Edge computing optimization control system and method based on cloud edge collaboration

Abstract

The invention relates to the technical field of power dispatching, in particular to an edge computing optimization control system and method based on cloud edge collaboration, and the system comprises a data collection and preprocessing module, an edge computing module, an intelligent resource optimization distribution module, a cloud edge collaboration control module, an application service module and a security and privacy protection module. According to the intelligent resource optimization distribution module, calculation tasks and storage resources are reasonably distributed, data transmission delay is reduced, the real-time response capacity is improved, and therefore the processing performance of the edge calculation module is enhanced, and the intelligent resource optimization distribution module can adapt to rapid changes of the frequency of a power grid and dynamic changes of the state of an energy storage system; meanwhile, the module reduces the data transmission quantity between the cloud platform and the edge node through optimizing the resource allocation, reduces the network bandwidth demand, and saves the communication cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power dispatching, and is an edge computing optimization control system based on cloud-edge collaboration, and also includes a control method. BACKGROUND

[0002] With the transformation of global energy structure and the rapid development of clean energy, the proportion of new energy in the power system is gradually increasing. However, new energy such as wind energy and solar energy has the characteristics of randomness and volatility, which brings challenges to the frequency stability of the power grid. In order to solve this problem, energy storage systems are introduced into the power system to smooth the fluctuations of new energy and stabilize the frequency of the power grid.

[0003] However, the existing frequency regulation control technology of energy storage systems mainly relies on preset control strategies, which often cannot adapt to the rapid changes of the grid frequency and the dynamic changes of the energy storage system state, resulting in poor frequency regulation effect, low utilization rate of energy storage systems, and other problems. In addition, the existing control system also has deficiencies in data processing, communication monitoring and safety protection, and is difficult to meet the efficient, intelligent and safe operation requirements of the power grid.

[0004] The patent application document with publication number CN120614354A proposes a cloud-edge collaborative management method based on edge computing. The method marks the data of the same project as target data, divides the time period and determines the receiving node, transmits the data to all receiving nodes, and then selects the standard node for storage according to the integrity score of the sub-period, thereby improving the storage and processing efficiency of cloud-edge collaboration.

[0005] The patent application document with publication number CN119152690A proposes an edge computing cloud-edge collaboration method, system and device, which includes acquiring real-time monitoring videos shot by AI cameras in each target area, and dividing them into effective video segments and ineffective video segments, dividing the effective video segments into explicit clear frame groups and implicit clear frame groups according to the definition, and determining the method of obtaining target information according to the clear frame group category, the edge filtering module receives the target information of the explicit clear frame group and the clear enhancement frame group, determines all target information of a single effective video segment according to the time sequence relationship, and filters the effective target information. According to the effective target information, determine the traffic information of each time period. SUMMARY

[0006] The present application provides an edge computing optimization control system and method based on cloud-edge collaboration, which can effectively solve the problem that the control strategy of the energy storage system cannot adapt to the rapid changes of the grid frequency and the dynamic changes of the energy storage system state, resulting in poor frequency regulation effect and low utilization rate of the energy storage system.

[0007] One of the technical solutions of the present application is realized by the following measures: an edge computing optimization control system based on cloud edge collaboration, comprising: a data acquisition and preprocessing module: collecting raw data, the raw data including real-time power consumption data of a smart meter, temperature data of a transformer and load conditions of a power grid, preprocessing the raw data, the preprocessing including data cleaning, data normalization and data dimensionality reduction, and transmitting the preprocessed data to an edge computing module; an edge computing module: receiving the preprocessed data, performing data processing on the preprocessed data, analyzing to obtain task execution data and resource usage, and sending the task execution data, resource usage and service performance to an intelligent resource optimization allocation module; an intelligent resource optimization allocation module: in-depth analysis and prediction of the received data, formulating a resource optimization allocation strategy according to the analysis and prediction results, and allocating resources according to the resource optimization allocation strategy, and feeding back the resource allocation results to the edge computing module; a cloud edge collaboration control module: receiving resource allocation instructions from the intelligent resource optimization allocation module, and managing task allocation and resource scheduling between the cloud computing platform and the edge device according to the resource allocation instructions; an application service module: providing various application services for terminal users, conveying service requirements to the intelligent resource optimization allocation module, and receiving resource allocation results to optimize services; a security and privacy protection module: ensuring data security and user privacy throughout the process, and working with the intelligent resource optimization allocation module to ensure the safety of resource allocation and data processing.

[0008] The following is a further optimization or / and improvement of one of the above-mentioned technical solutions of the present application: Further, the above-mentioned intelligent resource optimization allocation module comprises: a data collection sub-module: receiving task execution data, resource usage and service performance, the task execution data including task type, data volume and processing time; a data analysis and prediction sub-module: denoising, filling missing values and standardizing preprocessing of task execution data and resource usage data, extracting features that have important influence on resource allocation from the preprocessed data, the features that have important influence on resource allocation including task type, data volume and processing time, training a linear regression model using historical resource allocation and the features that have important influence on resource allocation, and predicting resource demand in a future period of time according to the linear regression model; a resource evaluation and modeling sub-module: using an integer linear programming algorithm to comprehensively evaluate, model and analyze edge computing resources, with the goal of maximizing the total benefit of resource allocation; Optimization strategy generation submodule: determine the optimal resource allocation strategy by searching for the optimal solution; Resource scheduling and allocation submodule: according to the optimal resource allocation strategy output by the optimization strategy generation submodule, perform resource scheduling and allocation operations.

[0009] Further, in the above data analysis and prediction submodule, the linear regression model is as follows: In the formula, y represents the prediction target; x1, x2, …, x n represent feature variables; β0, β1, …, β n represent regression coefficients; and ϵ represents an error term, representing random factors that the model cannot explain.

[0010] Further, in the above resource evaluation and modeling submodule, the total benefit of resource allocation is maximized as the target, and the objective function calculation formula is: The constraint conditions of the objective function are: a11x1+a12x2+…+a1nxn≤b1; a21x1+a22x2+…+a2nxn≤b2; ⋮ am1x1+am2x2+…+amnxn≤bm; xi∈{0,1},i=1,2,…,n Where: Z represents the objective function value, representing the total benefit of resource allocation; c1, c2, …, cn represent the benefit coefficients of resource allocation, representing the benefits brought by allocating different resources; x1, x2, …, xn represent decision variables, representing whether to allocate a certain resource, taking values of 0 or 1; aij represents the resource demand coefficient, representing the demand amount of the jth task for the ith resource; b1, b2, …, bm represent resource capacity constraints, i.e., the maximum available amount of each resource.

[0011] Further, in the above resource evaluation and modeling submodule, comprehensive resource evaluation, modeling and analysis are performed on edge computing resources, including: Resource evaluation: real-time evaluation of the computing power, storage capacity, network bandwidth and other resources of edge devices; Analysis: analyze the resource demand of different tasks, including computing demand, storage demand and network demand; Modeling: establish a resource allocation model to simulate system performance and resource utilization under different resource allocation strategies;

[0012] Further, in the optimization strategy generation submodule, the optimal solution is searched through a genetic algorithm to determine the optimal resource allocation strategy, and the following contents are run: Strategy definition: define the resource allocation strategy, including resource allocation mode, allocation ratio, priority setting; Target setting: set the optimization target according to the system target, and the optimization target is one or more of minimizing task delay, maximizing resource utilization, and balancing load; Strategy evaluation: evaluate the system performance under different strategies, including task completion time, resource waste, and service satisfaction; Strategy optimization: find the optimal resource allocation strategy using optimization algorithms.

[0013] The second technical solution of the application is realized by the following measures: a control method, comprising: collecting original data, and pre-processing the original data; Receiving pre-processed data, performing data processing and analysis on the pre-processed data to obtain task execution data and resource usage; In-depth analysis and prediction are performed on the task execution data, resource usage and service performance data, and a resource optimization allocation strategy is formulated according to the analysis and prediction results, and resource allocation is performed according to the resource optimization allocation strategy; According to the resource allocation instruction, the task allocation and resource scheduling between the cloud computing platform and the edge device are managed.

[0014] The application can solve the following problems: 1) The existing edge computing system usually adopts static or simple round-robin resource allocation strategy, which cannot be dynamically adjusted according to the real-time changes of computing task load, data traffic and edge node resource state. This leads to resource bottleneck and task delay at high load, and resource idling and waste at low load. The application realizes the elastic allocation of computing, storage and network resources through the intelligent resource optimization allocation module, which collects task demand and resource state data in real time and dynamically generates and executes resource scheduling strategy using optimization algorithms, significantly improves the resource utilization efficiency and the response ability to dynamic business demand. Solve the problem of rigid resource allocation that is difficult to meet dynamic demand.

[0015] 2) Existing systems often regard cloud computing and edge computing as independent levels, lacking effective coordination mechanisms. This leads to the inability of the powerful global optimization and analysis capabilities of the cloud to be organically combined with the agile local response capabilities of the edge, making it difficult to achieve the overall performance optimization of the system. The cloud-edge coordination control module of the present application establishes a collaborative working mechanism between the cloud and the edge in terms of task offloading, data synchronization, resource scheduling, etc. so that complex analysis tasks can be uploaded to the cloud and real-time response tasks can be performed at the edge, fully utilizing the synergistic advantages of cloud-edge integration and improving the overall efficiency of the system. The problem of insufficient system coordination and the inability to fully utilize the advantages of cloud-edge is solved.

[0016] 3) Existing resource allocation methods mostly focus on a single objective (such as minimizing delay), and the optimization algorithms used (such as simple linear programming) have limited processing capabilities for complex optimization problems with multiple constraints and multiple objectives (such as considering delay, energy consumption, cost, and load balancing) in edge environments, easily falling into local optimization. In the intelligent resource optimization and allocation module of the present application, advanced intelligent optimization algorithms such as genetic algorithms are introduced, which can effectively handle non-linear, high-dimensional multi-objective optimization problems, thereby generating resource allocation schemes that achieve a better balance between multiple performance indicators. The problem of single optimization algorithm and difficulty in handling complex multi-objective optimization is solved.

[0017] 4) Traditional models that rely on centralized processing in the cloud result in long data transmission distances, leading to large loop delays in data sensing, decision-making, and control, making it difficult to meet the stringent real-time requirements of industrial control, smart grids, and other scenarios. The present application enhances the local real-time data processing and analysis capabilities of the edge computing module and combines the near-end fast decision-making of the intelligent resource optimization and allocation module to significantly shorten the response time from data sensing to resource scheduling and control instruction issuance, effectively improving the real-time performance of the system. The problem of data sensing and decision-making lag and weak system real-time performance is solved.

[0018] 5) Edge computing nodes are widely distributed and have complex environments, making them more susceptible to security attacks, and involve a large amount of user sensitive data (such as electricity consumption behavior). Existing systems lack a unified security and privacy protection design throughout the entire life cycle of data collection, transmission, processing, and storage. The present application, through an independent security and privacy protection module, and in coordination with each module (especially the intelligent resource optimization and allocation module), implements integrated security measures such as data encryption, access control, and security monitoring, providing comprehensive and multi-level security protection for the system. The problem of imperfect system security and privacy protection mechanism is solved.

[0019] The beneficial effects of the present application are: In this invention, the intelligent resource optimization and allocation module plays a crucial role in the system. Its internal structure includes a resource evaluation submodule, an optimization algorithm submodule, and a decision execution submodule. First, the resource evaluation submodule monitors and analyzes the resource status of edge nodes and the cloud platform in real time, such as computing power, storage space, and network bandwidth, providing accurate basic data for resource optimization. The optimization strategy generation submodule uses a genetic algorithm to formulate the optimal resource allocation strategy based on the resource evaluation results and system requirements. The resource scheduling and allocation submodule is responsible for translating the optimization strategy into actual operation instructions, ensuring the accurate execution of resource allocation. Through the collaborative work of these submodules, the intelligent resource optimization and allocation module significantly improves resource utilization efficiency, reduces resource waste, and ensures stable system operation under high load conditions.

[0020] In this invention, the intelligent resource optimization and allocation module reduces data transmission latency and improves real-time response capabilities by rationally allocating computing tasks and storage resources. This enhances the processing performance of the edge computing module, enabling it to adapt to rapid changes in grid frequency and dynamic changes in the energy storage system's state. Simultaneously, by optimizing resource allocation, the module reduces data transmission volume between the cloud platform and edge nodes, lowering network bandwidth requirements and saving communication costs. Furthermore, the intelligent resource optimization and allocation module improves the system's scalability, flexibly addressing application needs of varying scales and complexities.

[0021] In summary, the intelligent resource optimization and allocation module not only improves the overall performance of the cloud-edge collaborative edge computing optimization control system, but also lays a solid foundation for the sustainable development of the system. Attached Figure Description

[0022] Appendix Figure 1 A flowchart of an edge computing-optimized control system based on cloud-edge collaboration.

[0023] Appendix Figure 2 A diagram showing the components of the intelligent resource optimization and allocation module. Detailed Implementation

[0024] The present invention is not limited to the following embodiments, and the specific implementation can be determined according to the technical solution of the present invention and the actual situation.

[0025] The present invention will be further described below with reference to embodiments: Example 1: As Figure 1 As shown, an edge computing optimization control system based on cloud-edge collaboration includes: Data acquisition and preprocessing module: Collects raw data, including real-time electricity consumption data from smart meters, temperature data from transformers, and load conditions of the power grid. The raw data is preprocessed, including data cleaning, data normalization, and data dimensionality reduction. The preprocessed data is then transmitted to the edge computing module. Edge computing module: Receives pre-processed data, performs data processing and analysis on the pre-processed data to obtain task execution data and resource usage, and sends the task execution data, resource usage and service performance to the intelligent resource optimization and allocation module; Intelligent resource optimization and allocation module: performs in-depth analysis and prediction of received data, formulates resource optimization and allocation strategies based on the analysis and prediction results, allocates resources according to the resource optimization and allocation strategies, and feeds back the resource allocation results to the edge computing module; Cloud-edge collaborative control module: Receives resource allocation instructions from the intelligent resource optimization and allocation module, and manages task allocation and resource scheduling between the cloud computing platform and edge devices according to the resource allocation instructions; Application Service Module: Provides various application services to end users, transmits service requests to the Intelligent Resource Optimization and Allocation Module, and receives resource allocation results to optimize services; Security and Privacy Protection Module: Ensures data security and user privacy throughout the entire process. It works in conjunction with the security and privacy management sub-module of the intelligent resource optimization and allocation module to ensure the security of resource allocation and data processing.

[0026] Example 2: As Figure 2 As shown, the intelligent resource optimization and allocation module includes: Data collection submodule: Receives task execution data, resource usage, and service performance. Task execution data includes task type, data volume, and processing time. Resource usage data includes historical load data and meteorological data, with the meteorological data including temperature, humidity, and time.

[0027] The data analysis and prediction submodule performs noise reduction, missing value filling, and standardization preprocessing on task execution data and resource usage data. It extracts features that have a significant impact on resource allocation from the preprocessed data, including task type, data volume, and processing time. It trains a linear regression model using historical resource allocation data and features that have a significant impact on resource allocation, and predicts resource demand in the future based on the linear regression model. The linear regression model can also be used to predict task load.

[0028] The resource evaluation and modeling submodule uses an integer linear programming algorithm to comprehensively evaluate, model, and analyze edge computing resources, aiming to maximize the total benefit of resource allocation, to achieve accurate allocation and efficient use of resources. The optimization strategy generation submodule determines the optimal resource allocation strategy by searching for the optimal solution. The resource scheduling and allocation submodule executes scheduling and allocation operations of resources according to the optimal resource allocation strategy output by the optimization strategy generation submodule, ensuring that resources can be efficiently and accurately allocated to each task according to the strategy.

[0029] In embodiment 3, as an optimization of embodiment 2, the linear regression model is as follows: In the formula, y represents the prediction target, such as resource demand.

[0030] x1, x2, …, x n represent feature variables, such as task type, data volume, etc.

[0031] β0, β1, …, β n represent regression coefficients, indicating the influence of feature variables on the prediction target.

[0032] ϵ represents the error term, representing random factors that the model cannot explain.

[0033] In embodiment 4, as an optimization of embodiment 2, in the resource evaluation and modeling submodule, the target function calculation formula is as follows: The constraint conditions of the target function are as follows: a11x1+a12x2+…+a1nxn≤b1; a21x1+a22x2+…+a2nxn≤b2; ⋮ am1x1+am2x2+…+amnxn≤bm; xi∈{0,1},i=1,2,…,n Where: Z represents the target function value, representing the total benefit of resource allocation. c1, c2, …, cn represent the benefit coefficients of resource allocation, representing the benefits brought by allocating different resources. x1, x2, …, xn represent decision variables, representing whether to allocate a certain resource, taking values of 0 or 1. aij represents the resource demand coefficient, representing the demand of the jth task for the ith resource. b1, b2, …, bm represent resource capacity constraints, i.e. the maximum available amount of each resource.

[0034] In the resource assessment and modeling submodule of the above-mentioned embodiment 2, comprehensive resource assessment, modeling and analysis of edge computing resources are performed, including: Resource assessment: real-time assessment of the computing power, storage capacity, network bandwidth and other resources of edge devices to understand the availability and performance of resources; Modeling: building a resource allocation model to simulate system performance and resource utilization under different resource allocation strategies; Optimization suggestions: based on the modeling and analysis results, resource optimization allocation suggestions are proposed to guide the actual resource allocation process.

[0035] In the optimization strategy generation submodule of the above-mentioned embodiment 2, the optimal resource allocation strategy is determined by searching for the optimal solution, including the following steps: Strategy definition: define resource allocation strategies, including resource allocation methods, allocation ratios, and priority settings; Objective setting: set optimization objectives according to system goals, including minimizing task delay, maximizing resource utilization, and balancing load; Strategy evaluation: evaluate system performance under different strategies, including task completion time, resource waste, and service satisfaction; Strategy optimization: use optimization algorithms (such as genetic algorithms) to find the optimal resource allocation strategy.

[0036] The cloud-edge collaborative control module is the "coordinator" of the system, responsible for coordinating the collaborative work between cloud computing resources and edge computing resources. In the smart grid scenario, this module can coordinate the large-scale data processing capability of the cloud and the real-time response capability of the edge to achieve more efficient grid management. For example, when the edge computing module detects abnormal conditions of the power grid, it can upload data to the cloud for in-depth analysis and feedback the analysis results to the edge to adjust the control strategy. The cloud-edge collaborative control module is also responsible for dynamic scheduling and task allocation of resources to ensure that computing resources are fully utilized.

[0037] The application service module is the "interface" of the system, responsible for providing various application services to users and receiving service requests from users. In the smart grid scenario, this module can provide power consumption query, fault alarm, energy efficiency analysis and other application services. For example, users can query their real-time power consumption data and historical power consumption records through this module to better manage their power consumption behavior; the system can also send fault alarm information to users through this module to remind them to handle power failures in a timely manner. The application service module is also responsible for converting user requirements into instructions that the system can understand and passing them to the corresponding modules for processing.

[0038] The security and privacy protection module is the "guardian" of the system, responsible for ensuring the security of system data and the protection of user privacy. In the smart grid scenario, this module can encrypt user power consumption data to ensure data security during transmission and storage; it can also implement fine-grained access control policies to ensure that only authorized users and devices can access specific data. In addition, this module is responsible for monitoring security events in the system, such as unauthorized intrusion and data tampering, and issuing alerts in a timely manner. Through these measures, the security and privacy protection module provides comprehensive security protection for the edge computing optimization control system, protecting the data privacy of users and the normal operation of the system.

[0039] The above technical features constitute respective embodiments of the present application, which have strong adaptability and implementation effect. Non-essential technical features can be added or removed according to actual needs to meet different needs.

Claims

1. A cloud edge collaboration based edge computing optimization control system, characterized in that, Comprise: Data acquisition and preprocessing module: collect raw data, preprocess the raw data, and transmit the preprocessed data to the edge computing module; Edge computing module: receiving preprocessed data, performing data processing and analysis on preprocessed data to obtain task execution data and resource usage, and sending task execution data, resource usage and service performance to the intelligent resource optimization allocation module; Intelligent resource optimization allocation module: in-depth analysis and prediction of received data, development of resource optimization allocation strategy based on analysis and prediction results, and resource allocation based on the resource optimization allocation strategy; Cloud edge collaborative control module: receiving resource allocation instructions from the intelligent resource optimization allocation module, managing task allocation and resource scheduling between the cloud computing platform and the edge device according to the resource allocation instructions; Application service module: providing various application services for terminal users, conveying service requirements to the intelligent resource optimization allocation module, and receiving resource allocation results to optimize services; Safety and privacy protection module: ensuring data security and user privacy throughout the process, and working with the intelligent resource optimization allocation module to ensure the safety of resource allocation and data processing. 2.The cloud-edge collaboration based edge computing optimization control system of claim 1, wherein, Intelligent resource optimization allocation module comprises: Data collection sub-module: receiving task execution data, resource usage and service performance, task execution data including task type, data volume and processing time; Data analysis and prediction sub-module: denoising, missing value filling and standardization preprocessing of task execution data and resource usage data, extracting features that have important influence on resource allocation from preprocessed data, including task type, data volume and processing time, training linear regression model using historical resource allocation and features that have important influence on resource allocation, and predicting resource demand in future period according to linear regression model; Resource evaluation and modeling sub-module: comprehensive resource evaluation, modeling and analysis of edge computing resources, with the goal of maximizing the total benefit of resource allocation; Optimization strategy generation sub-module: searching for optimal solution by genetic algorithm to determine optimal resource allocation strategy; Resource scheduling and allocation sub-module: performing resource scheduling and allocation operation according to optimal resource allocation strategy output by optimization strategy generation sub-module. 3.The cloud-edge collaboration based edge computing optimization control system of claim 2, wherein, In the data analysis and prediction sub-module, the linear regression model is as follows: In the formula, y represents a prediction target; x1, x2, …, x n represent feature variables; β0, β1, …, β n denotes the regression coefficients; and e denotes the error term. 4.The cloud-edge collaboration based edge computing optimization control system according to claim 2 or 3, characterized in that, In the resource evaluation and modeling sub-module, the goal is to maximize the total benefit of resource allocation, and the objective function calculation formula is: The constraint conditions of the objective function are: a11x1+a12x2+…+a1nxn≤b1; a21x1+a22x2+…+a2nxn≤b2; ⋮ am1x1+am2x2+…+amnxn≤bm; xi∈{0,1},i=1,2,…,n Where: Z represents the value of the objective function, which represents the total benefit of resource allocation; c1, c2, …, cn represent the benefit coefficients of resource allocation; x1, x2, …, xn represent decision variables; aij represents resource demand coefficient; b1, b2, …, bm represent resource capacity constraints. 5.The cloud-edge collaboration based edge computing optimization control system according to claim 2 or 3, characterized in that, In the resource assessment and modeling submodule, comprehensive resource assessment, modeling, and analysis of edge computing resources are performed, including: Resource assessment: Real-time assessment of edge device computing power, storage capacity, network bandwidth, and other resources; Analysis: Analysis of resource requirements for different tasks, including computing requirements, storage requirements, and network requirements; Modeling: Establishing a resource allocation model to simulate system performance and resource utilization under different resource allocation strategies; Optimization suggestions: Based on modeling and analysis results, resource optimization allocation suggestions are proposed to guide the actual resource allocation process. 6.The cloud-edge collaboration based edge computing optimization control system of claim 4, wherein, In the resource assessment and modeling submodule, comprehensive resource assessment, modeling, and analysis of edge computing resources are performed, including: Resource assessment: Real-time assessment of edge device computing power, storage capacity, network bandwidth, and other resources; Analysis: Analysis of resource requirements for different tasks, including computing requirements, storage requirements, and network requirements; Modeling: Establishing a resource allocation model to simulate system performance and resource utilization under different resource allocation strategies; 7. The cloud-edge collaboration based edge computing optimization control system according to claim 2 or 3 or 6, characterized in that, Optimization suggestions: Based on modeling and analysis results, resource optimization allocation suggestions are proposed to guide the actual resource allocation process. In the optimization strategy generation submodule, the optimal solution is searched through genetic algorithm to determine the optimal resource allocation strategy, with the following steps: Strategy definition: Define resource allocation strategies, including resource allocation methods, allocation ratios, and priority settings; Objective setting: Set optimization objectives according to system goals, including minimizing task delay, maximizing resource utilization, and balancing load; Strategy evaluation: Evaluate system performance under different strategies, including task completion time, resource waste, and service satisfaction; 8.The cloud-edge collaboration based edge computing optimization control system of claim 4, wherein, Strategy optimization: Use genetic algorithm to find the optimal resource allocation strategy. In the optimization strategy generation submodule, the optimal solution is searched through genetic algorithm to determine the optimal resource allocation strategy, with the following steps: Strategy definition: Define resource allocation strategies, including resource allocation methods, allocation ratios, and priority settings; Objective setting: Set optimization objectives according to system goals, including minimizing task delay, maximizing resource utilization, and balancing load; Strategy evaluation: Evaluate system performance under different strategies, including task completion time, resource waste, and service satisfaction; 9.The cloud-edge collaboration based edge computing optimization control system of claim 5, wherein, Strategy optimization: Use genetic algorithm to find the optimal resource allocation strategy. In the optimization strategy generation submodule, the optimal solution is searched through genetic algorithm to determine the optimal resource allocation strategy, with the following steps: Strategy definition: Define resource allocation strategies, including resource allocation methods, allocation ratios, and priority settings; Objective setting: Set optimization objectives according to system goals, including minimizing task delay, maximizing resource utilization, and balancing load; Strategy evaluation: Evaluate system performance under different strategies, including task completion time, resource waste, and service satisfaction; 10. A control method applied to the edge computing optimization control system based on cloud edge collaboration according to any one of claims 1 to 9, characterized in that, Strategy optimization: Use genetic algorithm to find the optimal resource allocation strategy. Including: Collecting raw data, and pre-processing the raw data; Receive the preprocessed data, perform data processing and analysis on the preprocessed data to obtain task execution data and resource usage; In-depth analysis and prediction are performed on the task execution data, resource usage and service performance data, resource optimization allocation strategies are formulated according to the analysis and prediction results, and resource allocation is performed according to the resource optimization allocation strategies; According to the resource allocation instruction, the task allocation and resource scheduling between the cloud computing platform and the edge device are managed.

Images