Power grid edge calculation platform and deployment method

Abstract

The invention relates to the technical field of edge computing platform deployment, and discloses a power grid edge computing platform and a deployment method, and the method comprises the steps: deploying an edge node terminal around power equipment, and marking the edge node terminal as a primary selection position; the edge node terminal collects the operation data of the power equipment at the primary selection position, and analyzes and processes the operation data to obtain processing result data; the execution terminal receives the processing result data and then checks the processing result data to generate feedback data; the cloud platform center receives the processing result data and the feedback data and carries out comprehensive analysis to obtain edge node terminal comprehensive evaluation; and the cloud platform center performs analysis by combining a calculation result of a built-in cost calculation algorithm and comprehensive evaluation of the edge node terminal to obtain a deployment position of the newly selected edge node terminal. According to the invention, comprehensive evaluation and cost calculation of the cloud platform center are carried out in combination with the edge node terminal, the optimal deployment position of the edge node terminal is obtained, and scientific deployment of the edge computing platform is realized.

Description

Technical Field

[0001] The present invention relates to the field of edge computing platform deployment technology, and in particular to a power grid edge computing platform and a deployment method. Background Art

[0002] In the IoT scenario, if the data generated by a large amount of power equipment is transmitted to the cloud for processing, it will cause network congestion and delay problems. Through edge computing, data processing can be performed near the device, reducing the amount of data transmission and delay.

[0003] In addition, many real-time monitoring and control of power grids require rapid response. Edge computing can realize instant data processing and improve the efficiency and safety of production lines. Combining edge computing with containerization technology can achieve rapid response of real-time monitoring and control, which is also a major direction of current power grid development and research. However, the location of edge computing in the power system is currently only set by technical experts or relevant personnel in planning departments based on actual experience, which is subject to subjective influence, is not scientific and rigorous, and cannot achieve optimal deployment of edge devices. Summary of the invention

[0004] In view of the problem that the location of edge computing in the power system in the prior art is subjectively affected and cannot be optimally deployed, the present invention provides a power grid edge computing platform and deployment method, which can comprehensively evaluate the edge node terminals for preliminary deployment and combine the cost calculation of the cloud platform center to obtain the optimal deployment location of the edge node terminals. The specific technical solution is as follows:

[0005] A method for deploying a power grid edge computing platform, comprising:

[0006] The edge node terminals are deployed around the power equipment and marked as the primary locations;

[0007] The edge node terminal collects the operation data of the power equipment at the primary location and performs analysis and processing to obtain the processing result data;

[0008] The execution terminal receives the processing result data, performs verification processing, and generates feedback data;

[0009] The cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal;

[0010] The cloud platform center combines the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to analyze and obtain the deployment location of the newly selected edge node terminal.

[0011] Preferably, a method for deploying a power grid edge computing platform also includes:

[0012] According to the location of the newly selected edge node terminal, the deployment of the power grid edge computing platform is completed.

[0013] Preferably, the edge node terminal collects the operation data of the power equipment at the primary position, and performs analysis and processing to obtain the processing result data including:

[0014] The edge node terminal collects the operating data of the power equipment at the primary location, integrates data processing, fault identification or monitoring algorithms through containerization technology, processes the operating data through the integrated algorithm, and obtains processing result data; the processing result data includes an alarm signal.

[0015] Preferably, the edge node terminal collecting the operating data of the power equipment at the preliminarily selected position includes the edge node terminal collecting the operating data of the power equipment at the preliminarily selected position in a one-to-one or one-to-many manner.

[0016] Preferably, the execution terminal performs verification processing after receiving the processing result data, and generating feedback data includes:

[0017] After receiving the processing result data, the execution terminal compares the key information of the processing result data with the actual inspection result. If they are inconsistent, the difference content is recorded and an error signal is generated. Otherwise, a correct signal is generated.

[0018] Preferably, the cloud platform center analyzes the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal, including:

[0019] The cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost under the edge node terminal deployment at the preliminary selected location to obtain a cost calculation model;

[0020] The cloud platform center obtains the benefit calculation model based on the failure rate, false alarm rate and feedback score of the comprehensive evaluation of the edge node terminal;

[0021] The cloud platform center obtains the objective function of the optimal deployment position of the edge node terminal according to the cost calculation model and the benefit calculation model;

[0022] The cloud platform center solves the objective function through a built-in simulated annealing algorithm to obtain the deployment location of the newly selected edge node terminal.

[0023] Preferably, the cost calculation model is expressed as:

[0024] Cost = C infra +C ene +C da_proc +C da_tran

[0025] In the formula, C infra is the infrastructure construction cost; C ene is the energy consumption cost; C da_proc is the data processing cost; C da_tran is the data transmission cost.

[0026] Preferably, the expression of the benefit calculation model is:

[0027] Benefit=ω1·FDR+ω2·(1-FAR)+ω3·UFS

[0028] Where FDR is the failure rate; FAR is the false alarm rate; UFS is the user feedback score; ω1, ω2, ω3 are the corresponding weight coefficients.

[0029] Preferably, the objective function is expressed as:

[0030] Objective Function=Cost+λ·(1-Benefit)

[0031] In the formula, λ is the coefficient of converting benefit into cost.

[0032] A power grid edge computing platform, comprising:

[0033] The edge node terminal is deployed around the power equipment and marked as a preliminary location, and is used to collect the operation data of the power equipment at the preliminary location and analyze and process the obtained processing result data;

[0034] An execution terminal is used to receive the processing result data, perform verification processing, and generate feedback data;

[0035] The cloud platform center is used to receive the processing result data and the feedback data, and perform comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal, and analyze the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] A method for deploying a power grid edge computing platform of the present invention is as follows: the edge node terminal is deployed around the power equipment and marked as a preliminary position; the edge node terminal collects the operation data of the power equipment at the preliminary position, and performs analysis and processing to obtain the processing result data; the execution terminal receives the processing result data and performs verification processing to generate feedback data; the cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal; the cloud platform center analyzes the calculation result of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment position of the newly selected edge node terminal. The present invention performs a comprehensive evaluation on the edge node terminal of the preliminary deployment and combines the cost calculation of the cloud platform center to obtain the optimal deployment position of the edge node terminal, thereby realizing the scientific deployment of the edge node terminal in the edge computing platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0039] Figure 1 A flow chart of a deployment method of a power grid edge computing platform of the present invention.

[0040] Figure 2 This is a schematic diagram of a power grid edge computing platform of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0043] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0044] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0045] See the following examples Figure 1 to Figure 2 .

[0046] The present application provides a method for deploying a power grid edge computing platform, including:

[0047] Step 1: deploy edge node terminals around power equipment and mark them as preliminary locations;

[0048] There are several edge node terminals, which are deployed at key locations of the power grid or around power equipment (such as transformers, transmission lines, smart meters, etc.). The edge node terminal is responsible for data collection and processing and is an important part of the power grid edge computing platform. The deployment location corresponding to the mark is recorded as the preliminary location for subsequent data collection and analysis.

[0049] By deploying edge nodes around power equipment, real-time monitoring and rapid response to the power grid status can be achieved.

[0050] In the second step, the edge node terminal collects the operating data of the power equipment at the primary location and performs analysis and processing to obtain the processing result data;

[0051] The edge node terminal collects the operating data of the power equipment at the primary location, integrates data processing, fault identification or monitoring algorithms through containerization technology (existing algorithms can be used directly, or fault identification algorithms can be trained through neural networks, etc.), processes the operating data through the integrated algorithm, and obtains the processing result data. The edge node terminal collects the operating data of the power equipment, such as current, voltage, power, etc. The collected data is analyzed and processed in real time using edge computing technology to obtain processing result data including abnormal status, fault warning signals, etc. At the same time, the processed result data is stored in the edge node terminal or transmitted to the cloud platform center for further analysis.

[0052] Through the analysis and processing of edge computing technology, potential problems in the power grid can be discovered in a timely manner, providing guarantees for the safe and stable operation of the power grid.

[0053] Step 3: After receiving the processing result data, the execution terminal verifies the data and generates feedback data;

[0054] The execution terminal receives the processing result data sent by the edge node terminal, and checks and verifies it. Based on the verification results, the execution terminal generates corresponding feedback data, such as confirmation information, error information or adjustment suggestions. For example, the execution terminal performs further maintenance and other processing based on the monitoring or alarm data of the edge node terminal, and further feeds back to the cloud platform center based on the on-site maintenance or verification processing results. For example, the edge node single terminal generates an alarm signal through its integrated fault identification algorithm and sends it to the execution terminal. After the execution terminal arranges staff to perform on-site maintenance based on the alarm signal, it finds that the alarm signal recognition error is found. At this time, it can feedback an error signal to the cloud platform center, or feedback a low-rated user feedback score, etc.

[0055] By executing the verification processing of the terminal, the accuracy and reliability of the data can be ensured, and the generated feedback data provides an important basis for the comprehensive analysis of the cloud platform center.

[0056] Step 4: The cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal;

[0057] The cloud platform center is connected to the edge node terminal and the execution terminal to receive the processing result data of the edge node terminal, thereby facilitating macro-control based on the processing result data, and also to receive feedback data from the execution terminal to further determine whether the algorithm integrated in the edge node terminal or the setting position of the edge node terminal needs to be adjusted.

[0058] In other words, the cloud platform center can obtain at least the following data:

[0059] (1) Failure rate. The failure rate is obtained from the alarm signal of the edge node terminal, which reflects the frequency of receiving the alarm signal within a fixed period.

[0060] (2) False alarm rate. The false alarm rate is obtained from the false alarm situation fed back by the execution terminal. It reflects the number of false alarm errors (false alarms) fed back by the edge node terminal after the execution terminal receives the alarm signal and conducts on-site investigation within a fixed period.

[0061] (3) User feedback score. The user feedback score is a comprehensive score based on the false alarm situation and the location of the edge node terminal by the execution terminal. The comprehensive score can be provided by technical experts or relevant technical personnel, reflecting the comprehensive feedback of the execution terminal on the edge node terminal and the cloud platform center.

[0062] Step 5: The cloud platform center analyzes the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal.

[0063] The location of edge node terminals is crucial for fault identification, data processing, and response rate. Therefore, the location of edge node terminals is a crucial link in this solution. In the location problem of edge nodes, the location of edge nodes is adjusted by combining cost minimization and comprehensive evaluation of edge node terminals (such as failure rate, user feedback score, response time, etc.).

[0064] The cloud platform center has a built-in cost calculation algorithm to calculate the cost-effectiveness of different deployment locations. Combining the comprehensive evaluation of edge node terminals and the calculation results of the cost calculation algorithm, the cloud platform center conducts a comprehensive analysis to determine the new edge node terminal deployment location. The new deployment location should be able to better meet the monitoring needs of the power grid, while reducing deployment costs and improving overall benefits.

[0065] According to the location of the newly selected edge node terminal, the deployment of the power grid edge computing platform is completed.

[0066] In this embodiment, data processing, fault identification or monitoring algorithms are integrated into the edge node terminal through containerization technology (existing algorithms can be used directly, or fault identification algorithms can be trained through neural networks, etc., which are all commonly used technologies and will not be elaborated here). For example, by deploying a power transmission video monitoring terminal on the edge side and integrating the Atlas 200AI acceleration module, running the AI ​​reasoning algorithm for on-site image and video analysis, intelligent inspection of transmission lines is achieved. This mode greatly improves the inspection efficiency. In addition, in addition to inheriting using containerization technology, it can also be integrated through other technologies, or simply stored in the database and then directly called to achieve it.

[0067] Each edge node terminal is connected to the cloud platform center and the execution terminal. The connection with the cloud platform center is to transmit some result data to the cloud platform center, such as the fault alarm signal in the fault identification algorithm, the alarm signal of the monitoring terminal in the edge node terminal, and only the processing result data is transmitted to the cloud platform center, but the process data is not transmitted to the cloud platform center. In this way, the demand for data transmission can be reduced, thereby reducing latency, reducing bandwidth requirements, improving data privacy and enhancing real-time performance. In addition, the edge node terminal is connected to the execution terminal to transmit the alarm signal to the execution terminal, so that the execution terminal can grasp the alarm situation, and then it is convenient for the execution terminal to arrange the corresponding staff to perform troubleshooting or fault warning, etc. It aims to allow the execution terminal to grasp some process data (such as real-time equipment data, real-time monitoring status, etc.) and result data (abnormal status, alarm signals, etc.) of the edge node terminal.

[0068] A method for deploying a power grid edge computing platform of the present invention is as follows: the edge node terminal is deployed around the power equipment and marked as a preliminary position; the edge node terminal collects the operation data of the power equipment at the preliminary position, and performs analysis and processing to obtain the processing result data; the execution terminal receives the processing result data and performs verification processing to generate feedback data; the cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal; the cloud platform center analyzes the calculation result of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment position of the newly selected edge node terminal. The present invention performs a comprehensive evaluation on the edge node terminal of the preliminary deployment and combines the cost calculation of the cloud platform center to obtain the optimal deployment position of the edge node terminal, thereby realizing the scientific deployment of the edge node terminal in the edge computing platform.

[0069] Specifically, in a preferred implementation of the present application, the edge node terminal collects the operating data of the power equipment at the preliminarily selected position, including the edge node terminal collecting the operating data of the power equipment at the preliminarily selected position in a one-to-one or one-to-many manner.

[0070] In a specific implementation, the edge node terminal is set around each power grid equipment (such as a transformer, etc.), and its relationship with the power grid equipment can be one-to-one or one-to-many, that is, an edge node terminal can be set around only one transformer and only receive and process data from one transformer, or it can be set near several transformers and receive and process data from several transformers.

[0071] One-to-one collection can ensure that each power device has a corresponding edge node terminal for data collection, thereby achieving data accuracy and integrity. The edge node terminal can perform customized data collection based on the needs of specific equipment, improving the pertinence and efficiency of data collection. The one-to-many collection method is suitable for scenarios where multiple power devices are centrally distributed, which can reduce the number of edge node terminals and reduce deployment costs. Through reasonable network layout and protocol design, the one-to-many collection method can realize the parallel collection of data from multiple power devices, further improving data collection efficiency.

[0072] Specifically, the execution terminal receives the processing result data and performs verification processing to generate feedback data including:

[0073] After receiving the processing result data, the execution terminal compares the key information of the processing result data with the actual inspection result. If they are inconsistent, the difference content is recorded and an error signal is generated. Otherwise, a correct signal is generated.

[0074] Specifically, in a preferred implementation of the present application, the cloud platform center analyzes the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal, including:

[0075] Step 1: The cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost under the edge node terminal deployment at the preliminary selected location to obtain a cost calculation model;

[0076] The cost calculation model is expressed as:

[0077] Cost = C infra +C ene +C da_proc +C da_tran

[0078] In the formula, C infra is the infrastructure construction cost; C ene is the energy consumption cost; C da_proc is the data processing cost; C da_tran is the data transmission cost.

[0079] Infrastructure construction costs: usually include the construction and maintenance of data centers, the purchase and maintenance costs of servers, storage devices, and network equipment. These costs can be obtained through financial statements, profit and loss statement analysis, or determined through contract prices with construction companies and equipment suppliers. For example, a comparative study of infrastructure construction costs in Asia may provide some reference data. Or it can be directly estimated by technical experts and related operators and managers.

[0080] Energy consumption cost: involves the power consumption of the data center, including the purchase cost of electricity, depreciation and amortization cost of power facilities. These data can be obtained from the bill of the power supplier, or collected through the energy consumption monitoring system of the data center. For example, the cost changes of Internet data center (IDC) operators can provide some reference. Or it can be directly estimated by technical experts and relevant operators and managers.

[0081] Data processing costs: including the costs of data collection, storage, processing, analysis and maintenance. These costs can be estimated by analyzing the life cycle costs of data assets, including data collection costs, data storage costs, data processing and cleaning costs, data analysis and mining costs, and data maintenance costs. They can be directly estimated by technical experts and relevant operators and managers.

[0082] Data transfer costs: involve the transmission of data between different locations, such as data within a data center, between data centers, or between users. These costs can be obtained through contract prices with network service providers, or estimated by analyzing network traffic and transmission distance. For example, the execution data transfer modeling framework provided by AWS can help calculate and optimize data transfer costs. Or it can be directly estimated by technical experts and relevant operators and managers.

[0083] In actual applications, in addition to the costs listed above, other costs may also be included. However, for the sake of calculation efficiency and difficulty, the main costs are selected for calculation illustration.

[0084] By comprehensively considering infrastructure construction costs, energy consumption costs, data processing costs, and data transmission costs, the cloud platform center can accurately assess the total cost under different deployment locations, avoid resource waste, and optimize resource allocation.

[0085] Step 2: The cloud platform center obtains a benefit calculation model based on the failure rate, false alarm rate and feedback score of the comprehensive evaluation of the edge node terminal;

[0086] The expression of the benefit calculation model is:

[0087] Benefit=ω1·FDR+ω2·(1-FAR)+ω3·UFS

[0088] Among them, FDR is the Fault Detection Rate, which is the number of successfully detected faults divided by the total number of faults. FAR is the False Alarm Rate, which is the number of normal events that are incorrectly marked as faults divided by the total number of normal events. UFS is the User Feedback Score, which can be a quantitative indicator of user satisfaction (user feedback score). ω1, ω2, and ω3 are corresponding weight coefficients used to balance the importance of different benefit indicators.

[0089] The benefit calculation model combines failure rate, false alarm rate and user feedback score, so that the cloud platform center can comprehensively evaluate the benefits of edge node terminals. It not only takes into account the reliability of the technology, but also the user experience and satisfaction, thus ensuring the comprehensiveness and practicality of the deployment plan.

[0090] Step 3: The cloud platform center obtains the objective function of the optimal deployment position of the edge node terminal according to the cost calculation model and the benefit calculation model;

[0091] In the simulated annealing algorithm, the objective function is a comprehensive reflection of cost and benefit, which can be expressed as:

[0092] Objective Function=Cost-Benefit

[0093] Or, if the benefit is in the form of reduced costs, it can be expressed as:

[0094] Objective Function=Cost+λ·(1-Benefit)

[0095] Among them, λ is the coefficient of converting benefits into costs.

[0096] The objective function obtained using cost and benefit can reflect the cost-benefit relationship under different deployment locations and provide clear guidance for optimizing site selection.

[0097] Step 4: The cloud platform center solves the objective function through a built-in simulated annealing algorithm to obtain the deployment location of the newly selected edge node terminal.

[0098] In each iteration of the simulated annealing algorithm, a new solution (i.e., a new location scheme for edge node terminals) is generated and its objective function value is calculated. The algorithm optimizes the location through the following steps:

[0099] Initialization: Select an initial solution and set a high initial temperature.

[0100] Iterative search: randomly generate a new solution in the neighborhood of the current solution.

[0101] Acceptance criterion: If the objective function value of the new solution is better than the current solution, then accept the new solution. If the objective function value of the new solution is worse than the current solution, accept the new solution with a certain probability, which is determined by the Metropolis criterion:

[0102]

[0103] Where ΔE is the difference between the objective function values ​​of the new solution and the current solution, and T is the current temperature.

[0104] Cooling: Lower the temperature at a predetermined cooling rate.

[0105] Termination condition: When the temperature is lower than a certain threshold or the maximum number of iterations is reached, the algorithm terminates and outputs the current optimal solution.

[0106] In this way, the simulated annealing algorithm can provide a preliminary site selection plan for edge nodes based on cost minimization and benefit maximization. This plan can optimize resource allocation and cost-effectiveness while meeting the efficiency and safety of power grid operation.

[0107] In this embodiment, the simulated annealing algorithm is used to optimize the cost of infrastructure construction, which can achieve refined management of the site selection of data centers and edge nodes. Through the iterative process of the algorithm, the lowest cost solution is found among possible site selections. The advantage of this algorithm is that it can take into account a variety of factors that affect costs, such as geographical location, land prices, construction material costs, labor costs, etc. The algorithm allows poor solutions to be accepted through the "high temperature" stage of the simulated annealing process, which helps the algorithm to jump out of the local optimal solution, thereby having a greater possibility of finding the global optimal solution. As the "temperature" decreases, the algorithm gradually tends to accept better solutions, and finally stabilizes in the "low temperature" stage to obtain a site selection plan with the lowest cost. It can help decision makers make the most economical and efficient choice within a limited budget. In the operation of cloud computing data centers, energy consumption costs account for a considerable proportion. The energy efficiency of data centers is optimized through the simulated annealing algorithm. The algorithm adjusts the operating parameters of the data center through continuous iteration, such as the switch status of the server, load distribution, and the operating mode of the cooling system, to find the configuration with the lowest energy consumption. The algorithm can dynamically adapt to changes in the workload of the data center and adjust the energy usage strategy in real time, thereby achieving a continuous reduction in energy costs. The simulated annealing algorithm is used to reduce costs by optimizing the data processing process and algorithm, as well as optimizing the data transmission path and transmission volume. The best processing strategy and the best transmission solution are found through global optimization search.

[0108] By solving the simulated annealing algorithm, the cloud platform center can generate a scientific and efficient edge node terminal deployment plan. Not only the cost-effectiveness relationship is taken into account, but also factors such as power grid operation efficiency and security, thereby ensuring the practicality and feasibility of the deployment plan. The optimized deployment plan can reasonably allocate resources, reduce total costs, and improve benefits. At the same time, it can also improve the reliability and security of the power grid, providing a strong guarantee for the stable operation of the power grid.

[0109] In this embodiment, through automated and intelligent methods, the cloud platform center can quickly and accurately generate deployment plans, providing a scientific and efficient method for the deployment of the power grid edge computing platform. It can not only reduce total costs and improve benefits, but also optimize resource allocation and improve the reliability and security of the power grid. It can also provide a scientific decision-making basis for the cloud platform center and improve decision-making efficiency and accuracy.

[0110] It should be noted that after determining the location of the edge node terminal, the location of the cloud platform center can also be determined. The final location of the cloud platform center can be obtained by making corresponding assessments based on the above-mentioned cost and benefit calculation logic.

[0111] The embodiment of the present application also provides a power grid edge computing platform, including:

[0112] The edge node terminal is deployed around the power equipment and marked as a preliminary location, and is used to collect the operation data of the power equipment at the preliminary location and analyze and process the obtained processing result data;

[0113] An execution terminal is used to receive the processing result data, perform verification processing, and generate feedback data;

[0114] The cloud platform center is used to receive the processing result data and the feedback data, and perform comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal, and analyze the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal.

[0115] The functional explanation of each terminal department of a power grid edge computing platform in this embodiment is the same as that in the previous embodiment and will not be repeated here.

[0116] The containerization technology of the present invention provides great flexibility for the implementation and deployment of the simulated annealing algorithm. Containerization technology packages the application and its dependencies in a lightweight container, so that the application can run seamlessly in any environment that supports containers. The application of this technology enables the simulated annealing algorithm to be quickly deployed on edge computing nodes without considering the differences in the underlying operating system. The rapid start and stop capabilities of the container also enable the algorithm to flexibly allocate and recycle resources according to computing needs. In addition, containerization technology also supports microservice architecture, so that the simulated annealing algorithm can be easily integrated with other services and applications to achieve more complex optimization tasks. For example, in the problem of optimal site selection for power grids, the algorithm can be deployed on edge nodes together with other power grid management services to jointly provide support for the efficient operation of the power grid.

[0117] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. 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.

[0118] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0119] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for deploying a power grid edge computing platform, characterized in that: include: The edge node terminals are deployed around the power equipment and marked as the primary locations; The edge node terminal collects the operation data of the power equipment at the primary position, and performs analysis and processing to obtain the processing result data; the execution terminal receives the processing result data, verifies it, and generates feedback data; The cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal; The cloud platform center combines the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to analyze and obtain the deployment location of the newly selected edge node terminal.

2. The method for deploying a power grid edge computing platform according to claim 1, further comprising: According to the location of the newly selected edge node terminal, the deployment of the power grid edge computing platform is completed.

3. A method for deploying a power grid edge computing platform according to claim 2, characterized in that: The edge node terminal collects the operation data of the power equipment at the primary position, and performs analysis and processing to obtain the processing result data including: The edge node terminal collects the operating data of the power equipment at the primary location, integrates data processing, fault identification or monitoring algorithms through containerization technology, processes the operating data through the integrated algorithm, and obtains processing result data; the processing result data includes an alarm signal.

4. A method for deploying a power grid edge computing platform according to claim 3, characterized in that: The edge node terminal collecting the operating data of the power equipment at the preliminarily selected position includes the edge node terminal collecting the operating data of the power equipment at the preliminarily selected position in a one-to-one or one-to-many manner.

5. A method for deploying a power grid edge computing platform according to claim 3, characterized in that: After receiving the processing result data, the execution terminal performs verification processing and generates feedback data including: After receiving the processing result data, the execution terminal compares the key information of the processing result data with the actual inspection result. If they are inconsistent, the difference content is recorded and an error signal is generated. Otherwise, a correct signal is generated.

6. A method for deploying a power grid edge computing platform according to claim 3, characterized in that: The cloud platform center analyzes the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal, including: The cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost under the edge node terminal deployment at the preliminary selected location to obtain a cost calculation model; The cloud platform center obtains a benefit calculation model based on the failure rate, false alarm rate and feedback score of the comprehensive evaluation of the edge node terminal; the cloud platform center obtains the objective function of the optimal deployment position of the edge node terminal based on the cost calculation model and the benefit calculation model; The cloud platform center solves the objective function through a built-in simulated annealing algorithm to obtain the deployment location of the newly selected edge node terminal.

7. A method for deploying a power grid edge computing platform according to claim 6, characterized in that: The cost calculation model is expressed as: Cost=C infra +C ene +C da_proc +C da_tran In the formula, C infra is the infrastructure construction cost; C ene is the energy consumption cost; C da_proc is the data processing cost; C da_tran is the data transmission cost.

8. A method for deploying a power grid edge computing platform according to claim 7, characterized in that: The expression of the benefit calculation model is: Benefit=ω1·FDR+ω2·(1-FAR)+ω3·UFS Where FDR is the failure rate; FAR is the false alarm rate; UFS is the user feedback score; ω1, ω2, ω3 are the corresponding weight coefficients.

9. A method for deploying a power grid edge computing platform according to claim 8, characterized in that: The expression of the objective function is: Objective Function=Cost+λ·(1-Benefit) In the formula, λ is the coefficient of converting benefit into cost.

10. A power grid edge computing platform, characterized in that: include: The edge node terminal is deployed around the power equipment and marked as a preliminary location, and is used to collect the operation data of the power equipment at the preliminary location and analyze and process the obtained processing result data; An execution terminal is used to receive the processing result data, perform verification processing, and generate feedback data; The cloud platform center is used to receive the processing result data and the feedback data, and perform comprehensive analysis to obtain a comprehensive evaluation of the edge node terminal, and analyze the calculation results of the built-in cost calculation algorithm and the comprehensive evaluation of the edge node terminal to obtain the deployment location of the newly selected edge node terminal.

Images