Methods, apparatus, devices and storage media for optimizing the operation of edge applications

Abstract

This application provides a method, apparatus, device, and storage medium for optimizing the operation of edge applications, applied to an edge application operation optimization system, including MEC, RIC, and wireless base stations. The method includes: obtaining the QoE of an edge application, where the edge application is an application running on the wireless base station in a first network state, the first network state being determined based on the service type and network indicator requirements of the edge application; obtaining a target edge application and its target network indicator requirements based on the QoE; and adjusting the network in the first network state according to the target edge application's target network indicator requirements to obtain a second network state, the second network state being the current network state used by the target edge application. This method enables real-time configuration of service and network adjustment strategies for edge applications, increasing service awareness and improving the user's service experience.

Description

Technical Field

[0001] This application relates to the field of application optimization technology, and in particular to a method, apparatus, device and storage medium for optimizing the operation of edge applications. Background Technology

[0002] In the 5G era, vertical industries have significant differentiated needs, with diverse business types in industrial parks, high latency requirements, and stringent requirements for construction period and cost. This necessitates the network side to provide on-demand services and higher network resource utilization efficiency to enhance the user experience.

[0003] In existing technologies, in order to meet the user's service experience, network data analysis function network elements on the core network side are usually used to analyze the operation data of the 5G network, thereby completing the optimization solution for the user's service experience.

[0004] However, network data analysis function elements can only obtain data from the core network side and cannot accurately obtain data from the radio side, resulting in large data delay errors. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for optimizing the operation of edge applications, in order to solve the problem in the prior art that when optimizing the operation of edge applications, network and application data can only be obtained from the core network side, and real-time data from the wireless side cannot be obtained.

[0006] Firstly, this application provides a method for optimizing the operation of edge applications, including:

[0007] Obtain the QoE of edge applications. Edge applications are applications that run in the first network state of the wireless base station. The first network state is determined based on the service type of the edge application and its requirements for network indicators.

[0008] Based on QoE, the target edge application and its target network requirements are obtained. The target edge application is obtained by updating the edge application based on QoE on the server side.

[0009] Based on the target edge application's target requirements for network metrics, the first network state is adjusted to obtain the second network state, which is the current network state used by the target edge application.

[0010] In this embodiment of the application, obtaining the QoE of the edge application includes:

[0011] Determine the application information of edge applications, including the service type of edge applications and their network metric requirements;

[0012] Based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC, the network state of the wireless base station is adjusted to obtain the first network state.

[0013] QoE for edge applications that gather user feedback when running in the first network state.

[0014] In this embodiment of the application, the network state of the wireless base station is adjusted based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC to obtain a first network state, including:

[0015] Based on the application information of edge applications, determine the network metric requirements of edge applications;

[0016] Based on the network metric requirements of edge applications and the DPI control strategy unit in MEC, determine the first control strategy to optimize the wireless base station.

[0017] Based on the RIC and the first control strategy, the network state of the wireless base station is adjusted to obtain the first network state.

[0018] In this embodiment of the application, the network state of the wireless base station is adjusted according to the RIC and the first control strategy to obtain the first network state, including:

[0019] According to the first control strategy, the first network information to be optimized for the wireless base station and the first optimization method for the first network information to be optimized are determined.

[0020] Based on the first network information to be optimized, RIC, and the first optimization method, the network state of the wireless base station is adjusted to obtain the first network state.

[0021] In this embodiment of the application, based on the target requirements of the target edge application for network metrics, a network adjustment is performed on the first network state to obtain a second network state, including:

[0022] Identify the wireless base station in the first network state;

[0023] Based on the target edge application's network metric requirements and the DPI control strategy unit, a second control strategy for optimizing the wireless base station in the first network state is determined.

[0024] Based on the RIC and the second control strategy, the wireless base station in the first network state is adjusted to obtain the second network state.

[0025] In this embodiment of the application, based on the RIC and the second control strategy, network adjustments are made to the wireless base station in the first network state to obtain the second network state, including:

[0026] According to the second control strategy, the second network information to be optimized for the wireless base station in the first network state and the second optimization method for the second network information to be optimized are determined.

[0027] Based on the second network information to be optimized, RIC, and the second optimization method, the wireless base station in the first network state is adjusted to obtain the second network state.

[0028] In this embodiment of the application, after adjusting the first network state according to the target requirements of the target edge application for network metrics to obtain the second network state, the method further includes:

[0029] The target edge application that obtains user feedback updates its QoE when running in the second network state;

[0030] If the updated QoE meets the user's business service requirements, then the second network state is determined as the target network state of the target edge application;

[0031] If the updated QoE does not meet the user's business service requirements, the second network state will be adjusted until the target network state that meets the user's business service requirements is obtained.

[0032] Secondly, this application provides an edge application operation optimization device, comprising:

[0033] The QoE acquisition module is used to acquire the QoE of edge applications. Edge applications are applications that run when the wireless base station is in the first network state. The first network state is determined based on the service type of the edge application and its requirements for network indicators.

[0034] The application obtains the module, which is used to obtain the target edge application and the target network requirements of the target edge application based on QoE. The target edge application is obtained by the server updating the edge application based on QoE.

[0035] The network status acquisition module is used to adjust the first network status according to the target edge application's target requirements for network metrics, and obtain the second network status, which is the current network status used by the target edge application.

[0036] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory to implement the method of the embodiments of this application.

[0039] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods of the embodiments of this application.

[0040] The edge application operation optimization method, apparatus, device, and storage medium provided in this application achieve the effect of multi-faceted protection for the differentiated needs of edge application services. By obtaining the QoE of the edge application, which is an application running in a first network state of the wireless base station, the first network state is determined according to the service type and network indicator requirements of the edge application. Based on the QoE, the target edge application and its target network indicator requirements are obtained. The target edge application is obtained by the server updating the edge application based on the QoE. Based on the target network indicator requirements of the target edge application, the first network state is adjusted to obtain a second network state, which is the current network state used by the target edge application. This method achieves the effect of multi-faceted protection for the differentiated needs of edge application services. By coordinating the wireless side and the remote server to complete the version update of the edge application and the real-time optimization of the wireless network, the service quality of the edge application is improved, and the user's service experience is enhanced. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] Figure 1 A flowchart illustrating the operation optimization method for edge applications provided in this application embodiment;

[0043] Figure 2 A flowchart illustrating another edge application operation optimization method provided in this application embodiment;

[0044] Figure 3 A schematic diagram of the structure of the edge application operation optimization device provided in the embodiments of this application;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0046] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] In existing technologies, in order to improve users' perception of services and service experience of edge applications, application data and network information of edge applications are usually obtained from network data analysis network elements on the core network side. However, the relevant data obtained through network data analysis network elements has a large time delay error, which makes the data more limited. At the same time, the core network side cannot obtain network data from the wireless side, which affects the network operation performance of edge applications and further reduces the user's service experience.

[0049] To address the aforementioned issues, this application provides an edge application operation optimization method, apparatus, device, and storage medium. Based on the edge application's network indicator requirements, it determines the network information in the current wireless base station that needs further optimization. The MEC DPI control strategy unit in the edge application operation optimization system determines a first control strategy for optimizing the wireless base station network information based on this network information and sends it to the RIC (Regulator-Instrument Control), enabling the RIC to optimize the network information in the wireless base station according to the first control strategy, thereby obtaining optimized wireless base station network information. The edge application runs under this optimized wireless base station network information, obtaining the edge application's QoE (Quality of Experience). This QoE is then sent to a remote server, allowing the remote server to update the edge application, obtaining the target edge application and its target network indicator requirements. Based on the target edge application's target network indicator requirements, network adjustments are made to the optimized wireless base station network information, resulting in updated wireless base station network information, which represents the current network status of the edge application. This solves the problem that existing technologies can only optimize edge applications through the core network. By using the wireless side and MEC platform, real-time optimization and adjustment of the network and services of edge applications can be achieved, improving the utilization rate of wireless network information. At the same time, by enabling edge applications to collaborate with remote servers to complete application updates, the efficiency of edge application updates is improved, and the collaborative development of the network and services of edge applications is promoted.

[0050] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0051] The execution subject of the edge application operation optimization method provided in this application embodiment can be a server. The server can be a computer or other device. This embodiment does not impose any particular restrictions on the implementation method of the execution subject, as long as the execution subject can obtain the QoE of the edge application, the edge application is an application running in a first network state (determined based on the service type and network indicator requirements of the edge application); based on the QoE, the target edge application and its target network indicator requirements are obtained, the target edge application being obtained by updating the edge application based on the QoE; based on the target edge application's target network indicator requirements, network adjustments are made to the first network state to obtain a second network state, which is the current network state used by the target edge application.

[0052] Among them, MEC (Multi-access Edge Computing) refers to a resource computing platform or a wireless network capability platform. By deeply integrating MEC with wireless base stations, the user's service experience can be improved and bandwidth resources can be saved. At the same time, the wireless side perception of MEC is more distributed and localized, and the service is closer to the user. By combining and deploying the MEC platform with wireless base stations, service optimization of edge applications can be better achieved.

[0053] DPI (Deep Packet Inspection) is an application-layer traffic inspection and control technology in the MEC platform. It can identify and block network attacks, understand user behavior, and monitor network traffic. DPI can quickly identify information that needs optimization in wireless networks and generate corresponding optimization control policies, which can greatly improve the efficiency of network optimization for edge applications.

[0054] RIC (Radio Intelligent Controller) refers to a wireless intelligent controller that can introduce wireless AI capabilities to wireless base stations, improving network performance and resource utilization efficiency. By receiving control optimization strategies sent by MEC DPI, RIC can determine the network information that needs to be optimized in the wireless base station and the specific optimization methods. Based on these methods, it can further optimize the network information that needs to be optimized, thereby completing network optimization on the wireless base station side.

[0055] Figure 1 This is a flowchart illustrating the edge application operation optimization method provided in this application embodiment, applied to an edge application operation optimization system, which consists of an MEC, a RIC, and a wireless base station. Figure 1 As shown, the method may include:

[0056] S101. Obtain the QoE of the edge application. The edge application is the application that the wireless base station is running in the first network state. The first network state is determined according to the service type of the edge application and its requirements for network indicators.

[0057] QoE (Quality of Experience) is a metric that measures user satisfaction with the network and is related to the service quality of edge applications and the user's personal experience.

[0058] The types of services can include video services, automatic control services, etc. Based on the types of services of edge applications, the characteristics of edge services can be determined, such as the size of data packets and the period of data packets in the service flow.

[0059] Network metric requirements can refer to the network latency and other metrics required by edge applications. For example, if the end-to-end latency requirement of an edge application is less than 1ms, then the edge application operation optimization system needs to optimize and control the network on the wireless base station side based on this end-to-end latency requirement.

[0060] In this embodiment of the application, obtaining the QoE of the edge application includes:

[0061] Determine the application information of edge applications, including the service type of edge applications and their network metric requirements;

[0062] Based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC, the network state of the wireless base station is adjusted to obtain the first network state.

[0063] QoE for edge applications that gather user feedback when running in the first network state.

[0064] By combining the service type of edge services, their network indicator requirements, and the service level requirements of the edge services themselves, network information to be optimized for edge application operation can be obtained. Based on this network information, MEC DPI can obtain the network optimization adjustment requirements on the wireless base station side and send these requirements to the RIC, so that the RIC can send adjustment information to the wireless base station. This allows the wireless base station to call on its network adjustment capabilities to perform fine-grained network adjustment processing for edge services, resulting in a wireless base station network state that meets the network service requirements of edge applications. After adjusting the wireless base station network state, the edge application is placed in this network state and run, and the user's Quality of Service (QoE) of the edge application under this network state can be obtained.

[0065] The network adjustment capabilities of wireless base stations can include flow adjustment based on dynamic 5QI (5G QoS), PRB (physical resource block) resource reservation, and Radio Resource Management (RRM) pre-adjustment indication. 5QI is a parameter that can be used to measure the wireless base station network using five key indicators: quality, time, cost, efficiency, and satisfaction. PRB resource reservation can divide a group of slice services that are of priority for edge applications into a slice user group, determine the network operating rate, and allow users within the slice user group to share bandwidth. When other slice users experience congestion, users within this slice are not affected. Radio Resource Management (RRM) pre-adjustment indication can provide service quality assurance for user terminals within the wireless base station network under limited bandwidth conditions. When the network traffic distribution is uneven and the channel characteristics fluctuate due to channel attenuation and interference, it can flexibly allocate and dynamically adjust the available resources of the wireless transmission part and the network, thereby maximizing the utilization of the wireless spectrum.

[0066] In this embodiment of the application, the network state of the wireless base station is adjusted based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC to obtain a first network state, including:

[0067] Based on the application information of edge applications, determine the network metric requirements of edge applications;

[0068] Based on the network metric requirements of edge applications and the DPI control strategy unit in MEC, determine the first control strategy to optimize the wireless base station.

[0069] Based on the RIC and the first control strategy, the network state of the wireless base station is adjusted to obtain the first network state.

[0070] In this embodiment of the application, the network state of the wireless base station is adjusted according to the RIC and the first control strategy to obtain the first network state, including:

[0071] According to the first control strategy, the first network information to be optimized for the wireless base station and the first optimization method for the first network information to be optimized are determined.

[0072] Based on the first network information to be optimized, RIC, and the first optimization method, the network state of the wireless base station is adjusted to obtain the first network state.

[0073] In the MEC, after the DPI control strategy unit determines the adjustment strategy requirements for the wireless base station, it encapsulates these requirements and sends them to the RIC unit on the wireless base station side via the MEC DP (Data Plane for Information Transmission) within the MEC. The RIC unit then determines the network information requiring optimization and the optimization control method based on these requirements, and sends a network optimization adjustment command to the wireless base station to optimize the wireless base station network. For example, the RIC sends the optimization control method to the E2 node on the wireless base station side, enabling the E2 node to configure this method on its corresponding application. When multiple users initiate service access to the application, the application sends an optimization command to the wireless base station based on real-time collected measurement information and user data reported from the wireless base station. This allows high-priority users to obtain wireless network resources first. The RIC then sends the corresponding network information and the experience information of high-priority users to the MEC via MECDP. The MEC DPI in the MEC integrates the current wireless network information and user experience information to determine the current QoE of the edge application.

[0074] S102. Based on QoE, obtain the target edge application and the target requirements of the target edge application for network metrics. The target edge application is obtained by the server updating the edge application based on QoE.

[0075] The server-side deployment uses an AI engine to model the characteristics of specific services to obtain a service feature model and regularly update the application version, thereby optimizing the user's QoE. For example, the server-side can refer to the terminal used by the programmer. For video streaming services, the programmer can use the terminal to identify the data packets corresponding to I-frames and P-frames in the service stream, and further identify the corresponding packet period, packet size, and packet arrival time. This guides the wireless base station to subdivide the I-frames and P-frames in the video streaming service and execute different adjustment strategies, enabling more refined identification of service features and thus achieving more refined service experience assurance.

[0076] Edge applications access remote servers with deployed AI engines via the public network. After the server extracts the application characteristics and current QoE of the edge application, it trains an AI model for the application version of the edge application, further optimizes the application model, and sends the optimized version information of the target edge application to the MEC. This allows the MEC DPI to propose new network optimization control strategies based on the new network indicator requirements of the target edge application, thereby achieving further optimization and updating of wireless base station network information.

[0077] S103. Based on the target edge application's target requirements for network metrics, adjust the first network state to obtain the second network state, which is the current network state used by the target edge application.

[0078] Specifically, the MEC DPI, based on the target edge application updated by the application version sent by the remote server, can determine the new network indicator requirements of the target edge application, and based on the new network indicator requirements, obtain the network information adjustment policy requirements on the wireless base station side corresponding to the target edge application; send the adjustment policy requirements to the MEC DP, the MEC DP encapsulates the policy requirements and sends them to the RIC, and the RIC optimizes and controls the network information on the wireless base station side again based on the encapsulated policy requirements, thereby obtaining the updated network status after optimization and control.

[0079] In this embodiment of the application, based on the target requirements of the target edge application for network metrics, the first network state is adjusted to obtain the second network state, including:

[0080] Identify the wireless base station in the first network state;

[0081] Based on the target edge application's network metric requirements and the DPI control strategy unit, a second control strategy for optimizing the wireless base station in the first network state is determined.

[0082] Based on the RIC and the second control strategy, the wireless base station in the first network state is adjusted to obtain the second network state.

[0083] In this embodiment of the application, the wireless base station in the first network state is adjusted according to the RIC and the second control strategy to obtain the second network state, including:

[0084] According to the second control strategy, the second network information to be optimized for the wireless base station in the first network state and the second optimization method for the second network information to be optimized are determined.

[0085] Based on the second network information to be optimized, RIC, and the second optimization method, the wireless base station in the first network state is adjusted to obtain the second network state.

[0086] In this embodiment of the application, after adjusting the first network state according to the target requirements of the target edge application for network metrics to obtain the second network state, the method further includes:

[0087] The target edge application that obtains user feedback updates its QoE when running in the second network state;

[0088] If the updated QoE meets the user's business service requirements, then the second network state is determined as the target network state for the target edge application.

[0089] If the updated QoE does not meet the user's business service requirements, the second network state will be adjusted until the target network state that meets the user's business service requirements is obtained.

[0090] Specifically, the second network state obtained after the RIC performs secondary optimization control on the wireless base station side is determined. The target edge application is placed in this second network state and runs in it. The user's service operation quality experience of the target edge application in this state can be obtained. If the user's service operation quality experience meets the user's service requirements, the second network state can be determined as the ideal network state for the target edge application, and the target edge application can continue to run in this second network state. If the user's service operation quality experience does not meet the user's service requirements, further optimization control is needed for the second network state where the target edge application is located. Through the mutual coordination between MEC DPI and RIC, the network information of the second network state is optimized until the optimized wireless base station network information can meet the user's service requirements.

[0091] The edge application operation optimization method provided in this application can obtain the QoE of the edge application, which is an application running in a first network state of the wireless base station. The first network state is determined based on the service type and network indicator requirements of the edge application. Based on the QoE, the target edge application and its target network indicator requirements are obtained. The target edge application is obtained by updating the edge application based on the QoE on the server side. Based on the target network indicator requirements of the target edge application, the first network state is adjusted to obtain a second network state, which is the current network state used by the target edge application. This solves the problem in the prior art that network optimization can only be performed based on the current operating data of the edge application obtained from the core network side, resulting in large data latency and poor service optimization capabilities. The method completes application optimization through a remote server and proposes network adjustment strategies, optimizing the latency of the wireless network and improving the user experience of edge applications.

[0092] Figure 2 This is a flowchart illustrating another edge application operation optimization method provided in an embodiment of this application. Figure 2 As shown, the method may include:

[0093] S201. Receive user access to MEC APP and send the application data and network requirements of MEC APP to MECDPI unit.

[0094] In this process, users access an optimized platform jointly deployed by MEC and wireless base stations and establish a user data plane session, enabling users to initiate access to MEC APP based on this user data plane session. MEC APP uses the MEC MP1 interface with the MEC platform to deposit application data of MEC APP to the MEC platform, including but not limited to service types or basic requirements for network indicators, such as video services, automatic control services, and end-to-end network latency.

[0095] S202, the MEC DPI unit determines the radio-side adjustment strategy based on the application data and network requirements of the MEC APP, and sends the radio-side adjustment strategy to the MEC DP.

[0096] The MEC DPI, based on the service type and network indicator requirements of the MEC APP, and combined with the required SLA guarantee, can convert service SLA requirements and learned service characteristics into radio-side adjustment policy requirements. It then invokes the base station's capabilities to send adjustment knowledge to the base station, thereby enabling refined differentiation and adjustment of service processing to meet the application's SLA requirements. Simultaneously, it assesses the end-to-end latency of the service and provides assurance. The MEC DPI forwards this information to the MEC DP via the N6 interface. Service characteristics can refer to packet size, packet period, etc., and base station capabilities can refer to flow adjustment based on dynamic 5QI, PRB resource reservation, and radio resource RRM pre-adjustment indication. Adjustment knowledge can refer to packet size, packet period, etc.

[0097] S203 and MEC DP encapsulate the wireless side adjustment strategy and send it to RIC so that RIC can optimize the wireless base station network and obtain wireless base station network information.

[0098] The MEC DP encapsulates the radio-side adjustment policy requirements and sends these requirements to the RIC via the A1 interface between the MEC DP and the RIC. The RIC then modifies the requirements accordingly and controls the base station to optimize base station information. The RIC platform, through the deployment of xApps, transmits network information (location, bandwidth management, RNIS, radio information services) to the MEC DP via the A1 interface. The RIC sends QoS optimization commands to the radio base station, which executes these commands. This enables finer-grained QoS protection from the user level to the flow level and then to the packet level, providing new network capabilities such as location awareness and link quality prediction. QoS optimization policies are configured on the xApp. When multiple users initiate service access, the QoS App, based on real-time collected measurement information, UE context, UE data, etc., reported from the base station, sends QoS optimization commands to the base station via the RIC. Higher-priority users receive radio resources first.

[0099] S204 and MEC DPI obtain the user's initial QoE based on the wireless base station network information and send the initial QoE to the MEC APP.

[0100] Among them, MEC DP sends user location, bandwidth offloading management, and RNIS from the wireless base station to MEC DPI. MEC DPI converts the current wireless network information and user experience score into QoE and sends the QoE to MEC APP through the MP1 interface.

[0101] S205 and MEC APP access the cloud via the public network so that the cloud can train the MEC APP model based on the MEC APP's application data and initial QoE to obtain an updated MEC APP.

[0102] The MEC APP accesses the cloud APP via the public network. The cloud APP extracts edge application features and user QoE, performs AI training in the cloud, optimizes the application model, and synchronizes the updated application version to the MEC APP via the public network.

[0103] S206, MEC DPI determines the updated radio-side adjustment policy based on the updated MEC APP, and sends the updated radio-side adjustment policy to MEC DP.

[0104] The MEC DPI converts the application data updated by the cloud APP into requirements for the updated radio-side adjustment policy and forwards it to the MEC DP. The application data includes the service type and network indicator requirements, and the radio-side adjustment policy requirements include 5QI, PRB resource reservation, and RRM pre-adjustment.

[0105] S207 and MEC DP encapsulate the updated radio-side adjustment strategy and send it to RIC so that RIC can optimize the radio base station network, obtain updated radio base station network information, and thus complete the QoE optimization of MEC APP.

[0106] The MEC DP encapsulates the updated radio-side adjustment policy requirements and sends them to the RIC via the A1 interface. The RIC then modifies the content according to the policy and controls the base station in reverse to optimize base station information. The RIC platform deploys xApps to transmit network information to the MEC DP via the A1 interface. For example, it sends QoS optimization-related commands to the radio base station, which executes the relevant QoS optimization commands. The xApp configures QoS optimization policies, and when multiple users initiate service access, the QoSApp sends QoS optimization commands to the base station via the RIC based on real-time collected measurement information, UE context, UE data, and other information reported from the base station. High-priority users are given priority access to radio resources.

[0107] Another QoE optimization method for edge applications provided in this application embodiment is to deploy a wireless base station control unit on the MEC platform to achieve deep packet recognition. The recognition results are then notified to the wireless base station via in-line packets. The wireless base station implements differentiated adjustment algorithm guarantees for specific service types according to the set strategy, thereby obtaining a better service experience for edge applications and realizing QoE optimization for edge applications.

[0108] Figure 3This is a schematic diagram of the structure of the edge application operation optimization device provided in the embodiments of this application. Figure 3 As shown, the edge application operation optimization device 30 includes:

[0109] QoE acquisition module 301 is used to acquire the QoE of edge applications. Edge applications are applications that run when the wireless base station is in the first network state. The first network state is determined according to the service type of the edge application and its requirements for network indicators.

[0110] The application obtains module 302, which is used to obtain the target edge application and the target network indicator requirements of the target edge application based on QoE. The target edge application is obtained by the server updating the edge application based on QoE.

[0111] The network status acquisition module 303 is used to adjust the first network status according to the target edge application's target requirements for network metrics to obtain a second network status, which is the current network status used by the target edge application.

[0112] In this embodiment of the application, the QoE acquisition module 301 can also be used for:

[0113] Determine the application information of edge applications, including the service type of edge applications and their network metric requirements;

[0114] Based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC, the network state of the wireless base station is adjusted to obtain the first network state.

[0115] QoE for edge applications that gather user feedback when running in the first network state.

[0116] In this embodiment of the application, the QoE acquisition module 301 can also be used for:

[0117] Based on the application information of edge applications, determine the network metric requirements of edge applications;

[0118] Based on the network metric requirements of edge applications and the DPI control strategy unit in MEC, determine the first control strategy to optimize the wireless base station.

[0119] Based on the RIC and the first control strategy, the network state of the wireless base station is adjusted to obtain the first network state.

[0120] In this embodiment of the application, the QoE acquisition module 301 can also be used for:

[0121] According to the first control strategy, the first network information to be optimized for the wireless base station and the first optimization method for the first network information to be optimized are determined.

[0122] Based on the first network information to be optimized, RIC, and the first optimization method, the network state of the wireless base station is adjusted to obtain the first network state.

[0123] In this embodiment of the application, the network status acquisition module 303 can also be used for:

[0124] Identify the wireless base station in the first network state;

[0125] Based on the target edge application's network metric requirements and the DPI control strategy unit, a second control strategy for optimizing the wireless base station in the first network state is determined.

[0126] Based on the RIC and the second control strategy, the wireless base station in the first network state is adjusted to obtain the second network state.

[0127] In this embodiment of the application, the network status acquisition module 303 can also be used for:

[0128] According to the second control strategy, the second network information to be optimized for the wireless base station in the first network state and the second optimization method for the second network information to be optimized are determined.

[0129] Based on the second network information to be optimized, RIC, and the second optimization method, the wireless base station in the first network state is adjusted to obtain the second network state.

[0130] In this embodiment of the application, the network status acquisition module 303 can also be used for:

[0131] The target edge application that obtains user feedback updates its QoE when running in the second network state;

[0132] If the updated QoE meets the user's business service requirements, then the second network state is determined as the target network state for the target edge application.

[0133] If the updated QoE does not meet the user's business service requirements, the second network state will be adjusted until the target network state that meets the user's business service requirements is obtained.

[0134] As can be seen from the above, the edge application operation optimization device 30 in this embodiment of the application comprises a QoE acquisition module 301, used to acquire the QoE of the edge application, wherein the edge application is an application running in a first network state of the wireless base station, and the first network state is determined according to the service type of the edge application and its requirements for network indicators; an application acquisition module 302, used to obtain the target edge application and the target requirements of the target edge application for network indicators based on the QoE, wherein the target edge application is obtained by the server updating the edge application based on the QoE; and a network state acquisition module 303, used to adjust the first network state according to the target requirements of the target edge application for network indicators to obtain a second network state, wherein the second network state is the current network state used by the target edge application. Thus, it is ensured that the wireless base station completes the differentiated adjustment algorithm for specific service types according to the set optimization strategy, thereby achieving better service performance and user service experience for the edge application.

[0135] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 40 includes:

[0136] The electronic device 40 may include a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a communication component 403, and other components. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0137] In the specific implementation process, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to execute the above-mentioned edge application operation optimization method.

[0138] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0139] In the above Figure 4In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0140] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0141] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0142] In some embodiments, a computer program product is also provided, comprising a computer program or instructions that, when executed by a processor, implement the steps in the operation optimization method for any of the aforementioned edge applications.

[0143] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0144] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0145] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any edge application operation optimization method provided in embodiments of this application.

[0146] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0147] According to one aspect of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium.

[0148] Since the instructions stored in the storage medium can execute the steps in any of the edge application operation optimization methods provided in the embodiments of this application, the beneficial effects that any of the edge application operation optimization methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0149] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0150] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for optimizing the operation of edge applications, characterized in that, The method, applied to an edge application operation optimization system, which includes MEC, RIC, and wireless base stations, comprises: Obtain the QoE of an edge application, wherein the edge application is an application running in a first network state of the wireless base station, and the first network state is determined according to the service type of the edge application and its requirements for network indicators. Based on the QoE, the target edge application and the target network metrics requirements of the target edge application are obtained. The target edge application is obtained by the server updating the edge application based on the QoE. The server uses an AI engine to train an AI model on the application features of the edge application and the QoE to optimize the application model, and then updates the target edge application. Based on the target edge application's target requirements for network metrics, the first network state is adjusted to obtain a second network state, which is the current network state used by the target edge application. The acquisition of the QoE of the edge application includes: Determine the application information of the edge application, including the service type of the edge application and the network metric requirements of the edge application; Based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC, the network state of the wireless base station is adjusted to obtain a first network state; The edge application obtains user feedback on its QoE when running in the first network state.

2. The method according to claim 1, characterized in that, The step of adjusting the network state of the wireless base station based on the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC to obtain a first network state includes: Based on the application information of the edge application, determine the network metric requirements of the edge application; Based on the network metric requirements of the edge application and the DPI control strategy unit in the MEC, a first control strategy for optimizing the wireless base station is determined. Based on the RIC and the first control strategy, the network state of the wireless base station is adjusted to obtain a first network state.

3. The method according to claim 2, characterized in that, The step of adjusting the network state of the wireless base station according to the RIC and the first control strategy to obtain a first network state includes: Based on the first control strategy, determine the first network information to be optimized for the wireless base station and the first optimization method for the first network information to be optimized. Based on the first network information to be optimized, the RIC, and the first optimization method, the network state of the wireless base station is adjusted to obtain a first network state.

4. The method according to claim 1, characterized in that, The step of adjusting the first network state to obtain a second network state based on the target network metric requirements of the target edge application includes: Identify the wireless base station in the first network state; Based on the target edge application's target requirements for network metrics and the DPI control strategy unit in the MEC, a second control strategy is determined to optimize the wireless base station in the first network state. Based on the RIC and the second control strategy, network adjustments are made to the wireless base station in the first network state to obtain the second network state.

5. The method according to claim 4, characterized in that, The step of adjusting the wireless base station in the first network state according to the RIC and the second control strategy to obtain the second network state includes: Based on the second control strategy, the second network information to be optimized for the wireless base station in the first network state and the second optimization method for the second network information to be optimized are determined. Based on the second network information to be optimized, the RIC, and the second optimization method, the wireless base station in the first network state is adjusted to obtain the second network state.

6. The method according to claim 1, characterized in that, After adjusting the first network state according to the target requirements of the target edge application for network metrics to obtain the second network state, the method further includes: The target edge application, as reported by the user, is updated in the QoE when running in the second network state; If the updated QoE meets the user's business service requirements, then the second network state is determined to be the target network state of the target edge application; If the updated QoE does not meet the user's service requirements, then the second network state is adjusted until a target network state that meets the user's service requirements is obtained.

7. An edge application operation optimization device, characterized in that, include: The QoE acquisition module is used to acquire the QoE of an edge application, wherein the edge application is an application that runs in a first network state of the wireless base station. The first network state is determined according to the service type of the edge application and its requirements for network indicators. The application module is used to obtain the target edge application and the target network metrics requirements of the target edge application based on the QoE. The target edge application is obtained by the server updating the edge application based on the QoE. The server uses an AI engine to train an AI model on the application features of the edge application and the QoE to optimize the application model, and then updates and obtains the target edge application. The network status acquisition module is used to adjust the first network status according to the target requirements of the target edge application for network metrics, and obtain a second network status, wherein the second network status is the current network status used by the target edge application. The QoE acquisition module is specifically used to determine the application information of the edge application, including the service type of the edge application and the network indicator requirements of the edge application; adjust the network state of the wireless base station according to the application information of the edge application, the DPI control strategy unit in the MEC, and the RIC to obtain a first network state; and acquire the QoE of the edge application running in the first network state as reported by the user.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images