intelligent control middleware. In this case, the policy coordination and optimization module needs to resolve the conflict and formulate the final policy rules to send to the intelligent control middleware.

[0120] The optimization of policy information mainly targets policy adjustments, which means that the adjustment rules obtained through different interfaces for the same parameter are different. For example, the resource allocation for a certain third-party application obtained from the Xc interface of the MEC system needs to be increased by 10%, while the resource allocation for the same third-party application obtained from the intelligent control middleware through the internal interface of the wireless network intelligent control platform needs to be increased by 20%. In this case, the policy coordination optimization module needs to adjust this difference and formulate the final policy rules to send to the intelligent control middleware.

[0121] The intelligent control middleware is primarily responsible for collecting base station-related data and simultaneously sending the policy optimization results from the policy coordination and optimization module to the base station for execution. Optionally, the intelligent control middleware can be a functional module installed within the base station.

[0122] This invention provides a schematic diagram of the interaction architecture between the wireless network intelligent control platform and the MEC system, illustrating the basic architecture of information interaction between the wireless network intelligent control platform, the 5G core network, the UE, the base station, and the MEC system. The wireless network intelligent control platform provides comprehensive intelligent control and management of the access network, more effectively utilizing wireless network resources to reduce the overall network cost investment of wireless network operators. The combination of the wireless network intelligent control platform and the MEC system allows for the analysis of base station resources, user traffic data, and behavioral operations using technologies such as artificial intelligence, thereby improving the accuracy of resource allocation and enhancing user experience.

[0123] Figure 2 This is one of the flowcharts illustrating the strategy optimization method provided in this embodiment of the invention, such as... Figure 2 As shown, this embodiment of the invention provides a strategy optimization method, the execution body of which is a strategy collaborative optimization module, including:

[0124] Step 201: Based on the original service parameters and original resource availability information, optimize the output results of the original parameters to determine the base station-level optimization strategy.

[0125] Specifically, the strategy coordination optimization module comprehensively judges the original output results of the third-party application optimization module based on the original resource availability information queried from the intelligent control middleware and the original service parameters queried from the MEC system, resolves conflicts or adjusts strategies, and formulates base station-level optimization strategies.

[0126] The third-party application optimization module for wireless network optimization or management based on AI models receives near real-time data output from the data warehouse module, and also receives function models output from the AI ​​model training module to deploy various third-party applications, such as load balancing, QoE optimization, RAN slicing, etc.

[0127] The third-party application optimization module outputs raw parameters, including the wireless network parameters to be optimized and traffic prediction information. The policy-coordinated optimization module obtains the raw parameter outputs from the third-party application optimization module through an interface within the wireless network control platform.

[0128] The strategy collaborative optimization module interacts with the MEC orchestrator of the MEC system through the Xc interface to obtain raw service parameters such as the user's service type, service resource prediction information, and user SLA sent by the MEC orchestrator.

[0129] The strategy coordination optimization module interacts with the intelligent control middleware through the internal interface of the wireless network intelligent control platform to obtain the original resource availability information of the current wireless network. The intelligent control middleware is used for issuing wireless network commands and collecting data; in this embodiment of the invention, it mainly refers to issuing commands and collecting data for base stations.

[0130] The strategy coordination optimization module optimizes the output results of the original parameters based on the original service parameters and the original resource availability information to determine the base station-level optimization strategy, including conflict resolution and strategy adjustment.

[0131] For example, if the output of the original parameters is adjusted based on the original business data, and it is determined that the resources allocated to a certain third-party application need to be increased, while the output of the original parameters is adjusted based on the original resource availability information, and it is determined that the resources allocated to that third-party application need to be reduced, then the strategy coordination and optimization module needs to resolve the conflict and determine the final strategy rules.

[0132] For example, if the output of the original parameters is adjusted based on the original business data, and it is determined that the resources allocated to a certain third-party application need to be reduced by 10%, and the output of the original parameters is adjusted based on the original resource availability information, and it is determined that the resources allocated to the third-party application need to be reduced by 20%, then the strategy coordination and optimization module needs to coordinate the final reduction of resources allocated to the third-party application to determine the final strategy rules.

[0133] In this invention, the base station-level optimization strategy refers to the policy rules issued at the base station level, including policy rules and execution instructions. Unlike the PCF in the 5G core network, the PCF's policy control is user-level policy information.

[0134] Step 202: Send the base station-level optimization strategy to the base station.

[0135] Specifically, after the strategy coordination and optimization module determines the final optimization strategy, it needs to send the optimization strategy to the base station for execution.

[0136] The strategy coordination and optimization module sends the final optimization strategy, such as strategy rules and execution instructions, to the intelligent control middleware. The intelligent control middleware is used to collect base station-related data and simultaneously distributes the optimization strategy from the strategy coordination and optimization module to the base station for execution.

[0137] Among them, the intelligent control middleware can be a functional module set inside the base station.

[0138] The strategy optimization method provided in this invention deeply integrates the wireless network intelligent control platform and the MEC system through information interaction, realizing coordinated interaction between services and air interface resources. It optimizes the output results of the original parameters using the original service parameters and the original resource availability information, maximizing the utilization of air interface resources while optimizing the base station's strategy rules, thereby improving the user experience.

[0139] Optionally, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0140] Receive the original service parameters sent by the multi-access edge computing system.

[0141] Specifically, the original business parameters are obtained from the MEC system by the strategy collaboration optimization module.

[0142] The strategy collaboration optimization module and the MEC orchestrator of the MEC system exchange information through the Xc interface to query raw business parameters, including user business type, business resource prediction information, user SLA and other parameters.

[0143] The MEC orchestrator is a core function in MEC system-level management, used to maintain an overall view of the MEC system, including deployed MEC hosts, available resources, available MEC services, and network topology.

[0144] The strategy optimization method provided in this embodiment of the invention realizes the coordinated interaction of services and air interface resources between the wireless network intelligent control module and the MEC system through information interaction between the wireless network intelligent control module and the MEC system. It optimizes the original parameter output results by using the original service parameters obtained from the MEC system, maximizes the utilization of air interface resources, optimizes the base station's strategy rules, and improves the user experience.

[0145] Optionally, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0146] Receive the original resource availability information sent by the intelligent control middleware.

[0147] Specifically, the original resource availability information is obtained by the strategy collaborative optimization module from the intelligent control middleware.

[0148] The intelligent control middleware is used to collect base station-related data. The strategy coordination and optimization module interacts with the intelligent control middleware through the interface inside the wireless network intelligent control platform to obtain the current base station resource availability information sent by the intelligent control middleware, i.e., the original resource availability information.

[0149] Among them, the intelligent control middleware can serve as a functional module within the base station, collecting relevant data from the base station and simultaneously sending the final optimization strategy from the strategy collaboration optimization module to the base station for execution.

[0150] The strategy optimization method provided in this invention provides a comprehensive intelligent control and management system for the access network through a wireless network intelligent control platform. This system makes more effective use of wireless network resources to reduce the overall network cost investment of base station operators. At the same time, it optimizes the original output results based on the original resource availability information and original service parameters, maximizing the use of air interface resources while optimizing the base station's strategy rules, thereby improving the user experience.

[0151] Optionally, before determining the base station-level optimization strategy by optimizing the output results of the original parameters based on the original service parameters and the original resource availability information, the method further includes:

[0152] Receive the raw parameter output results sent by the third-party application optimization module.

[0153] Specifically, the raw parameter output results are obtained by the measurement co-optimization module from the third-party application optimization module.

[0154] The strategy-coordinated optimization module interacts with the third-party application optimization module through the internal interface of the wireless network intelligent control platform, and receives the raw parameter output results from the third-party application optimization module, including the wireless network parameters that need to be optimized and traffic prediction information.

[0155] The third-party application optimization module receives near real-time data from the data warehouse module and model functions output by the AI ​​model training module. Based on these models, it determines strategy information, such as resource allocation and allocation priority. The third-party application optimization module is primarily used to deploy various third-party applications optimized or managed according to AI models, such as load balancing, QoE optimization, and RAN slicing.

[0156] The strategy optimization method provided in this invention provides a wireless network intelligent control platform to perform comprehensive intelligent control and management of the access network, making more effective use of wireless network resources to reduce the overall network cost investment of base station operators. At the same time, it optimizes the original output results and sends the optimized strategy information to the base station for execution, maximizing the use of air interface resources while optimizing the base station's strategy rules, thereby improving the user experience.

[0157] Optionally, after determining the base station-level optimization strategy, the method further includes:

[0158] The base station-level optimization strategy is sent to the multi-access edge computing system.

[0159] Specifically, the base station-level optimization strategies determined by the strategy coordination and optimization module, in addition to being sent to the base station for execution, also need to be fed back to the MEC system so that the MEC system can adjust the original service parameters.

[0160] The strategy collaboration optimization module interacts with the MEC orchestrator of the MEC system through the interface Xc. The MEC orchestrator is a core function in the entire MEC system-level management, responsible for maintaining the overall view of the MEC system.

[0161] The strategy optimization method provided in this embodiment of the invention feeds back the base station-level optimization strategy formulated by the strategy collaborative optimization module to the MEC system through information interaction between the wireless network intelligent control platform and the MEC system, so that the MEC system can adjust the service parameters and realize the coordinated interaction between services and air interface resources.

[0162] The optimization method for the above strategy will be explained below with a specific real-time example. Figure 3 This is a second flowchart illustrating the strategy optimization method provided in this embodiment of the invention, as shown below. Figure 3 As shown, the strategy optimization method provided in this embodiment of the invention includes:

[0163] The third-party application optimization module sends the raw parameter output results to the policy collaborative optimization module. The third-party application optimization module for wireless network optimization or management based on AI models sends the output results of the optimization algorithm to the policy collaborative optimization module. The output results include the wireless network parameters to be optimized and traffic prediction information, etc.

[0164] After receiving the raw parameter output, the strategy-coordinated optimization module queries the intelligent control middleware for the availability of current wireless network resources. The strategy-coordinated optimization module interacts with the intelligent control middleware through an interface within the wireless network intelligent control platform to obtain the availability information of current wireless network resources collected by the intelligent control middleware.

[0165] Simultaneously, the strategy co-optimization module queries the MEC orchestrator for user service parameters. The strategy co-optimization module queries the MEC orchestrator of the MEC system via the Xc interface for user service parameters, including the user's service type, predicted service resources, and user SLA information.

[0166] The strategy coordination optimization module, based on the acquired user service parameters and the availability of current wireless network resources, resolves conflicts or optimizes strategies based on the output results of the third-party application optimization module to determine the final optimization strategy. In this embodiment of the invention, the wireless network mainly refers to the base station. Finally, a base station-level optimization strategy is determined and distributed to the base station for execution.

[0167] Figure 4 This is the third flowchart illustrating the strategy optimization method provided in this embodiment of the invention, as shown below. Figure 4 As shown, this embodiment of the invention provides a strategy optimization method, the execution subject of which is an MEC system, including:

[0168] Step 401: Receive the base station-level optimization strategy sent by the strategy coordination optimization module.

[0169] Specifically, when the strategy coordination and optimization module formulates base station-level optimization strategies, it adjusts and updates the original service parameters and feeds back the updated user service parameters and optimization strategies to the MEC system.

[0170] The strategy collaboration optimization module resolves strategy conflicts and optimizes strategies based on the original parameter output results of the third-party application optimization module, the original resource availability information of the intelligent control middleware, and the original business parameters of the MEC system.

[0171] After the strategy collaboration optimization module formulates the base station-level optimization strategy, it updates the original parameter output results and feeds them back to the third-party application optimization module, updates the original resource availability information and feeds it back to the intelligent control middleware, and updates the original service parameters and feeds them back to the MEC system.

[0172] The MEC orchestrator of the MEC system interacts with the policy coordination and optimization module of the wireless network intelligent control platform through the Xc interface to obtain the base station-level optimization policies and updated resource availability information formulated by the policy coordination and optimization module.

[0173] Step 402: Determine the optimized user service parameters based on the user's service level agreement and the base station-level optimization strategy.

[0174] Specifically, after the MEC system receives the base station-level optimization policy sent by the policy coordination and optimization module, it adjusts the parameters of the user's service content based on the user's SLA and the updated wireless network resource availability information. User service parameters include the user service type, predicted service resources, and the user's SLA, etc. The main parameter to be adjusted here is the predicted service resource information.

[0175] For example, for video services, adjust parameters such as video encoding / decoding and resolution.

[0176] Step 403: Send the optimized user service parameters to the core network.

[0177] Specifically, after optimizing and adjusting the user service content, the MEC system feeds back the optimized user service parameters to the 5G core network.

[0178] In the MEC system, the MEC orchestrator receives base station-level optimization policies from the policy coordination and optimization module of the wireless network intelligent control platform. Based on the updated resource availability information and the user's SLA level, it adjusts the user service parameters and sends the adjusted user service parameters to the 5G core network through the Naf interface.

[0179] The 5G core network formulates new policy information and sends it to the UPF via the N4 interface. These policy rules include policy rules for service flows, user information, etc. The UPF performs authorization checks on the policy rules from the 5G core network according to the local configuration of the MEC system, mapping them into policy rule information that the MEC system can recognize and process.

[0180] The policy optimization method provided in this invention sinks services to the network edge through the MEC system to reduce end-to-end latency and load on the transmission network, thereby achieving efficient service delivery. Through information interaction between the MEC orchestrator and the policy collaborative optimization module, a deep integration between the network intelligent control platform and the MEC system is achieved, enabling coordinated interaction between services and air interface resources. This maximizes the utilization of air interface resources while optimizing the policy rules of the base station, and provides feedback on user service content in the 5G core network, thereby improving the user experience.

[0181] Optionally, before the base station-level optimization strategy sent by the receiving strategy collaborative optimization module, the following further includes:

[0182] The original business parameters are sent to the strategy collaborative optimization module.

[0183] Specifically, the base station-level optimization strategy of the strategy coordination optimization module needs to be formulated based on the original service parameters, which are sent to the strategy coordination optimization module by the MEC system.

[0184] The strategy coordination optimization module resolves strategy conflicts, optimizes strategies, and formulates base station-level optimization strategies based on the original parameter output results of the third-party application optimization module, the original service parameters queried from the MEC system, and the original availability resource information obtained from the intelligent control middleware.

[0185] The MEC orchestrator of the MEC system and the policy coordination optimization module of the wireless network intelligent control platform exchange information through the Xc interface, sending raw service parameters to the policy coordination optimization module. The raw service parameters include parameters such as the user's service type, predicted service resource information, and user SLA.

[0186] The strategy optimization method provided in this embodiment of the invention, through information interaction between the MEC system and the wireless network intelligent control platform, sends the original service parameters to the strategy collaborative optimization module to resolve strategy conflicts, optimize strategies, formulate base station-level optimization strategies, realize the coordinated interaction between services and air interface resources, maximize the utilization of air interface resources while optimizing the base station's strategy rules, and improve the user experience.

[0187] The optimization method for the above strategy will be explained below with a specific real-time example. Figure 5 This is the fourth flowchart illustrating the strategy optimization method provided in this embodiment of the invention, as shown below. Figure 5 As shown, an embodiment of the present invention provides a strategy optimization method, including:

[0188] The strategy coordination optimization module resolves strategy conflicts, optimizes strategies, and formulates base station-level optimization strategies based on the original parameter output results of the third-party application optimization module, the original service parameters queried from the MEC system, and the original resource availability information obtained from the intelligent control middleware.

[0189] After formulating the base station-level optimization strategy, the strategy collaborative optimization module feeds back the adjusted wireless network parameter optimization results to the third-party application optimization module. The third-party application optimization module can then perform operations such as correction and optimization of the optimization algorithm based on these adjusted wireless network parameter optimization results.

[0190] The strategy-coordinated optimization module updates the original resource availability information and traffic prediction information according to the established base station-level optimization strategy, and feeds back the updated resource availability information and traffic prediction information to the MEC orchestrator of the MEC system.

[0191] After receiving updated wireless network resource availability information and traffic prediction information, the MEC orchestrator adjusts the user service content based on the user's SLA to obtain optimized user service parameters.

[0192] For example, for video services, adjustments can be made to the video encoding / decoding, resolution, and other parameters.

[0193] The MEC orchestrator can exchange information with the operation support system, and the MEC system will feed back the optimized user service parameters to the 5G core network.

[0194] The 5G core network formulates new policy rules based on the optimized user service parameters and distributes the new policy rules to the local UPF.

[0195] Figure 6 This is the fifth flowchart illustrating the strategy optimization method provided in this embodiment of the invention, as shown below. Figure 6 As shown, this embodiment of the invention provides a strategy optimization method, the execution subject of which is a 5G core network, including:

[0196] Step 601: Receive the optimized user service parameters sent by the multi-access edge computing system.

[0197] Specifically, the MEC system adjusts user service content based on base station-level optimization strategies and user SLAs, and sends the optimized user service parameters to the 5G core network.

[0198] As a functional entity of the MEC system, the MEC orchestrator acts as the AF (Agent Flight Controller) to interact with different network functions of the 5G core network and influence user plane strategies.

[0199] For example, a trusted AF can influence user plane policies directly through the PCF and SMF, while an untrusted AF can influence user plane policies through the NEF, PCF, and SMF. The MEC system, as a special form of AF, can interact with the NEF and PCF, and invoke 5G core network development capabilities, such as message subscription and QoS.

[0200] Step 602: Determine the traffic splitting optimization strategy based on the optimized user service parameters.

[0201] Specifically, the 5G core network formulates traffic offloading optimization strategies based on optimized user service parameters.

[0202] Step 603: Send the traffic splitting optimization strategy to the multi-access edge computing router.

[0203] Specifically, the 5G core network sends the established traffic offloading and optimization strategies to the MEC router.

[0204] UPF can receive messages from the 5G core network through the N4 interface. These messages include traffic offloading optimization policies, user information, and other information. UPF performs authorization checks on the policy rules from the 5G core network according to the local configuration of the MEC system and maps them into policy rule information that the MEC system can recognize and process.

[0205] The MEC host level is configured to connect to MEC routers that support policy-based traffic splitting and can exchange information with these MEC routers. UPF distributes the traffic splitting optimization policies issued by the 5G core network to the MEC routers that support policy-based traffic splitting.

[0206] Policy-based traffic allocation rules are used to indicate the allocation path and proportion of traffic, such as whether it is allocated to the local core network or the local data network. Some traffic is allocated to the 5G core network and other traffic is allocated to the local data network.

[0207] The strategy optimization method provided in this embodiment of the invention achieves coordinated interaction between services and air interface resources through information interaction between the wireless network intelligent control platform and the MEC system. It enables the 5G core network to adjust the traffic policy rules on the local UPF, maximizing the utilization of air interface resources while maximizing the improvement of user experience.

[0208] Figure 7 This is one of the structural schematic diagrams of the strategy optimization device provided in the embodiments of the present invention, such as... Figure 7 As shown, this embodiment of the invention provides a strategy optimization device, the execution body of which is a strategy collaborative optimization module, including:

[0209] The first determining module 701 is used to optimize the output results of the original parameters based on the original service parameters and the original resource availability information to determine the base station-level optimization strategy.

[0210] The first sending module 702 is used to send the base station-level optimization strategy to the base station.

[0211] Optionally, the device further includes a first receiving module;

[0212] The first receiving module is used to receive the original service parameters sent by the multi-access edge computing system.

[0213] Optionally, the device further includes a second receiving module;

[0214] The second receiving module is used to receive the original resource availability information sent by the intelligent control middleware.

[0215] Optionally, the device further includes a third receiving module;

[0216] The third receiving module is used to receive the raw parameter output results sent by the third-party application optimization module.

[0217] Optionally, the device further includes a second transmitting module;

[0218] The second sending module is used to send the base station-level optimization strategy to the multi-access edge computing system.

[0219] Figure 8 This is a second schematic diagram of the strategy optimization device provided in the embodiments of the present invention, as shown below. Figure 8 As shown, this embodiment of the invention provides a strategy optimization device, the execution entity of which is an MEC system, including:

[0220] The fourth receiving module 801 is used to receive the base station-level optimization strategy sent by the strategy coordination optimization module;

[0221] The second determining module 802 is used to determine the optimized user service parameters based on the user's service level agreement and the base station-level optimization strategy;

[0222] The third sending module 803 is used to send the optimized user service parameters to the core network.

[0223] Optionally, the device further includes a fourth transmitting module;

[0224] The fourth sending module is used to send the original business parameters to the strategy collaborative optimization module.

[0225] Figure 9 This is the third structural schematic diagram of the strategy optimization device provided in the embodiments of the present invention, as shown below. Figure 9 As shown, this embodiment of the invention provides a strategy optimization device, the execution entity of which is a 5G core network, including:

[0226] The fifth receiving module 901 is used to receive optimized user service parameters sent by the multi-access edge computing system;

[0227] The third determining module 902 is used to determine the traffic splitting optimization strategy based on the optimized user service parameters;

[0228] The fifth sending module 903 is used to send the traffic splitting optimization strategy to the multi-access edge computing router.

[0229] Specifically, the strategy optimization device provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0230] Figure 10 This is a schematic diagram of the physical structure of the electronic device provided in the embodiments of the present invention, such as... Figure 10 As shown, the electronic device may include: a processor 1001, a communications interface 1002, a memory 1003, and a communication bus 1004, wherein the processor 1001, the communications interface 1002, and the memory 1003 communicate with each other via the communication bus 1004. The processor 1001 can call logical instructions in the memory 1003 to execute a strategy optimization method, which includes:

[0231] Based on the original service parameters and original resource availability information, the original parameter output results are optimized to determine the base station-level optimization strategy;

[0232] The base station-level optimization strategy is sent to the base station.

[0233] Or, including:

[0234] Receive the base station-level optimization strategy sent by the strategy coordination optimization module;

[0235] The optimized user service parameters are determined based on the user's service level agreement and the base station-level optimization strategy.

[0236] The optimized user service parameters are sent to the core network.

[0237] Or, including:

[0238] Receive optimized user service parameters sent by the multi-access edge computing system;

[0239] Determine the traffic splitting optimization strategy based on the optimized user service parameters;

[0240] The traffic splitting optimization strategy is sent to the multi-access edge computing router.

[0241] Furthermore, the logical instructions in the aforementioned memory 1003 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part 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 described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0242] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the strategy optimization method provided by the above methods, the method comprising:

[0243] Based on the original service parameters and original resource availability information, the original parameter output results are optimized to determine the base station-level optimization strategy;

[0244] The base station-level optimization strategy is sent to the base station.

[0245] Or, including:

[0246] Receive the base station-level optimization strategy sent by the strategy coordination optimization module;

[0247] The optimized user service parameters are determined based on the user's service level agreement and the base station-level optimization strategy.

[0248] The optimized user service parameters are sent to the core network.

[0249] Or, including:

[0250] Receive optimized user service parameters sent by the multi-access edge computing system;

[0251] Determine the traffic splitting optimization strategy based on the optimized user service parameters;

[0252] The traffic splitting optimization strategy is sent to the multi-access edge computing router.

[0253] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the aforementioned strategy optimization methods, the method comprising:

[0254] Based on the original service parameters and original resource availability information, the original parameter output results are optimized to determine the base station-level optimization strategy;

[0255] The base station-level optimization strategy is sent to the base station.

[0256] Or, including:

[0257] Receive the base station-level optimization strategy sent by the strategy coordination optimization module;

[0258] The optimized user service parameters are determined based on the user's service level agreement and the base station-level optimization strategy.

[0259] The optimized user service parameters are sent to the core network.

[0260] Or, including:

[0261] Receive optimized user service parameters sent by the multi-access edge computing system;

[0262] Determine the traffic splitting optimization strategy based on the optimized user service parameters;

[0263] The traffic splitting optimization strategy is sent to the multi-access edge computing router.

[0264] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0265] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0266] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of policy optimization, characterized by, The method, applied to a strategy collaborative optimization module, includes: Based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware, the original parameter output results of the third-party application optimization module are optimized to determine the base station-level optimization strategy. Send the base station-level optimization strategy to the base station; The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

2. The method of claim 1, wherein, Before determining the base station-level optimization strategy, the following steps are also included: Receive the original service parameters sent by the multi-access edge computing system.

3. The method of claim 1, wherein, Before determining the base station-level optimization strategy, the following steps are also included: Receive the original resource availability information sent by the intelligent control middleware.

4. The method of claim 1, wherein, Before determining the base station-level optimization strategy, the following steps are also included: Receive the original parameter output results sent by the third-party application optimization module.

5. The method of claim 1, wherein, After determining the base station-level optimization strategy, the following is also included: The base station-level optimization strategy is sent to the multi-access edge computing system.

6. A method of policy optimization, characterized by, The method, applied to multi-access edge computing systems, includes: Receive the base station-level optimization strategy sent by the strategy coordination optimization module; The optimized user service parameters are determined based on the user's service level agreement and the base station-level optimization strategy. The optimized user service parameters are sent to the core network; The base station-level optimization strategy is determined by optimizing the original parameter output results of the third-party application optimization module based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware. The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

7. The method of policy optimization of claim 6, wherein, Before the base station-level optimization strategy sent by the receiving strategy collaborative optimization module, the following is also included: The original business parameters are sent to the strategy collaborative optimization module.

8. A method of policy optimization, characterized by, Applied to 5G core networks, the method includes: Receive optimized user service parameters sent by the multi-access edge computing system; Determine the traffic splitting optimization strategy based on the optimized user service parameters; The traffic splitting optimization strategy is sent to the multi-access edge computing router; The optimized user service parameters are determined based on the user's service level agreement and base station-level optimization strategies. The base station-level optimization strategy is determined by optimizing the original parameter output results of the third-party application optimization module based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware. The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

9. A policy optimization apparatus characterized by comprising: The device, applied to a strategy collaborative optimization module, includes: The first determining module is used to optimize the original parameter output results of the third-party application optimization module and determine the base station-level optimization strategy based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware. The first sending module is used to send the base station-level optimization strategy to the base station; The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

10. The policy optimization apparatus according to claim 9, wherein The device further includes a first receiving module; The first receiving module is used to receive the original service parameters sent by the multi-access edge computing system.

11. The policy optimization apparatus according to claim 9, wherein The device also includes a second receiving module; The second receiving module is used to receive the original resource availability information sent by the intelligent control middleware.

12. The strategy optimization apparatus according to claim 9, characterized in that, The device also includes a third receiving module; The third receiving module is used to receive the original parameter output results sent by the third-party application optimization module.

13. The strategy optimization apparatus according to claim 9, characterized in that, The device also includes a second transmitting module; The second sending module is used to send the base station-level optimization strategy to the multi-access edge computing system.

14. A strategy optimization device, characterized in that, The device, applied to a multi-access edge computing system, includes: The fourth receiving module is used to receive base station-level optimization strategies sent by the strategy coordination optimization module; The second determining module is used to determine the optimized user service parameters based on the user's service level agreement and the base station-level optimization strategy. The third sending module is used to send the optimized user service parameters to the core network; The base station-level optimization strategy is determined by optimizing the original parameter output results of the third-party application optimization module based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware. The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

15. The strategy optimization apparatus according to claim 14, characterized in that, The device also includes a fourth transmitting module; The fourth sending module is used to send the original service parameters to the strategy collaborative optimization module.

16. A strategy optimization device, characterized in that, The device, applied to 5G core networks, includes: The fifth receiving module is used to receive optimized user service parameters sent by the multi-access edge computing system; The third determining module is used to determine the traffic splitting optimization strategy based on the optimized user service parameters. The fifth sending module is used to send the traffic splitting optimization strategy to the multi-access edge computing router; The optimized user service parameters are determined based on the user's service level agreement and base station-level optimization strategies. The base station-level optimization strategy is determined by optimizing the original parameter output results of the third-party application optimization module based on the original service parameters of the multi-access edge computing system and the original resource availability information of the intelligent control middleware. The optimization strategy includes resolving resource allocation conflicts for third-party applications and adjusting resource allocation strategies.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the strategy optimization method as described in any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the strategy optimization method as described in any one of claims 1 to 8.

Images