A power grid edge computing platform and deployment method

Abstract

The application relates to the technical field of edge computing platform deployment, and discloses a power grid edge computing platform and a deployment method, which comprises the following steps: deploying edge node terminals around power equipment and marking the edge node terminals as initial selection positions; collecting operation data of the power equipment under the initial selection positions by the edge node terminals, performing analysis and processing on the operation data to obtain processing result data; performing checking processing on the processing result data received by a terminal to generate feedback data; receiving the processing result data and the feedback data by a cloud platform center, comprehensively analyzing the processing result data and the feedback data to obtain an edge node terminal comprehensive evaluation; and analyzing the calculation result of a built-in cost calculation algorithm and the edge node terminal comprehensive evaluation by the cloud platform center to obtain a newly selected deployment position of the edge node terminal. The application combines the comprehensive evaluation of the edge node terminal and the cost calculation of the cloud platform center to obtain the optimal deployment position of the edge node terminal, and realizes scientific deployment of the edge computing platform.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of edge computing platform deployment, in particular to a power grid edge computing platform and a deployment method. BACKGROUND

[0002] In the Internet of Things scenario, if the data generated by a large number 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 equipment, reducing data transmission volume and reducing delay.

[0003] In addition, many real-time monitoring and control of the power grid require fast response. Edge computing can realize instant processing of data, improve the efficiency and safety of the production line. The combination of edge computing and container technology can realize fast response of real-time monitoring and control, which is also a major direction of the current development and research of the power grid. However, the current setting position of edge computing in the power system is only set by technical experts or relevant personnel of planning departments based on actual experience, which is greatly influenced by subjectivity, is not scientific and rigorous, and cannot achieve optimal deployment of edge devices. SUMMARY

[0004] In view of the problem that the setting position of edge computing in the power system in the prior art is influenced by subjectivity and cannot achieve optimal deployment, the present application provides a power grid edge computing platform and a deployment method, which can comprehensively evaluate the initially selected edge node terminal and combine the cost calculation of the cloud platform center to obtain the optimal deployment position of the edge node terminal. The specific technical solutions are as follows:

[0005] A deployment method of a power grid edge computing platform, comprising:

[0006] The edge node terminal is deployed around the power equipment and is marked as an initially selected position;

[0007] The edge node terminal collects the operation data of the power equipment at the initially selected position and analyzes and processes the collected data to obtain processing result data;

[0008] The execution terminal receives the processing result data and performs checking processing to generate feedback data;

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

[0010] The cloud platform center analyzes the calculation result of the built-in cost calculation algorithm and the edge node terminal comprehensive evaluation to obtain a newly selected deployment position of the edge node terminal.

[0011] Preferably, the deployment method of the power grid edge computing platform further comprises:

[0012] According to the position 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 selected position, and the processing result data obtained through analysis and processing includes:

[0014] The edge node terminal collects the operation data of the power equipment at the primary selected position, integrates data processing, fault identification or monitoring algorithms through containerization technology, processes the operation data through the integrated algorithms to obtain processing result data; the processing result data includes an alarm signal.

[0015] Preferably, the edge node terminal collects the operation data of the power equipment at the primary selected position includes that the edge node terminal collects the operation data of the power equipment at the primary selected position in a one-to-one or one-to-many manner.

[0016] Preferably, the feedback data generated by the execution terminal after receiving the processing result data includes:

[0017] The execution terminal compares the key information of the processing result data with the actual inspection result after receiving the processing result data, and if they are inconsistent, records the difference content, generates an error signal, and otherwise generates a correct signal.

[0018] Preferably, 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, which includes:

[0019] The cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost of the edge node terminal deployed at the primary selected position to obtain a cost calculation model;

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

[0021] The cloud platform center obtains a target 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 target function through a built-in simulated annealing algorithm to obtain the deployment position of the newly selected edge node terminal.

[0023] Preferably, the expression of the cost calculation model is:

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

[0029] Preferably, the expression of the objective function is:

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

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

[0032] A power grid edge computing platform comprises:

[0033] An edge node terminal is deployed around a power device and is marked as a primary selected position, and is used to collect operation data of the power device at the primary selected position, and to analyze and process the collected operation data to obtain processing result data.

[0034] An execution terminal is used to receive the processing result data and to perform checking processing to generate feedback data.

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

[0036] Compared with the prior art, the power grid edge computing platform has the following beneficial effects:

[0037] The deployment method of the power grid edge computing platform of the application is characterized in that: the edge node terminal is deployed around the power equipment and marked as a primary selected position; the edge node terminal collects the operation data of the power equipment at the primary selected position, analyzes and processes the collected data to obtain processing result data; the terminal receives the processing result data and performs checking processing to generate feedback data; the cloud platform center receives the processing result data and the feedback data, comprehensively analyzes the data, obtains an edge node terminal comprehensive evaluation, and combines the calculation result of the built-in cost calculation algorithm and the edge node terminal comprehensive evaluation to analyze and obtain a newly selected deployment position of the edge node terminal. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0039] Fig. 1 The flow chart of the deployment method of the power grid edge computing platform of the application.

[0040] Fig. 2 The principle diagram of the power grid edge computing platform of the application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

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

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

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

[0045] The following examples are provided for reference Figs. 1-2 .

[0046] The embodiments of the present application provide a deployment method of a power grid edge computing platform, comprising:

[0047] First step, deploy edge node terminals around power equipment and mark as initial selection position;

[0048] The edge node terminals are provided with several, respectively deployed around the key positions of the power grid or power equipment (such as transformers, power 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 corresponding deployment position is marked as the initial selection position, so as to carry out data collection and analysis subsequently.

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

[0050] Second step, the edge node terminal collects the operation data of the power equipment at the initial selection position, and analyzes and processes the obtained processing result data;

[0051] The edge node terminal collects the operation data of the power equipment at the initial selection position, integrates data processing, fault identification or monitoring algorithms (which can directly use existing algorithms, or train fault identification algorithms through neural networks, etc.) through containerization technology, processes the operation data through integrated algorithms, and obtains processing result data. The edge node terminal collects the operation data of the power equipment, such as current, voltage, power, etc. The collected data is analyzed and processed in real time by using edge computing technology, and the processing result data including abnormal state, fault warning signal, etc. is obtained. 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 time, providing guarantee for the safe and stable operation of the power grid.

[0053] The third step is to perform a checking process after the terminal receives the processing result data to generate feedback data.

[0054] The execution terminal receives the processing result data sent by the edge node terminal and performs checking and verification. According to the checking result, the execution terminal generates corresponding feedback data, such as confirmation information, error information, or adjustment suggestions, etc. For example, the execution terminal makes further maintenance and other processes 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 checking processing result. For example, the edge node terminal generates an alarm signal through the 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 is found that the alarm signal identification is incorrect. At this time, an error signal can be fed back to the cloud platform center, or a low-score user feedback score can be fed back.

[0055] Through the checking process of the execution 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] The fourth step is that 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 with the edge node terminal and the execution terminal, which is used to receive the processing result data of the edge node terminal, so as to facilitate macro control based on the processing result data, and is also used to receive the feedback data of the execution terminal, so as to further judge whether the algorithm integrated in the edge node terminal or the setting position of the edge node terminal needs to be adjusted.

[0058] That is, the cloud platform center can at least obtain the following data:

[0059] (1) Fault rate. The fault 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 feedback of the execution terminal, which reflects the number of false alarms of the edge node terminal within a fixed period after the execution terminal receives the alarm signal and feeds back the false alarm number after on-site investigation.

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

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

[0063] The location selection of the edge node terminal is crucial for fault identification, data processing, and response rate, so the location selection of the edge node terminal is a crucial joint of the present scheme. In the location selection of the edge node, the position of the edge node is adjusted by combining cost minimization and comprehensive evaluation of the edge node terminal (such as fault rate, user feedback score, response time, etc.).

[0064] The cloud platform center is built-in with a cost calculation algorithm for calculating the cost benefits under different deployment locations. The cloud platform center analyzes the results of the comprehensive evaluation of the edge node terminal and the cost calculation algorithm to determine the new deployment location of the edge node terminal. The new deployment location should 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, the edge node terminal is integrated with data processing, fault identification or monitoring algorithms through containerization technology (existing algorithms can be directly used, or fault identification algorithms can be trained through neural networks, etc., which are not described here, and are common technologies). For example, by deploying a power transmission video monitoring terminal on the edge side and integrating an Atlas 200AI acceleration module, an AI inference algorithm is run for on-site image and video analysis to achieve intelligent inspection of power transmission lines. This mode greatly improves the inspection efficiency. In addition, in addition to using containerization technology, other technologies can also be integrated, or only the algorithm can be stored in the database and then directly called to achieve it.

[0067] Each edge node terminal is connected with 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, only the processing result data is transmitted to the cloud platform center, and the process data is not transmitted to the cloud platform center, which can reduce the demand for data transmission, thereby reducing the delay, reducing the bandwidth demand, improving the data privacy and enhancing the real-time performance. In addition, the edge node terminal is connected with the execution terminal to transmit the alarm signal to the execution terminal, so as to enable the execution terminal to master the alarm situation, thereby facilitating the execution terminal to arrange corresponding staff to troubleshoot or fault warning, etc. Its purpose is to enable the execution terminal to master some process data (such as real-time device data, real-time monitoring situation, etc.) and result data (abnormal state, alarm signal, etc.) of the edge node terminal.

[0068] The deployment method of the power grid edge computing platform of the application deploys edge node terminals around power equipment and marks as a primary selection position; the edge node terminal collects operation data of the power equipment at the primary selection position, analyzes and processes the obtained processing result data; the execution terminal receives the processing result data and performs checking processing to generate feedback data; the cloud platform center receives the processing result data and the feedback data and performs comprehensive analysis to obtain an edge node terminal comprehensive evaluation; the cloud platform center analyzes the calculation result of the built-in cost calculation algorithm and the edge node terminal comprehensive evaluation to obtain a newly selected deployment position of the edge node terminal. The application obtains the optimal deployment position of the edge node terminal by comprehensively evaluating the initially deployed edge node terminal in combination with the cost calculation of the cloud platform center, thereby realizing scientific deployment of the edge node terminal in the edge computing platform.

[0069] Specifically, in a preferred embodiment of the application, the edge node terminal collects operation data of the power equipment at the primary selection position includes that the edge node terminal collects operation data of the power equipment at the primary selection position in a one-to-one or one-to-many manner.

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

[0071] One-to-one collection can ensure that each power equipment has a corresponding edge node terminal for data collection, thereby realizing accuracy and integrity of data. The edge node terminal can customize data collection according to the needs of specific equipment, thereby improving the pertinence and efficiency of data collection. The one-to-many collection mode is suitable for scenarios where multiple power equipment are distributed in clusters, and can reduce the number of edge node terminals and deployment costs. Through reasonable network layout and protocol design, the one-to-many collection mode can realize parallel collection of data of multiple power equipment, thereby further improving data collection efficiency.

[0072] Specifically, the execution terminal receives the processing result data and performs checking processing to generate feedback data, which includes:

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

[0074] Specifically, in a preferred implementation of the present application, the cloud platform center analyzes the results 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, which includes:

[0075] Step one, the cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost of the edge node terminal under the initial selected position to obtain a cost calculation model;

[0076] The expression of the cost calculation model is:

[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 cost: usually includes the construction and maintenance of data center, the purchase and maintenance cost of server, storage device and network equipment. These costs can be obtained by analyzing financial statements, profit and loss statements, or determined by 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 relevant operating personnel and management personnel.

[0080] Energy consumption cost: involves the power consumption of data center, including the purchase cost of electricity, the depreciation and amortization cost of power facilities. These data can be obtained from the bills of power suppliers, or collected through the energy consumption monitoring system of 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 operating personnel and management personnel.

[0081] Data processing cost: includes the cost of data collection, storage, processing, analysis and maintenance. These costs can be estimated by analyzing the life cycle cost of data assets, including data collection cost, data storage cost, data processing and cleaning cost, data analysis and mining cost and data maintenance cost. It can be directly estimated by technical experts and relevant operating personnel and management personnel.

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

[0083] In practical applications, in addition to the above-mentioned several costs, other costs can also be included. However, in order to calculate efficiency and difficulty, the main costs are selected for calculation and explanation.

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

[0085] Step two, the cloud platform center obtains the benefit calculation model according to the fault rate, false alarm rate and feedback score of the edge node terminal comprehensive evaluation;

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

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

[0088] Where FDR is the fault detection rate, that is, the number of successfully detected faults divided by the total number of faults. FAR is the false alarm rate, that is, the number of normal events 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, ω3 are the corresponding weight coefficients, used to balance the importance of different benefit indicators.

[0089] The benefit calculation model combines the fault rate, false alarm rate and user feedback score, so that the cloud platform center can comprehensively evaluate the benefit of the edge node terminal. Not only the reliability of the technology is considered, but also the user experience and satisfaction are considered, so as to ensure the comprehensiveness and practicality of the deployment scheme.

[0090] Step three, the cloud platform center obtains the target function of the optimal deployment location of the edge node terminal according to the cost calculation model and the benefit calculation model;

[0091] In the simulated annealing algorithm, the target function is a comprehensive embodiment of cost and benefit, which can be represented as:

[0092] Objective Function = Cost - Benefit

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

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

[0095] Where λ is the coefficient of benefit conversion to cost.

[0096] The objective function obtained by cost and benefit can reflect the cost-benefit relationship under different deployment locations, providing clear guidance for optimization site selection.

[0097] Step four, the cloud platform center solves the objective function by built-in simulated annealing algorithm, and gets the newly selected deployment location of edge node terminal.

[0098] In each iteration of the simulated annealing algorithm, a new solution (i.e. a new site selection scheme of edge node terminal) is generated, and its objective function value is calculated. The algorithm optimizes site selection 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 criteria: If the objective function value of the new solution is better than the current solution, 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: Reduce the temperature according to the 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 scheme for edge nodes based on the consideration of cost minimization and benefit maximization. This scheme can optimize resource allocation and cost-benefit while meeting the efficiency and safety of power grid operation.

[0107] In this embodiment, the simulated annealing algorithm is used to optimize the infrastructure construction cost, which can realize the fine management of data center and edge node site selection. Through the iterative process of the algorithm, the lowest cost solution is found among the possible sites. The algorithm can consider various factors that affect the cost, such as geographic location, land price, construction material cost, labor cost, etc. The algorithm allows to accept worse solutions in the "high temperature" stage of the simulated annealing process, which helps the algorithm to jump out of the local optimal solution and has a greater possibility to find 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 get a site selection scheme with the lowest cost. It can help decision-makers make the most economical and efficient choice within the limited budget. In the operation of cloud computing data centers, energy consumption cost accounts for a considerable proportion. Through the simulated annealing algorithm, the energy use efficiency of the data center is optimized. The algorithm adjusts the operation parameters of the data center, such as the on-off state of the server, load distribution, and operation mode of the cooling system, through continuous iteration to find the configuration with the lowest energy consumption. The algorithm can dynamically adapt to the changes in the workload of the data center and adjust the energy use strategy in real time, thereby continuously reducing the energy cost. The simulated annealing algorithm is used to optimize the data processing flow and algorithm to reduce the cost, as well as to optimize the data transmission path and transmission volume. Through global optimization, the best processing strategy and the best transmission scheme are found.

[0108] Through the solution of the simulated annealing algorithm, the cloud platform center can generate a scientific and efficient edge node terminal deployment scheme. Not only the cost-benefit relationship is considered, but also the factors such as power grid operation efficiency and safety are considered, so as to ensure the practicality and feasibility of the deployment scheme. The optimized deployment scheme can reasonably allocate resources, reduce the total cost, and improve the efficiency. At the same time, it can also improve the reliability and safety of the power grid, providing strong guarantee for the stable operation of the power grid.

[0109] In this embodiment, through the automatic and intelligent method, the cloud platform center can quickly and accurately generate the deployment scheme, providing a scientific and efficient method for the deployment of the power grid edge computing platform. Not only can it reduce the total cost and improve the efficiency, but also can optimize resource allocation and improve the reliability and safety of the power grid. It can also provide 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 site selection of the edge node terminal, the site selection of the cloud platform center can also be determined. According to the above cost and benefit calculation logic, the final site selection of the cloud platform center can be obtained.

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

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

[0113] An execution terminal is used to perform checking processing after receiving the processing result data, and generate feedback data;

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

[0115] The function explanation of the terminal department of the power grid edge computing platform in the embodiment is the same as that of the foregoing embodiment, and will not be repeated here.

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

[0117] Those skilled in the art can appreciate that the units of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components of the examples have been described in the above description in general terms. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0118] In the embodiments provided by the application, it should be understood that the division of units is only a logical functional division, and actual implementation can have another division manner, for example, multiple units can be combined as one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0119] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0120] When the integrated unit is realized in the form of a software function 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 solutions of the present application or the part of the prior art that essentially contributes or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0121] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present application, and they should be covered in the scope of the claims and the description of the present application.

Claims

1. A method for deployment of a grid edge computing platform, the method comprising: Comprise: ​ The edge node terminal is deployed around the power equipment and is marked as a primary selected position; The edge node terminal collects the operation data of the power equipment at the primary selected position, and the processing result data obtained by analysis and processing, specifically including that the edge node terminal collects the operation data of the power equipment at the primary selected position, integrates data processing, fault identification or monitoring algorithms through containerization technology, processes the operation data through the integrated algorithms to obtain processing result data, and sends the processing result data to the execution terminal and the cloud platform center respectively, wherein the processing result data includes an alarm signal; The execution terminal receives the processing result data and performs checking processing to generate feedback data, specifically including that the execution terminal compares the key information of the processing result data with the actual inspection result after receiving the processing result data, records the difference content if they are inconsistent, generates an error signal, otherwise generates a correct signal, and sends the cloud platform center; The cloud platform center receives the processing result data and the feedback data, and performs comprehensive analysis to obtain an edge node terminal comprehensive evaluation; The cloud platform center analyzes the calculation result of the built-in cost calculation algorithm and the edge node terminal comprehensive evaluation to obtain a newly selected edge node terminal deployment position, specifically including: The cloud platform center calculates the infrastructure construction cost, energy consumption cost, data processing cost and data transmission cost of the edge node terminal deployment at the primary selected position to obtain a cost calculation model; the expression of the cost calculation model is: In the formula, is the infrastructure construction cost; is the energy consumption cost; is the data processing cost; is the data transmission cost; The cloud platform center obtains a benefit calculation model according to the failure rate, false alarm rate and feedback score of the edge node terminal comprehensive evaluation; the expression of the benefit calculation model is: wherein is the failure rate; is the false positive rate; is the user feedback score; , , are the respective weight coefficients; The cloud platform center obtains a target function of the optimal deployment position of the edge node terminal according to the cost calculation model and the benefit calculation model; the expression of the target function is: wherein The cloud platform center solves the target function through the built-in simulated annealing algorithm to obtain the deployment position of the newly selected edge node terminal. is a coefficient of benefit conversion into cost; 2. The power grid edge computing platform deployment method according to claim 1, further comprising: According to the position of the newly selected edge node terminal, the deployment of the power grid edge computing platform is completed. The edge node terminal collects the operation data of the power equipment at the primary selected position, including that the edge node terminal collects the operation data of the power equipment at the primary selected position in a one-to-one or one-to-many manner.

3. The method of claim 1, wherein, The power grid edge computing platform deployment method according to any one of claims 1 to 3, comprising:

4. An electric grid edge computing platform, characterized by, An edge node terminal is deployed around the power equipment and is marked as a primary selected position, used to collect the operation data of the power equipment at the primary selected position, and to analyze and process the processing result data obtained; An execution terminal is used to receive the processing result data and perform checking processing to generate feedback data; A cloud platform center is used to receive the processing result data and the feedback data, perform comprehensive analysis to obtain an edge node terminal comprehensive evaluation, and analyze the calculation result of the built-in cost calculation algorithm and the edge node terminal comprehensive evaluation to obtain a newly selected edge node terminal deployment position. ​

Images