Computing resource allocation method and device based on vehicle-mounted edge computing network

Abstract

The invention provides a computing resource allocation method and device based on a vehicle-mounted edge computing network, and relates to the technical field of computers, and the method comprises the steps: receiving a resource allocation request sent by a target vehicle; in response to the resource allocation request, obtaining service resource information and service satisfaction information of the vehicle-mounted edge server in real time; determining a target weight factor of the target service satisfaction of the target vehicle according to the service resource information and the service satisfaction information of the vehicle-mounted edge server; and generating a resource allocation decision based on the target service satisfaction and the target weight factor, and allocating corresponding computing resources to the target vehicle according to the resource allocation decision. According to the method and the system, changes of tasks and network environments can be flexibly handled, the computing resource allocation decision of the server is dynamically adjusted, the resource utilization rate and the task processing efficiency of the system are improved, and the robustness and the stability of the system are enhanced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for allocating computing resources based on a vehicle-mounted edge computing network. Background Art

[0002] In recent years, with the continuous development of mobile communications and intelligent vehicles, in-vehicle networks have become a research hotspot to support a variety of in-vehicle entertainment and safety application services, such as autonomous driving, intelligent navigation, in-vehicle entertainment applications, etc. However, many in-vehicle services are computationally intensive and latency sensitive, requiring intensive computing power for real-time processing, which often exceeds the limited computing and storage capabilities of mobile devices. Although services can be offloaded to the cloud for processing, the service latency is about 50-100 milliseconds, which exceeds the latency requirements. Vehicular Edge Computing (VEC) based on Mobile Edge Computing (MEC) has become a promising solution to provide low latency and high computing power for popular in-vehicle services.

[0003] VEC can provide low-latency computing services to vehicles by deploying servers at the edge of the vehicular network, such as edge servers connected to base stations (BS) and road side units (RSU). However, due to the limited coverage of VEC servers, fast-moving vehicles may often drive out of the coverage of the VEC servers that provide services to them. The increase in the distance between the VEC server and the vehicle will seriously degrade the quality of service (QoS), further leading to a decrease in the service satisfaction perceived by the vehicle. In order to improve the QoS of the service and always provide a high level of service satisfaction to vehicle users, service migration to adapt to high mobility is inevitable. Therefore, designing an efficient resource allocation algorithm is crucial for the service migration strategy.

[0004] Existing edge computing resource allocation algorithms have obvious problems in adaptability and are difficult to flexibly respond to dynamic user needs. These algorithms are usually based on fixed assumptions and predefined rules, ignoring changes in user needs and the dynamic nature of the environment. For example, user task loads and network conditions may fluctuate significantly over time, and existing algorithms often cannot adjust resource allocation strategies in real time to adapt to such changes, resulting in inefficient resource utilization or poor user experience. Summary of the invention

[0005] The present invention provides a computing resource allocation method and device based on a vehicle-mounted edge computing network, which can analyze the dynamically changing resource status of the server and the service requirements of the user in edge computing, dynamically adjust the computing resource allocation decision of the server, and flexibly respond to changes in tasks and network environment. It not only improves the system's resource utilization and task processing efficiency, but also enhances the system's robustness and stability.

[0006] In a first aspect, a method for allocating computing resources of a vehicle-mounted edge server is provided, comprising: Receive a resource allocation request sent by a target vehicle, where the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server; In response to the resource allocation request, obtaining service resource information and service satisfaction information of the vehicle-mounted edge server in real time, the service resource information including the upper limit of computing resources, the total amount of allocated resources, and the average amount of allocated resources of the vehicle-mounted edge server, and the service satisfaction information including the average satisfaction of the first service of the deployed service instance; Determine a target weight factor of a target service satisfaction level of a target vehicle based on the service resource information and service satisfaction level information of the vehicle-mounted edge server; Generate resource allocation decisions based on target service satisfaction and target weight factors, and allocate corresponding computing resources to target vehicles according to the resource allocation decisions.

[0007] In a possible implementation, before obtaining the service resource information and service satisfaction information of the vehicle-mounted edge server in real time in response to the resource allocation request, the computing resource allocation method of the vehicle-mounted edge server further includes: Determine a first service delay for each deployed service instance on the vehicle-mounted edge server, where the first service delay is the sum of an uplink transmission delay, a calculation delay, and a downlink transmission delay corresponding to each of the deployed service instances; Calculating the service satisfaction of each of the deployed service instances based on the first service delay; An average of the deployed service instances with respect to the service satisfaction is calculated to obtain the first service average satisfaction.

[0008] In a possible implementation, determining a target weight factor of a target service satisfaction level of a target vehicle according to the service resource information and the service satisfaction level information of the vehicle-mounted edge server includes: Obtaining a target weight factor of a target service satisfaction level of the target vehicle; Based on the first service average satisfaction, the service resource information, the resource shortage threshold, and the resource idle threshold, determining whether the resource status of the vehicle-mounted edge server needs to be adjusted; When it is determined that the resource status of the vehicle-mounted edge server does not need to be adjusted, keeping the target weight factor unchanged; When it is determined that the resource status of the vehicle-mounted edge server needs to be adjusted, the target weight factor of the service satisfaction in the resource allocation calculation is dynamically updated.

[0009] In a possible implementation, when it is determined that the resource status of the vehicle-mounted edge server needs to be adjusted, dynamically updating the target weight factor of the service satisfaction in the resource allocation calculation includes: When it is determined that the resource state of the vehicle-mounted edge server is a resource-constrained state, the target weight factor of the service satisfaction in the computing resource allocation is reduced based on a preset incremental value until it is determined that a first service satisfaction improvement condition is met, and an updated target weight factor is obtained, wherein the first service satisfaction improvement condition is that the updated target weight factor is greater than 0, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to a service satisfaction threshold; When it is judged that the resource status of the on-board edge server is a sufficient resource status and the first service average satisfaction is insufficient, the target weight factor of the service satisfaction in the computing resource allocation is increased based on the preset incremental value until it is judged that the second service satisfaction improvement condition is met, and an updated target weight factor is obtained, wherein the second service satisfaction improvement condition is that the updated target weight factor is less than or equal to 1, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to the service satisfaction threshold.

[0010] In a possible implementation, the reducing the target weight factor of the service satisfaction in the computing resource allocation based on the preset increment value until it is determined that the first service satisfaction improvement condition is met to obtain the updated target weight factor includes: Iteratively perform the following target weight factor reduction operation until it is determined that the first service satisfaction improvement condition is met, and obtain an updated target weight factor; The operation of reducing the target weight factor includes: The difference between the current target weight factor and the preset increment value is used as the updated target weight factor; If it is determined that the updated target weight factor is greater than 0, reallocating computing resources for the deployed service instance based on the updated target weight factor, and calculating the second service average satisfaction of the deployed service instance after the computing resources are reallocated; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, the updated target weight factor is used as the current target weight factor, and the operation of reducing the current target weight factor is repeatedly performed; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the first service satisfaction improvement condition is met, and a final updated target weight factor is obtained; And / or, increasing the target weight factor of the service satisfaction in the computing resource allocation based on the preset increment value until it is determined that the second service satisfaction improvement condition is met to obtain an updated target weight factor, including: Iteratively perform the following target weight factor increase operation until it is determined that the second service satisfaction improvement condition is met, and obtain an updated target weight factor; The operation of increasing the target weight factor includes: The sum of the current target weight factor and the preset increment value is used as the updated target weight factor; If it is determined that the updated target weight factor is less than or equal to 1, reallocate computing resources for the deployed service instance based on the updated target weight factor, and calculate the second service average satisfaction of the deployed service instance after the computing resources are reallocated; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, the updated target weight factor is used as the current target weight factor, and the operation of increasing the current target weight factor is repeatedly performed; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the second service satisfaction improvement condition is met, and the final updated target weight factor is obtained.

[0011] In a possible implementation manner, before generating a resource allocation decision based on the target service satisfaction and the target weight factor, the method further includes: Obtaining a second service delay of the target vehicle, where the second service delay is the sum of an uplink transmission delay, a calculation delay, and a downlink transmission delay of the target vehicle; The target service satisfaction level is calculated according to the second service delay and the second service delay threshold.

[0012] In a possible implementation manner, generating a resource allocation decision based on the target service satisfaction and the target weight factor includes: Repeat the following iterative update process of the resource allocation decision until a preset convergence condition is reached to obtain a final resource allocation decision; The iterative update process of the resource allocation decision includes: constructing a utility function according to the target service satisfaction, the target weight factor, and the resource allocation decision; Given the initial value of the resource allocation decision as the current resource allocation decision, determining the gradient vector corresponding to the utility function under the current resource allocation decision; Calculate the search direction of the current resource allocation decision according to the Hessian matrix and the gradient vector; Using the search direction and a preset update step size, updating the current resource allocation decision; When it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is greater than or equal to the convergence threshold, the updated resource allocation decision is used as the current resource allocation decision, and the above-mentioned updating process of the current resource allocation decision is repeatedly executed; When it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is less than the convergence threshold, it is determined that the preset convergence condition is met, and the updated resource allocation decision is determined as the final resource allocation decision.

[0013] In a second aspect, a computing resource allocation device for a vehicle-mounted edge server is provided, comprising: A receiving module, used to receive a resource allocation request sent by a target vehicle, where the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server; an acquisition module, configured to obtain service resource information and service satisfaction information of the vehicle-mounted edge server in real time in response to a resource allocation request, wherein the service resource information includes an upper limit of computing resources, a total amount of allocated resources, and an average amount of allocated resources of the vehicle-mounted edge server, and the service satisfaction information includes an average satisfaction of a first service of a deployed service instance; An updating module, configured to determine a target weight factor of a target service satisfaction level of a target vehicle based on the service resource information and service satisfaction level information of the vehicle-mounted edge server; The generation module is used to generate resource allocation decisions based on the target service satisfaction and the target weight factor, and allocate corresponding computing resources to the target vehicle according to the resource allocation decision.

[0014] According to a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementations.

[0015] According to a fourth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method according to the first aspect or its various implementations.

[0016] Through the technical solution provided by the present invention, after receiving a resource allocation request carrying the resource demand of the target vehicle, in response to the resource allocation request, the service resource information and service satisfaction information of the vehicle-mounted edge server can be obtained in real time, the service resource information includes the upper limit of the computing resources of the vehicle-mounted edge server, the total amount of allocated resources and the average amount of allocated resources, and the service satisfaction information includes the average satisfaction of the first service of the deployed service instance; then, according to the service resource information and service satisfaction information of the vehicle-mounted edge server, the target weight factor of the target service satisfaction of the target vehicle is determined; finally, based on the target service satisfaction and the target weight factor, a resource allocation decision is generated, and corresponding computing resources are allocated to the target vehicle according to the resource allocation decision. The technical solution in this application can dynamically adjust the computing resource allocation decision of the vehicle-mounted edge server by analyzing the dynamically changing resource status of the server in edge computing and the service demand of the user, and can flexibly respond to changes in tasks and network environment, which not only improves resource utilization and task processing efficiency, but also enhances the robustness and stability of the vehicle-mounted edge computing network.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present invention. Other features and advantages of the present invention will be described in detail in the following specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 An application scenario diagram provided for an embodiment of the present application; Figure 2 A flowchart of a method for allocating computing resources of a vehicle-mounted edge server provided in an embodiment of the present application; Figure 3 A flowchart of a method for allocating computing resources of a vehicle-mounted edge server provided in another embodiment of the present application; Figure 4 A schematic diagram of the structure of a computing resource allocation device for a vehicle-mounted edge server provided in an embodiment of the present application; Figure 5A schematic diagram of the structure of a computing resource allocation device for a vehicle-mounted edge server provided in another embodiment of the present application; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] In recent years, with the continuous development of mobile communications and intelligent vehicles, in-vehicle networks have become a research hotspot to support a variety of in-vehicle entertainment and safety application services, such as autonomous driving, intelligent navigation, in-vehicle entertainment applications, etc. However, many in-vehicle services are computationally intensive and latency sensitive, requiring intensive computing power for real-time processing, which often exceeds the limited computing and storage capabilities of mobile devices. Although services can be offloaded to the cloud for processing, the service latency is about 50-100 milliseconds, which exceeds the latency requirements. Vehicular Edge Computing (VEC) based on Mobile Edge Computing (MEC) has become a promising solution to provide low latency and high computing power for popular in-vehicle services.

[0023] VEC can provide low-latency computing services to vehicles by deploying servers at the edge of the vehicular network, such as edge servers connected to base stations (BS) and road side units (RSU). However, due to the limited coverage of VEC servers, fast-moving vehicles may often drive out of the coverage of the VEC servers that provide services to them. The increase in the distance between the VEC server and the vehicle will seriously degrade the quality of service (QoS), further leading to a decrease in the service satisfaction perceived by the vehicle. In order to improve the QoS of the service and always provide a high level of service satisfaction to vehicle users, service migration to adapt to high mobility is inevitable. Therefore, designing an efficient resource allocation algorithm is crucial for the service migration strategy.

[0024] Existing edge computing resource allocation algorithms have obvious problems in adaptability and are difficult to flexibly respond to dynamic user needs. These algorithms are usually based on fixed assumptions and predefined rules, ignoring changes in user needs and the dynamic nature of the environment. For example, user task loads and network conditions may fluctuate significantly over time, and existing algorithms often cannot adjust resource allocation strategies in real time to adapt to such changes, resulting in inefficient resource utilization or poor user experience.

[0025] In addition, many algorithms fail to effectively consider the diversity of user needs and cannot provide personalized resource allocation solutions for tasks of different priorities or heterogeneous users. This inflexible allocation method makes it difficult to achieve a balance between efficient resource utilization and service satisfaction in practical applications, highlighting the limitations of existing algorithms in dealing with complex dynamic environments. Although the "A Synaesthesia Resource Allocation Method" with patent number CN202411097033.2 dynamically adjusts the strategy to achieve a compromise between privacy entropy and queuing delay, its optimization process may still rely on fixed model parameters and rules, and lacks the ability to flexibly respond to real-time user needs and environmental changes. Secondly, the compromise weight between privacy entropy and queuing delay may not reflect the actual needs or emergencies of users in a timely manner, resulting in insufficient or inaccurate resource allocation. In addition, although constraint transformation helps to decouple long-term management from short-term decision-making, it may lead to decision lags in rapidly changing scenarios and fail to quickly adapt to new user needs or environmental changes. These factors make this method unable to effectively achieve adaptive and flexible resource management when facing dynamic and complex actual Internet of Vehicles applications.

[0026] In order to solve the above technical problems, the inventive concept of the present invention is to propose an adaptive computing resource allocation method for dynamic user needs. The method is divided into two parts: user satisfaction model construction and adaptive resource allocation based on user dynamic needs. First, the current environment and user needs are evaluated by real-time monitoring of user task load, network status and computing resource status in the system. Then, based on the evaluation results, the optimal resource allocation scheme is dynamically calculated to ensure efficient utilization of resources and low latency in task processing. Finally, by adaptively adjusting the resource allocation strategy, the system is guaranteed to be able to flexibly respond to environmental changes and fluctuations in user needs, and to achieve efficient resource management and improved user experience. The method of the present invention is deployed in an edge server, and the method provided by the present invention is used to make resource allocation decisions when a vehicle requests resource allocation.

[0027] It should be understood that the technical solution of the present invention can be applied to the following scenarios, but is not limited to: In some possible implementations, Figure 1 An application scenario diagram provided by an embodiment of the present invention, such as Figure 1 As shown, the application scenario may include an electronic device 110 and a network device 120. The electronic device 110 may establish a connection with the network device 120 via a wired network or a wireless network.

[0028] Exemplarily, the electronic device 110 may be a desktop computer, a laptop computer, a tablet computer, etc., but is not limited thereto. The network device 120 may be a terminal device or a server, but is not limited thereto. In one embodiment of the present invention, the electronic device 110 may send a request message to the network device 120, and the request message may be used to request to obtain the service resource information and service satisfaction information of the vehicle-mounted edge server. Further, the electronic device 110 may receive a response message sent by the network device 120, and the response message includes the service resource information and service satisfaction information of the vehicle-mounted edge server.

[0029] also, Figure 1 An electronic device 110 and a network device 120 are provided as an example, but other numbers of electronic devices and network devices may be included in practice, and the present invention is not limited thereto.

[0030] In other possible implementations, the technical solution of the present invention may also be executed by the electronic device 110, or the technical solution of the present invention may also be executed by the network device 120, and the present invention does not limit this. Specifically, as an example, the technical solution of the present invention may be executed by a vehicle-mounted edge server.

[0031] After introducing the application scenarios of the embodiments of the present invention, the technical solutions of the present invention will be described in detail below: Figure 2A flowchart of a method for allocating computing resources of a vehicle-mounted edge server provided by an embodiment of the present invention. Figure 2 As shown, the method may include the following steps: Step 210: Receive a resource allocation request sent by the target vehicle, where the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server.

[0032] Among them, the target vehicle is a vehicle to be allocated resources in the vehicle network, and the resource allocation request can carry the resource demand of the target vehicle, or the resource demand can be called from the target vehicle at any time in subsequent method steps, which is not limited here.

[0033] The executor of the present application may be a vehicle-mounted edge server, which may receive a resource allocation request sent by a target vehicle in real time, and then respond to the resource allocation request to obtain service resource information and service satisfaction information of the vehicle-mounted edge server in real time, and further dynamically allocate computing resources based on the service resource information and service satisfaction information of the vehicle-mounted edge server.

[0034] Step 220: In response to the resource allocation request, obtain service resource information and service satisfaction information of the vehicle-mounted edge server in real time.

[0035] Among them, the service resource information includes the computing resource upper limit, the total allocated resources and the average allocated resources of the vehicle-mounted edge server, and the service satisfaction information includes the average satisfaction of the first service of the deployed service instance.

[0036] For the disclosed embodiment, by obtaining the service resource information and service satisfaction information of the vehicle-mounted edge server, the vehicle task load, network status and computing resource status in the vehicle-mounted network can be monitored in real time, so as to facilitate the evaluation of the current environment and user needs. Specifically, real-time mastering of the resource upper limit can prevent the server from being overloaded due to excessive resource allocation, which may cause performance degradation, such as computing task response delay, service interruption and other problems; obtaining the total amount of allocated resources can understand the total amount of computing resources currently allocated in real time, which is helpful to monitor the usage of server resources; the average amount of allocated resources can reflect whether the resources are evenly distributed between different services or vehicles. If the average amount of allocated resources is too different, there may be a situation where some services occupy too much resources while other services are insufficient, which helps to discover the problem of unfair distribution; the average service satisfaction is an important indicator for measuring the quality of deployed service instances. It directly reflects the user's (such as passengers or drivers in the vehicle) experience of the service, such as whether the navigation service is accurate, whether the multimedia service is smooth, etc. If the average service satisfaction is low, it is necessary to analyze the cause in depth, which may be insufficient computing resources leading to slow service response, or there may be functional defects in the service itself, so as to make targeted improvements.

[0037] Step 230: Determine a target weight factor of a target service satisfaction level of a target vehicle based on the service resource information and service satisfaction level information of the vehicle-mounted edge server.

[0038] In specific application scenarios, the goal of adaptive resource allocation is to maximize average user satisfaction. The optimization problem cannot only maximize the service satisfaction of a single vehicle, but also needs to balance the service satisfaction of a single vehicle with the computational cost to achieve a state that satisfies the entire vehicle group. This application takes the computational cost into consideration to formulate the utility function , by maximizing the utility function to solve the optimal resource allocation decision , the function definition is as follows:

[0039] here, The target vehicle Target service satisfaction, Indicates the target vehicle The target weight factor of service satisfaction. When , it means that computing resources are allocated with the goal of maximizing the satisfaction of a single user, which is suitable for the situation where there are few vehicles and sufficient system resources. When it gradually approaches 0, it means that the proportion of computing cost is getting higher and higher, which is suitable for situations where there are many vehicles and insufficient system resources. For the embodiments of the present disclosure, by adjusting the target weight factor in real time according to the service resource information and service satisfaction information of the vehicle-mounted edge server, adaptive resource allocation decisions can be made according to the service instance density and resource scarcity in the edge server of the Internet of Vehicles to maximize average user satisfaction. In the following text, as a refinement and expansion, the circumstances under which the target weight factor can be adjusted and how to adjust the target weight factor will be further explained, that is, the target weight factor can be adjusted or not adjusted according to the situation.

[0040] Step 240: Generate a resource allocation decision based on the target service satisfaction and the target weight factor, and allocate corresponding computing resources to the target vehicle according to the resource allocation decision.

[0041] For the embodiments of the present disclosure, resource allocation decisions are closely related to the target weight factor and the target service satisfaction. The resource allocation decisions generated based on the two can adapt to the current service demand and resource status, thereby improving service satisfaction and resource utilization efficiency.

[0042] In summary, according to the computing resource allocation method of the vehicle-mounted edge server provided by the present invention, after receiving the resource allocation request carrying the resource demand of the target vehicle, in response to the resource allocation request, the service resource information and service satisfaction information of the vehicle-mounted edge server can be obtained in real time, the service resource information includes the upper limit of the computing resources of the vehicle-mounted edge server, the total amount of allocated resources and the average amount of allocated resources, and the service satisfaction information includes the average satisfaction of the first service of the deployed service instance; then, according to the service resource information and service satisfaction information of the vehicle-mounted edge server, the target weight factor of the target service satisfaction of the target vehicle is determined; finally, based on the target service satisfaction and the target weight factor, a resource allocation decision is generated, and the corresponding computing resources are allocated to the target vehicle according to the resource allocation decision. The technical solution in this application can dynamically adjust the computing resource allocation decision of the vehicle-mounted edge server by analyzing the dynamically changing resource status of the server in edge computing and the service demand of the user, and can flexibly respond to changes in tasks and network environment, which not only improves resource utilization and task processing efficiency, but also enhances the robustness and stability of the vehicle-mounted edge computing network.

[0043] based on Figure 2 The embodiment shown is a refinement and extension of the above embodiment. In order to fully illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 3 The specific method shown. Figure 3 based on Figure 2 As shown in 3, the method comprises the following steps: Step 310: Receive a resource allocation request sent by the target vehicle, where the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server.

[0044] For the embodiment of the present disclosure, the specific implementation process can refer to the relevant description in step 210 of the embodiment, which will not be repeated here.

[0045] Step 320: In response to the resource allocation request, obtain service resource information and service satisfaction information of the vehicle-mounted edge server in real time.

[0046] Among them, the service resource information includes the computing resource upper limit, the total allocated resources and the average allocated resources of the vehicle-mounted edge server, and the service satisfaction information includes the average satisfaction of the first service of the deployed service instance.

[0047] Service delay is crucial to the driver's driving safety and the passenger's service experience. At time t, a resource allocation request is initiated to the vehicle-mounted edge server that provides computing services for it. After the vehicle-mounted edge server processes the resource allocation request, it sends the response data back to the target vehicle. Therefore, for the target vehicle For the second service delay Delay for uplink transmission , calculation delay and downstream transmission delay The sum is expressed as:

[0048] This application can divide service satisfaction into multiple levels, where each level is associated with a certain range of service delay. Service satisfaction in this application is related to service delay and context. Context is a combination of several variables that affect service satisfaction, such as service type, time and location. Usually for a specific context, the service will have a consistent satisfaction behavior, that is, it depends only on the service delay. Service satisfaction is expressed as follows:

[0049] in, means round up, as an example, , , , are all parameters in the nonlinear index satisfaction function. It can be understood that the values ​​of the three parameters can be selected according to the situation and are not limited here. Service satisfaction uses two variables and Modeling, is the service delay; It is the maximum delay time set, which is a constant (for example, 600ms, which is related to user service requirements); Represents context, which is a combination of several variables that affect service satisfaction, such as service type, time and location, etc. In actual situations, different values ​​can be set according to different applications. In this application, the value applied can be set to 0.6. The decrease of service satisfaction leads to an increase in user tolerance, and vice versa. The value of is fixed, service satisfaction Is the service delay It is understandable that the target vehicle The target service satisfaction is the second service delay of the target vehicle function.

[0050] In a specific application scenario, when calculating the average satisfaction of the first service of a deployed service instance, the service satisfaction of each deployed service instance on the vehicle edge server can be calculated based on the above method, and then the average service satisfaction of multiple deployed service instances is calculated to obtain the average satisfaction of the first service.

[0051] Accordingly, the steps of the embodiment may include: determining the first service delay of each deployed service instance on the vehicle edge server, the first service delay being the sum of the uplink transmission delay, calculation delay and downlink transmission delay corresponding to each deployed service instance; calculating the service satisfaction of each deployed service instance based on the first service delay; calculating the average value of the service satisfaction of the deployed service instances to obtain the first service average satisfaction.

[0052] Step 330: Obtain a target weight factor of a target service satisfaction level of a target vehicle.

[0053] For the disclosed embodiment, the second service delay of the target vehicle can be obtained, and the second service delay is the sum of the uplink transmission delay, calculation delay and downlink transmission delay of the target vehicle; the target service satisfaction is calculated according to the second service delay and the second service delay threshold. After that, the target service satisfaction corresponding to the initial target weight factor can be determined, and in the subsequent steps, according to the service instance density and resource shortage of the vehicle-mounted edge server, it is determined whether the initial target weight factor needs to be adjusted, that is, the target weight factor can be adjusted or not adjusted according to the situation.

[0054] Step 340: Based on the first service average satisfaction, service resource information, resource shortage threshold, and resource idle threshold, determine whether the resource status of the vehicle edge server needs to be adjusted.

[0055] In a specific application scenario, when it is judged that the computing resources of the vehicle edge server are sufficient and the average satisfaction of the first service is high, it can be judged that the resource status of the vehicle edge server does not need to be adjusted; when it is judged that the computing resources of the vehicle edge server are insufficient, or the resource status of the vehicle edge server is in a sufficient resource state and the average satisfaction of the first service is insufficient, it can be judged that the resource status of the vehicle edge server needs to be adjusted.

[0056] For the embodiment of the present disclosure, the computing resource limit of the vehicle-mounted edge server can be and the total amount of resources allocated ,in, =1,2,…N, represents the serial number of each deployed service instance, N is the total number of deployed service instances on the vehicle edge server, For the The resource allocation corresponding to the deployed service instances; calculate the remaining computing resources of the vehicle edge server . And calculate the average amount of allocated resources and resource scarcity threshold The first product of is calculated and compared with the remaining amount of computing resources to determine whether the resource status of the vehicle-mounted edge server is in a resource-constrained state. , then the resource status of the vehicle-mounted edge server is determined to be resource-intensive; in addition, the average amount of allocated resources and the resource idle threshold can also be calculated The second product of is calculated and compared with the remaining amount of computing resources to determine whether the resource status of the vehicle-mounted edge server is sufficient. and , it is determined that the resource status of the vehicle-mounted edge server is sufficient, but the average satisfaction of the first service is insufficient. is the service satisfaction of the i-th deployed service instance.

[0057] For the embodiments of the present disclosure, by analyzing the resource status of the vehicle-mounted edge server in real time, it is possible to dynamically adjust the computing resources of the edge server based on the resource status, so that the allocation of computing resources can respond to changes in network load or computing demand in real time, thereby avoiding resource waste and task delays.

[0058] Step 350a: When it is determined that the resource status of the vehicle-mounted edge server does not need to be adjusted, the target weight factor is kept unchanged.

[0059] In step 350b of the embodiment parallel to step 350a of the embodiment, when it is determined that the resource status of the vehicle-mounted edge server needs to be adjusted, the target weight factor of the service satisfaction in the calculation resource allocation is dynamically updated.

[0060] For the embodiments of the present disclosure, when dynamically updating the target weight factor of service satisfaction in computing resource allocation, as a possible implementation method, when it is judged that the resource state of the vehicle-mounted edge server is a resource-constrained state, the target weight factor of service satisfaction in computing resource allocation is reduced based on a preset incremental value until it is judged that the first service satisfaction improvement condition is met, and the updated target weight factor is obtained.

[0061] Among them, the first service satisfaction improvement condition is that the updated target weight factor is greater than 0, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to the service satisfaction threshold.

[0062] For the embodiment of the present disclosure, when the target weight factor of the service satisfaction in the computing resource allocation is reduced based on the preset incremental value until it is determined that the first service satisfaction improvement condition is met and the updated target weight factor is obtained, the code execution process is: Input: Server computing resource limit , the total number of deployed service instances N, the allocated resources , Deployed Service Satisfaction , preset increment value , target weight factor , resource shortage threshold , service satisfaction threshold ; Output: Updated target weight factor ; If : Repeat:

[0063] Based on the updated target weight factor Reallocate resources for deployed service instances in the vehicle-mounted edge server and calculate relevant parameter information at this time: Deployed service satisfaction

[0064] If and :( The average satisfaction of the second service, Average satisfaction with first service

[0065] break If : break Accordingly, in the steps of the embodiment, reducing the target weight factor of the service satisfaction in the computing resource allocation based on the preset increment value until it is determined that the first service satisfaction improvement condition is met, and obtaining the updated target weight factor may include: The following target weight factor reduction operation is iteratively performed until it is determined that the first service satisfaction improvement condition is met, thereby obtaining an updated target weight factor.

[0066] Among them, the reduction operation of the target weight factor includes: taking the difference between the current target weight factor and the preset incremental value as the updated target weight factor; if it is judged that the updated target weight factor is greater than 0, then reallocating computing resources for the deployed service instances based on the updated target weight factor, and calculating the second service average satisfaction of the deployed service instances after the reallocation of computing resources; when it is judged that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, taking the updated target weight factor as the current target weight factor, and repeatedly performing the reduction operation on the current target weight factor; when it is judged that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, determining that the first service satisfaction improvement condition is met, and obtaining the final updated target weight factor .

[0067] When dynamically updating the target weight factor of service satisfaction in computing resource allocation, as another possible implementation method, when it is judged that the resource status of the on-board edge server is a sufficient resource state and the average satisfaction of the first service is insufficient, the target weight factor of service satisfaction in computing resource allocation is increased based on a preset incremental value until it is judged that the second service satisfaction improvement condition is met, and the updated target weight factor is obtained.

[0068] Among them, the second service satisfaction improvement condition is that the updated target weight factor is less than or equal to 1, and the difference between the second service average satisfaction and the first service average satisfaction corresponding to the updated target weight factor is greater than or equal to the service satisfaction threshold.

[0069] For the embodiment of the present disclosure, when the target weight factor of the service satisfaction in the computing resource allocation is increased based on the preset increment value until it is determined that the second service satisfaction improvement condition is met and the updated target weight factor is obtained, the code execution process is: Input: Server computing resource limit , the total number of deployed service instances N, the allocated resources , Deployed Service Satisfaction , preset increment value , target weight factor , resource idle threshold , service satisfaction threshold ; Output: Updated target weight factor ; If and : Repeat:

[0070] Based on the updated target weight factor Reallocate resources for deployed service instances in the vehicle-mounted edge server and calculate relevant parameter information at this time: Deployed service satisfaction

[0071] If and :( The average satisfaction of the second service, Average satisfaction with first service

[0072] break If : break Accordingly, in the embodiment, the target weight factor of service satisfaction in computing resource allocation is increased based on the preset incremental value until it is determined that the second service satisfaction improvement condition is met, and the updated target weight factor is obtained, which may include: The following target weight factor increase operation is iteratively performed until it is determined that the second service satisfaction improvement condition is met, thereby obtaining an updated target weight factor.

[0073] Among them, the increase operation of the target weight factor includes: taking the sum of the current target weight factor and the preset increment value as the updated target weight factor; if it is judged that the updated target weight factor is less than or equal to 1, then based on the updated target weight factor, the computing resources of the deployed service instance are reallocated, and the second service average satisfaction of the deployed service instance after the computing resources are reallocated is calculated; when it is judged that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, the updated target weight factor is used as the current target weight factor, and the increase operation of the current target weight factor is repeatedly performed; when it is judged that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the second service satisfaction improvement condition is met, and the final updated target weight factor is obtained. .

[0074] It is understandable that if and When the computing resources of the vehicle edge server are sufficient and the average satisfaction of the first service is high, it can be determined that the resource status of the vehicle edge server does not need to be adjusted.

[0075] For the disclosed embodiment, under different resource states of the vehicle-mounted edge server, the weight factor can be dynamically adjusted so that resource allocation can adapt to the current service demand and resource status, thereby improving service satisfaction and resource utilization efficiency.

[0076] Step 360: Generate a resource allocation decision based on the target service satisfaction and the target weight factor, and allocate corresponding computing resources to the target vehicle according to the resource allocation decision.

[0077] The goal of adaptive resource allocation is to maximize average user satisfaction. The optimization problem cannot only maximize the service satisfaction of a single vehicle, but also needs to balance the service satisfaction of a single vehicle with the computational cost to achieve a state that satisfies the entire vehicle group. This application takes the computational cost into consideration to formulate the utility function , by maximizing the utility function to solve the optimal resource allocation decision , the function definition is as follows:

[0078] here, It indicates that the weight factor is the target weight factor of service satisfaction, Is a user service satisfaction. When , it means that computing resources are allocated with the goal of maximizing the satisfaction of a single user, which is suitable for the situation where there are few vehicles and sufficient system resources. When it gradually approaches 0, it means that the proportion of computing cost is getting higher and higher, which is suitable for the situation where there are a large number of vehicles and insufficient system resources.

[0079] User satisfaction Substitute the formula into the utility function After that, we get the resource allocation decision (a user's computing resource classification) and utility function The relationship is as follows:

[0080] Then take the second derivative of this function and you get:

[0081] in, , , is the parameter in the nonlinear exponential satisfaction function. As an example, , ; represents context, which is a combination of several variables that affect service satisfaction, such as service type, time and location; The target vehicle Uplink transmission delay; The target vehicle Downlink transmission delay; The target vehicle The amount of resources required; It is the maximum delay time set, which is a constant (for example, 600ms, which is related to user service requirements); Indicates the maximum value of service satisfaction; is the unit computing intensity, which can be understood as the complexity or workload of the computing task performed under conditions such as unit time or unit resource consumption. About resource allocation decisions The second derivative of and resource demand The quadratic correlation is positive, although the technical solution of this application does not involve the resource demand direct improvement, but understandably, the resource requirements With the utility function Solving the resource allocation decision There are inherent connections, which will have a certain impact on the final solution, so I will not go into details here.

[0082] However, since this function involves many parameters and complex exponential and logarithmic functions, it is impossible to find an analytical solution. A common approach to this problem is to use numerical optimization techniques, such as Newton's method or quasi-Newton's method, to iteratively approximate a solution that makes the derivative equal to zero. By providing an initial guess, the algorithm will gradually converge to a solution that meets the conditions. Here we can use Newton's method to solve it, and the corresponding algorithm flow is described as follows: Input includes resource requirements , target weight factor and convergence threshold . When initializing, select an initial point As the current resource allocation decision, and set the initial Hessian matrix is the unit matrix. The algorithm continuously calculates the gradient vector through an iterative process , and using the Hessian matrix and gradient vector Determine the search direction Next, the step size is determined by line search (binary search) , update the parameters to obtain new resource allocation decisions After each iteration, the Hessian matrix is ​​updated The algorithm meets the preset convergence conditions. Stop when , and finally output the optimal resource allocation decision This method can improve the efficiency and accuracy of resource allocation and is suitable for scenarios such as edge computing.

[0083] Accordingly, for the embodiment of the present disclosure, when generating a resource allocation decision based on the target service satisfaction and the updated target weight factor, step 360 of the embodiment may include: Step 360-1: Repeat the following iterative update process of resource allocation decision until a preset convergence condition is reached to obtain a final resource allocation decision.

[0084] Among them, the iterative update process of the resource allocation decision includes: constructing a utility function according to the target service satisfaction, the target weight factor and the resource allocation decision; giving the initial value of the resource allocation decision as the current resource allocation decision, and determining the gradient vector corresponding to the utility function under the current resource allocation decision; calculating the search direction of the current resource allocation decision according to the Hessian matrix and the gradient vector; updating the current resource allocation decision using the search direction and the preset update step size; when it is judged that the difference between the updated resource allocation decision and the current resource allocation decision is less than the convergence threshold, it is judged that the preset convergence condition is reached, and the updated resource allocation decision is determined as the final resource allocation decision; when it is judged that the difference between the updated resource allocation decision and the current resource allocation decision is greater than or equal to the convergence threshold, the updated resource allocation decision is used as the current resource allocation decision, and the above-mentioned update process of the current resource allocation decision is repeated.

[0085] Accordingly, when the current resource allocation decision is updated using the search direction and the preset update step, the embodiment steps may include: calculating the product of the search direction and the preset update step; adding the product to the current resource allocation decision as the updated resource allocation decision. The resource allocation decision may be the amount of resources allocated to the target vehicle. For example, if the updated resource allocation decision is 10, 10 GHz of computing resources may be allocated to the target vehicle.

[0086] In summary, the technical solution in this application analyzes the dynamically changing resource status of the vehicle-mounted edge server and the service requirements of the user in edge computing, and dynamically adjusts the computing resource allocation decision of the vehicle-mounted edge server. The algorithm can flexibly respond to different resource requirements and network conditions. Traditional static resource allocation algorithms often allocate resources based on predefined strategies, which is difficult to respond to changes in network load or computing requirements in real time. The dynamically adjusted algorithm can intelligently adjust the resource allocation strategy according to factors such as current resource usage, task complexity, network bandwidth, and delay, thereby avoiding resource waste and task delays. Secondly, the dynamically adjusted algorithm can effectively improve resource utilization. When resources are limited, a reasonable dynamic allocation strategy can ensure that each task can be allocated the most appropriate computing resources according to its priority and needs. For example, when the urgency of the task is high, the system can allocate more computing resources to it to speed up the processing speed; in the case of non-urgent tasks, the allocation of resources can be reduced to reserve more resources for other tasks. Through this dynamic optimization of resources, the processing efficiency of the entire system can be significantly improved. In addition, the dynamic adjustment algorithm is also adaptive and robust. When the resource environment changes suddenly, such as a sudden failure of an edge server or a significant increase in network latency, the system can quickly make adjustments and reallocate tasks and resources to avoid system crashes caused by single point failures or resource bottlenecks. Such a dynamic adjustment mechanism can ensure that the system has stronger response capabilities and stability in complex practical application scenarios. In general, the decision algorithm for dynamically adjusting computing resource allocation can intelligently optimize resource allocation and flexibly respond to changes in tasks and network environments, which not only improves the system's resource utilization and task processing efficiency, but also enhances the system's robustness and stability. The successful application of this algorithm not only provides an important reference for the design of future intelligent computing systems, but also plays a positive role in task scheduling and optimization in edge computing environments with limited resources.

[0087] Based on the above Figure 2 , Figure 3 A detailed description of the computing resource allocation method of the vehicle-mounted edge server is provided, such as Figure 4 As shown, Figure 4 FIG. 1 is a structural block diagram of a computing resource allocation device for a vehicle-mounted edge server according to an exemplary embodiment. Figure 4 As shown, the device comprises: The receiving module 41 may be used to receive a resource allocation request sent by a target vehicle, the resource allocation request carries the resource demand of the target vehicle, and the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server; An acquisition module 42, which can be used to respond to the resource allocation request and obtain service resource information and service satisfaction information of the vehicle-mounted edge server in real time, wherein the service resource information includes the upper limit of computing resources, the total amount of allocated resources, and the average amount of allocated resources of the vehicle-mounted edge server, and the service satisfaction information includes the average satisfaction of the first service of the deployed service instance; An updating module 43 may be used to determine a target weight factor of a target service satisfaction level of a target vehicle according to the service resource information and service satisfaction level information of the vehicle-mounted edge server; The generation module 44 may be used to generate a resource allocation decision based on the target service satisfaction and the target weight factor, and allocate corresponding computing resources to the target vehicle according to the resource allocation decision.

[0088] In some embodiments of the present application, Figure 5 As shown, the device further includes: a determination module 45 and a calculation module 46; A determination module 45 may be used to determine a first service delay for each deployed service instance on the vehicle edge server, where the first service delay is the sum of an uplink transmission delay, a calculation delay, and a downlink transmission delay corresponding to each deployed service instance; A calculation module 46, which can be used to calculate the service satisfaction of each deployed service instance based on the first service delay; The calculation module 46 may also be used to calculate an average of service satisfaction of deployed service instances to obtain a first service average satisfaction.

[0089] In some embodiments of the present application, when determining the target weight factor of the target service satisfaction of the target vehicle based on the service resource information and service satisfaction information of the vehicle edge server, the update module 43 can be specifically used to obtain the target weight factor of the target service satisfaction of the target vehicle; based on the first service average satisfaction, service resource information, resource shortage threshold and resource idle threshold, determine whether the resource status of the vehicle edge server needs to be adjusted; when it is determined that the resource status of the vehicle edge server does not need to be adjusted, keep the target weight factor unchanged; when it is determined that the resource status of the vehicle edge server needs to be adjusted, dynamically update the target weight factor of the service satisfaction in the calculation resource allocation.

[0090] In some embodiments of the present application, when it is determined that the resource status of the vehicle edge server needs to be adjusted, when the target weight factor of the service satisfaction in the computing resource allocation is dynamically updated, the update module 43 can be specifically used to reduce the target weight factor of the service satisfaction in the computing resource allocation based on the preset incremental value when the resource status of the vehicle edge server is determined to be a resource-constrained state, until it is determined that the first service satisfaction improvement condition is met, and the updated target weight factor is obtained, wherein the first service satisfaction improvement condition is that the updated target weight factor is greater than 0, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to the service satisfaction threshold; when it is determined that the resource status of the vehicle edge server is a resource-sufficient state and the first service average satisfaction is insufficient, the target weight factor of the service satisfaction in the computing resource allocation is increased based on the preset incremental value until it is determined that the second service satisfaction improvement condition is met, and the updated target weight factor is obtained, wherein the second service satisfaction improvement condition is that the updated target weight factor is less than or equal to 1, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to the service satisfaction threshold.

[0091] In some embodiments of the present application, when the target weight factor of service satisfaction in computing resource allocation is reduced based on a preset incremental value until it is determined that the first service satisfaction improvement condition is met and an updated target weight factor is obtained, the update module 43 can be specifically used to iteratively perform the following target weight factor reduction operation until it is determined that the first service satisfaction improvement condition is met and an updated target weight factor is obtained; wherein, the target weight factor reduction operation includes: taking the difference between the current target weight factor and the preset incremental value as the updated target weight factor; if it is determined that the updated target weight factor is greater than 0, reallocating computing resources for the deployed service instances based on the updated target weight factor, and calculating the second service average satisfaction of the deployed service instances after the computing resources are reallocated; when it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, taking the updated target weight factor as the current target weight factor, and repeatedly performing the reduction operation on the current target weight factor; when it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, determining that the first service satisfaction improvement condition is met and obtaining the final updated target weight factor.

[0092] In some embodiments of the present application, when the target weight factor of service satisfaction in computing resource allocation is increased based on a preset incremental value until it is determined that the second service satisfaction improvement condition is met and an updated target weight factor is obtained, the update module 43 iteratively performs the following target weight factor increase operation until it is determined that the second service satisfaction improvement condition is met and an updated target weight factor is obtained; wherein the target weight factor increase operation includes: taking the sum of the current target weight factor and the preset incremental value as the updated target weight factor; if it is determined that the updated target weight factor is less than or equal to 1, then reallocating computing resources for the deployed service instances based on the updated target weight factor, and calculating the second service average satisfaction of the deployed service instances after the computing resources are reallocated; when it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, then taking the updated target weight factor as the current target weight factor, and repeatedly performing the increase operation on the current target weight factor; when it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the second service satisfaction improvement condition is met and the final updated target weight factor is obtained.

[0093] In some embodiments of the present application, the calculation module 46 can also be used to obtain the second service delay of the target vehicle, where the second service delay is the sum of the uplink transmission delay, calculation delay and downlink transmission delay of the target vehicle; and the target service satisfaction is calculated based on the second service delay and the second service delay threshold.

[0094] In some embodiments of the present application, when a resource allocation decision is generated based on the target service satisfaction and the target weight factor, the generation module 44 can be specifically used to repeatedly execute the following iterative update process of the resource allocation decision until a preset convergence condition is reached to obtain a final resource allocation decision; wherein, the iterative update process of the resource allocation decision includes: constructing a utility function according to the target service satisfaction, the target weight factor and the resource allocation decision; given an initial value of the resource allocation decision as the current resource allocation decision, determining a gradient vector corresponding to the utility function under the current resource allocation decision; calculating a search direction of the current resource allocation decision according to the Hessian matrix and the gradient vector; updating the current resource allocation decision using the search direction and the preset update step size; when it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is less than a convergence threshold, it is determined that the preset convergence condition is reached, and the updated resource allocation decision is determined as the final resource allocation decision; when it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is greater than or equal to the convergence threshold, the updated resource allocation decision is used as the current resource allocation decision, and the above-mentioned update process of the current resource allocation decision is repeatedly executed.

[0095] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0096] The embodiments of the present application can analyze the dynamically changing resource status of the server in edge computing and the service requirements of the user, and dynamically adjust the computing resource allocation decision of the server. The algorithm can flexibly respond to different resource requirements and network conditions. Traditional static resource allocation algorithms often allocate resources based on predefined strategies, which is difficult to respond to changes in network load or computing requirements in real time. The dynamically adjusted algorithm can intelligently adjust the resource allocation strategy according to factors such as current resource usage, task complexity, network bandwidth, and delay, thereby avoiding resource waste and task delay. For example, when the network bandwidth is sufficient, the system can choose to transfer more tasks to the cloud for processing; when the bandwidth is limited, it can give priority to processing on the edge device, thereby reducing the delay in data transmission. Secondly, the dynamically adjusted algorithm can effectively improve the utilization of resources. In the case of limited resources, a reasonable dynamic allocation strategy can ensure that each task can be allocated the most appropriate computing resources according to its priority and needs. For example, when the urgency of the task is high, the system can allocate more computing resources to it to speed up the processing speed; in the case of non-urgent tasks, the allocation of resources can be reduced to reserve more resources for other tasks. Through this dynamic optimization of resources, the processing efficiency of the entire system can be significantly improved. In addition, the dynamic adjustment algorithm is also adaptive and robust. When the resource environment changes suddenly, such as a sudden failure of an edge server or a significant increase in network latency, the system can quickly make adjustments and reallocate tasks and resources to avoid system crashes caused by single point failures or resource bottlenecks. Such a dynamic adjustment mechanism can ensure that the system has stronger response capabilities and stability in complex practical application scenarios. In general, the decision algorithm for dynamically adjusting computing resource allocation can intelligently optimize resource allocation and flexibly respond to changes in tasks and network environments, which not only improves the system's resource utilization and task processing efficiency, but also enhances the system's robustness and stability. The successful application of this algorithm not only provides an important reference for the design of future intelligent computing systems, but also plays a positive role in task scheduling and optimization in resource-limited edge computing environments.

[0097] In the above, the computing resource allocation device of the vehicle-mounted edge server of the embodiment of the present invention is described from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the computing resource allocation method embodiment of the vehicle-mounted edge server in the embodiment of the present invention can be completed by the hardware integrated logic circuit and / or software instructions in the processor, and the steps of the computing resource allocation method of the vehicle-mounted edge server applied in conjunction with the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or a combination of hardware and software modules in the decoding processor to execute. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps in the computing resource allocation method embodiment of the above-mentioned vehicle-mounted edge server in combination with its hardware.

[0098] Figure 6 is a schematic block diagram of an electronic device 600 according to an embodiment of the present invention.

[0099] like Figure 6 As shown, the electronic device 600 may include: The memory 610 and the processor 620, the memory 610 is used to store the computer program and transmit the program code to the processor 620. In other words, the processor 620 can call and run the computer program from the memory 610 to implement the method in the embodiment of the present invention.

[0100] For example, the processor 620 may be configured to execute the above method embodiments according to instructions in the computer program.

[0101] In some embodiments of the present invention, the processor 620 may include but is not limited to: General-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0102] In some embodiments of the present invention, the memory 610 includes but is not limited to: Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus random access memory (Direct Rambus RAM, DR RAM).

[0103] In some embodiments of the present invention, the computer program may be divided into one or more modules, which are stored in the memory 610 and executed by the processor 620 to complete the method provided by the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the controller.

[0104] like Figure 6 As shown, the electronic device 600 may further include: The transceiver 630 may be connected to the processor 620 or the memory 610 .

[0105] The processor 620 may control the transceiver 630 to communicate with other devices, specifically, to send data to other devices or receive data sent by other devices. The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of antennas may be one or more.

[0106] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0107] The present invention also provides a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the method of the above method embodiment. In other words, an embodiment of the present invention also provides a computer program product containing instructions, which, when executed by a computer, enables the computer to perform the method of the above method embodiment.

[0108] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (Digital Video Disc, DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0109] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments applied herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0110] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0111] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0112] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this application, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for allocating computing resources of a vehicle-mounted edge server, characterized in that: include: Receive a resource allocation request sent by a target vehicle, where the resource allocation request is used to request allocation of computing resources in a vehicle-mounted edge server; In response to the resource allocation request, obtaining service resource information and service satisfaction information of the vehicle-mounted edge server in real time, the service resource information including the upper limit of computing resources, the total amount of allocated resources, and the average amount of allocated resources of the vehicle-mounted edge server, and the service satisfaction information including the average satisfaction of the first service of the deployed service instance; Determining a target weight factor of a target service satisfaction level of the target vehicle according to the service resource information and the service satisfaction level information of the vehicle-mounted edge server; A resource allocation decision is generated based on the target service satisfaction and the target weight factor, and corresponding computing resources are allocated to the target vehicle according to the resource allocation decision.

2. The method according to claim 1, characterized in that Before obtaining the service resource information and service satisfaction information of the vehicle-mounted edge server in real time in response to the resource allocation request, the method further includes: Determine a first service delay for each deployed service instance on the vehicle-mounted edge server, where the first service delay is the sum of an uplink transmission delay, a calculation delay, and a downlink transmission delay corresponding to each of the deployed service instances; Calculating the service satisfaction of each of the deployed service instances based on the first service delay; An average of the deployed service instances with respect to the service satisfaction is calculated to obtain the first service average satisfaction.

3. The method according to claim 1, characterized in that Determining a target weight factor of a target service satisfaction level of a target vehicle according to the service resource information and the service satisfaction level information of the vehicle-mounted edge server includes: Obtaining a target weight factor of a target service satisfaction level of the target vehicle; Based on the first service average satisfaction, the service resource information, the resource shortage threshold, and the resource idle threshold, determining whether the resource status of the vehicle-mounted edge server needs to be adjusted; When it is determined that the resource status of the vehicle-mounted edge server does not need to be adjusted, keeping the target weight factor unchanged; When it is determined that the resource status of the vehicle-mounted edge server needs to be adjusted, the target weight factor of the service satisfaction in the resource allocation calculation is dynamically updated.

4. The method according to claim 3, characterized in that When it is determined that the resource status of the vehicle-mounted edge server needs to be adjusted, dynamically updating the target weight factor of the service satisfaction in the resource allocation calculation includes: When it is determined that the resource state of the vehicle-mounted edge server is a resource-constrained state, the target weight factor of the service satisfaction in the computing resource allocation is reduced based on a preset incremental value until it is determined that a first service satisfaction improvement condition is met, and an updated target weight factor is obtained, wherein the first service satisfaction improvement condition is that the updated target weight factor is greater than 0, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to a service satisfaction threshold; When it is judged that the resource status of the on-board edge server is a sufficient resource status and the first service average satisfaction is insufficient, the target weight factor of the service satisfaction in the computing resource allocation is increased based on the preset incremental value until it is judged that the second service satisfaction improvement condition is met, and an updated target weight factor is obtained, wherein the second service satisfaction improvement condition is that the updated target weight factor is less than or equal to 1, and the difference between the second service average satisfaction corresponding to the updated target weight factor and the first service average satisfaction is greater than or equal to the service satisfaction threshold.

5. The method according to claim 4, characterized in that The step of reducing the target weight factor of the service satisfaction in the computing resource allocation based on the preset incremental value until it is determined that the first service satisfaction improvement condition is met to obtain an updated target weight factor includes: Iteratively perform the following target weight factor reduction operation until it is determined that the first service satisfaction improvement condition is met, and obtain an updated target weight factor; The operation of reducing the target weight factor includes: The difference between the current target weight factor and the preset increment value is used as the updated target weight factor; If it is determined that the updated target weight factor is greater than 0, reallocating computing resources for the deployed service instance based on the updated target weight factor, and calculating the second service average satisfaction of the deployed service instance after the computing resources are reallocated; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, the updated target weight factor is used as the current target weight factor, and the operation of reducing the current target weight factor is repeatedly performed; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the first service satisfaction improvement condition is met, and a final updated target weight factor is obtained; And / or, increasing the target weight factor of the service satisfaction in the computing resource allocation based on the preset increment value until it is determined that the second service satisfaction improvement condition is met to obtain an updated target weight factor, including: Iteratively perform the following target weight factor increase operation until it is determined that the second service satisfaction improvement condition is met, and obtain an updated target weight factor; The operation of increasing the target weight factor includes: The sum of the current target weight factor and the preset increment value is used as the updated target weight factor; If it is determined that the updated target weight factor is less than or equal to 1, reallocate computing resources for the deployed service instance based on the updated target weight factor, and calculate the second service average satisfaction of the deployed service instance after the computing resources are reallocated; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is less than the service satisfaction threshold, the updated target weight factor is used as the current target weight factor, and the operation of increasing the current target weight factor is repeatedly performed; When it is determined that the difference between the second service average satisfaction and the first service average satisfaction is greater than or equal to the service satisfaction threshold, it is determined that the second service satisfaction improvement condition is met, and the final updated target weight factor is obtained.

6. The method according to claim 1, characterized in that Before generating a resource allocation decision based on the target service satisfaction and the target weight factor, the method further includes: Obtaining a second service delay of the target vehicle, where the second service delay is the sum of an uplink transmission delay, a calculation delay, and a downlink transmission delay of the target vehicle; The target service satisfaction level is calculated according to the second service delay and the second service delay threshold.

7. The method according to claim 1, characterized in that The generating a resource allocation decision based on the target service satisfaction and the target weight factor comprises: Repeat the following iterative update process of the resource allocation decision until a preset convergence condition is reached to obtain a final resource allocation decision; The iterative update process of the resource allocation decision includes: constructing a utility function according to the target service satisfaction, the target weight factor, and the resource allocation decision; Given the initial value of the resource allocation decision as the current resource allocation decision, determining the gradient vector corresponding to the utility function under the current resource allocation decision; Calculate the search direction of the current resource allocation decision according to the Hessian matrix and the gradient vector; Updating the current resource allocation decision using the search direction and a preset update step size; When it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is greater than or equal to the convergence threshold, the updated resource allocation decision is used as the current resource allocation decision, and the above-mentioned updating process of the current resource allocation decision is repeatedly executed; When it is determined that the difference between the updated resource allocation decision and the current resource allocation decision is less than the convergence threshold, it is determined that the preset convergence condition is met, and the updated resource allocation decision is determined as the final resource allocation decision.

8. A computing resource allocation device for a vehicle-mounted edge server, characterized in that: include: A receiving module, used to receive a resource allocation request sent by a target vehicle, wherein the resource allocation request is used to request allocation of computing resources in the vehicle-mounted edge server; an acquisition module, configured to acquire, in real time, service resource information and service satisfaction information of the vehicle-mounted edge server in response to the resource allocation request, wherein the service resource information includes an upper limit of computing resources, a total amount of allocated resources, and an average amount of allocated resources of the vehicle-mounted edge server, and the service satisfaction information includes an average satisfaction level of a first service of a deployed service instance; An updating module, configured to determine a target weight factor of a target service satisfaction level of the target vehicle according to the service resource information and the service satisfaction level information of the vehicle-mounted edge server; A generation module is used to generate a resource allocation decision based on the target service satisfaction and the target weight factor, and allocate corresponding computing resources to the target vehicle according to the resource allocation decision.

9. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 7.

Images