An electronic scheduling-based power grid operation optimization method and system

Abstract

The application provides a power grid operation optimization method and system based on electronic scheduling, and relates to the technical field of digital processing.The method comprises the following steps: connecting the power grid operation optimization management system, and acquiring basic equipment components of a target power grid; performing data monitoring on the basic equipment components based on the data acquisition device, acquiring real-time operation data of electric power, performing visual distribution, acquiring multi-level electric power operation data, inputting the equipment energy consumption analysis model, acquiring energy consumption analysis results according to the equipment energy consumption analysis model, inputting the optimization decision tree, acquiring optimization decision results according to the optimization decision tree, and optimizing the target power grid.The technical problem that the equipment energy consumption of the power grid is low in adaptation to the optimization scheme, resulting in low precision of power grid operation optimization management is solved, the technical effect that energy consumption is evaluated based on field data, an optimization scheme is determined in a targeted manner, the optimization scheme is selected, and the precision of power grid operation optimization management is improved is achieved.

Description

Technical Field

[0001] This invention relates to the field of digital processing technology, and specifically to a power grid operation optimization method and system based on electronic dispatching. Background Technology

[0002] Electricity, as a widely used energy source, is typically transmitted to users through the power grid. With the development of science and technology, high-tech products (such as circuit breakers, current-limiting reactors, voltage transformers, and current transformers) are continuously introduced into the operation and management of the power grid, improving the efficiency of power grid operation and management.

[0003] In terms of power grid operation optimization, professional management personnel are generally required to carry out control. During the operation of the power grid, various types of parameters and indicators will be generated. Comprehensive data analysis is needed to find the inherent relationship between various types of parameters and indicators and to promptly discover the different information brought about by data changes. Therefore, it is urgent to build a power grid operation optimization management system to carry out targeted optimization during the operation of the power grid.

[0004] Existing technologies suffer from the technical problem of low compatibility between power grid equipment energy consumption and optimization schemes, resulting in low precision in power grid operation optimization management. Summary of the Invention

[0005] This application provides a power grid operation optimization method and system based on electronic dispatch, which solves the technical problem of low equipment energy consumption and low optimization scheme adaptability in the power grid, resulting in low accuracy of power grid operation optimization management. It achieves the technical effect of improving the accuracy of power grid operation optimization management by conducting energy consumption assessment based on field data, determining optimization schemes in a targeted manner, selecting the best optimization scheme, and so on.

[0006] In view of the above problems, this application provides a power grid operation optimization method and system based on electronic dispatch.

[0007] The first aspect of this application provides a power grid operation optimization method based on electronic dispatching. The method is applied to a power grid operation optimization management system, which is communicatively connected to a data acquisition device. The method includes: connecting to the power grid operation optimization management system to acquire the basic equipment components of the target power grid; monitoring the basic equipment components using the data acquisition device to acquire real-time power operation data; visualizing the real-time power operation data to acquire multi-level power operation data; inputting the multi-level power operation data into an equipment energy consumption analysis model, and obtaining energy consumption analysis results based on the equipment energy consumption analysis model; inputting the energy consumption analysis results into an optimization decision tree, and obtaining optimization decision results based on the optimization decision tree; and optimizing the target power grid based on the optimization decision results.

[0008] A second aspect of this application provides a power grid operation optimization system based on electronic dispatching, wherein the system includes: an equipment component acquisition unit, which is used to connect to the power grid operation optimization management system to acquire basic equipment components of the target power grid; a data monitoring unit, which is used to monitor the basic equipment components based on a data acquisition device to acquire real-time power operation data; an operation data acquisition unit, which is used to acquire multi-level power operation data by visualizing the distribution of the real-time power operation data; an energy consumption analysis unit, which is used to input the multi-level power operation data into an equipment energy consumption analysis model and acquire energy consumption analysis results based on the equipment energy consumption analysis model; a decision result acquisition unit, which is used to input the energy consumption analysis results into an optimization decision tree and acquire optimization decision results based on the optimization decision tree; and an optimization execution unit, which is used to optimize the target power grid based on the optimization decision results.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By employing a connection to the power grid operation optimization management system, acquiring the basic equipment components of the target power grid, monitoring data, obtaining real-time power operation data, visualizing the distribution, acquiring multi-level power operation data, inputting the data into the equipment energy consumption analysis model to obtain energy consumption analysis results, inputting the data into the optimization decision tree, obtaining optimization decision results based on the optimization decision tree, and optimizing the target power grid based on the optimization decision results, this application achieves the technical effect of improving the accuracy of power grid operation optimization management by conducting energy consumption assessment based on field data, determining targeted optimization schemes, selecting the best optimization scheme, and improving the accuracy of power grid operation optimization management. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating a power grid operation optimization method based on electronic dispatching according to this application;

[0012] Figure 2 This is a schematic diagram illustrating the process of optimizing a target power grid according to a power grid operation optimization method based on electronic dispatching proposed in this application.

[0013] Figure 3 This is a schematic diagram of the process for obtaining optimization execution instructions in a power grid operation optimization method based on electronic dispatching according to this application;

[0014] Figure 4 This is a schematic diagram of the structure of a power grid operation optimization system based on electronic dispatching according to this application.

[0015] Explanation of reference numerals in the attached drawings: Equipment component acquisition unit 11, data monitoring unit 12, operation data acquisition unit 13, energy consumption analysis unit 14, decision result acquisition unit 15, optimization execution unit 16. Detailed Implementation

[0016] This application provides a power grid operation optimization method and system based on electronic dispatch, which solves the technical problem of low equipment energy consumption and low optimization scheme adaptability in the power grid, resulting in low accuracy of power grid operation optimization management. It achieves the technical effect of improving the accuracy of power grid operation optimization management by conducting energy consumption assessment based on field data, determining optimization schemes in a targeted manner, selecting the best optimization scheme, and so on.

[0017] Example 1

[0018] like Figure 1 As shown, this application provides a power grid operation optimization method based on electronic dispatching, wherein the method is applied to a power grid operation optimization management system, the system being communicatively connected to a data acquisition device, and the method includes:

[0019] Step S100: Connect to the power grid operation optimization management system to obtain the basic equipment components of the target power grid;

[0020] Step S200: Based on the data acquisition device, perform data monitoring on the basic equipment components to obtain real-time power operation data;

[0021] Specifically, the operation optimization management of power grids has low correlation with the basic data related to transmission networks. In the initial design of transmission networks, it is necessary to consider the load requirements of the power grid and meet relevant safety standards. During the construction process, the focus is on the convenience of construction and the reasonableness of cost. After the power grid is completed, there are certain differences between the operation optimization management scheme of the power grid and the calculations determined in the initial design. On-site data collection and analysis are carried out to achieve visualized management, and comprehensive energy consumption is analyzed and evaluated to optimize the target power grid and improve the accuracy of optimization management.

[0022] Specifically, the target power grid is a power transmission network formed by any power circuit. The power grid operation optimization method is executed in the power grid operation optimization management system, which connects the power grid operation optimization management system with the target power grid. The target power grid is characterized to obtain the basic equipment components of the target power grid. The basic equipment components are the basic equipment for building the target power grid. Commonly, the basic equipment components can be transformers, circuit breakers, surge arresters, current-limiting reactors, voltage transformers, current transformers, and other related basic equipment components of the power network. The data acquisition device can be ammeters, energy meters, and other related field data monitoring and acquisition devices. Through the functional characteristics of the data acquisition device, the basic equipment components are monitored (the deployment of the data acquisition device corresponds to the basic equipment components, and the data acquisition device is used to monitor the basic equipment components), and real-time power operation data is obtained. The real-time power operation data is the data collected by the data acquisition device from the current monitoring, providing a data foundation for subsequent data analysis.

[0023] Step S300: Obtain multi-level power operation data by visualizing and distributing the real-time power operation data;

[0024] Step S400: Input the multi-level power operation data into the equipment energy consumption analysis model, and obtain the energy consumption analysis results according to the equipment energy consumption analysis model;

[0025] Specifically, the power network layout is reconstructed through the deployment of the target power grid. Using a power grid simulation platform [BPA (software name), PSCAD (software name), PSS / E (software name)], the target power grid is reconstructed to obtain a power grid simulation model topology. The real-time power operation data is marked on this topology, achieving a visual distribution of the real-time power operation data. The distribution pattern of this visual distribution is consistent with the distribution pattern of basic equipment components in the target power grid. After marking the real-time power operation data, the node positions of the basic equipment components in the power grid simulation model topology are determined. Once determined, the node positions are associated and bound with the real-time power operation data. Multi-level power operation data represents the association and binding results between the node positions and the real-time power operation data. This multi-level power operation data is used as input data and input into the equipment energy consumption analysis model. Based on the equipment energy consumption analysis model, energy consumption is evaluated on the multi-level power operation data, and energy consumption analysis results are obtained. Through energy consumption evaluation, the optimization direction of the target power grid is determined (targeted optimization is performed for those with high energy consumption evaluation outputs), providing support for the optimization of the target power grid.

[0026] Furthermore, the multi-level power operation data is input into the equipment energy consumption analysis model, and the energy consumption analysis results are obtained based on the equipment energy consumption analysis model. Step S400 also includes:

[0027] Step S410: Input the multi-level power operation data into the equipment energy consumption analysis model, wherein the equipment energy consumption analysis model includes an energy consumption identification layer, an energy consumption comparison layer, and an energy consumption output layer;

[0028] Step S420: Based on the energy consumption identification layer in the equipment energy consumption analysis model, identify the energy consumption data of the multi-level power operation data and output real-time energy consumption data;

[0029] Step S430: Compare the real-time energy consumption data with the energy consumption comparison database embedded in the energy consumption comparison layer, and output the difference energy consumption data;

[0030] Step S440: Use the difference energy consumption data as the energy consumption analysis result and output it through the energy consumption output layer.

[0031] Furthermore, embodiments of this application also include:

[0032] Step S431: Generate a power grid simulation model by performing initial performance modeling on all devices in the target power grid;

[0033] Step S432: Perform equipment operation simulation tests based on the power grid simulation model and obtain simulation test data;

[0034] Step S433: Based on the simulated test data, obtain simulated energy consumption data, wherein the simulated energy consumption data is energy consumption data based on initial performance conditions;

[0035] Step S434: Use the simulated energy consumption data as the energy consumption comparison database to perform energy consumption difference comparison.

[0036] Specifically, an energy consumption analysis model is constructed, comprising an energy consumption identification layer, an energy consumption comparison layer, and an energy consumption output layer. These three layers are all functional layers. The energy consumption identification layer contains energy consumption identification tags, including power loss tags, line loss rate tags, and network loss rate tags. The inputs to the energy consumption identification layer are marked and identified using these tags. After ensuring the output accuracy is not lower than a preset accuracy rate (a preset parameter), the energy consumption identification layer is determined based on the energy consumption identification tags. The energy consumption comparison layer embeds an energy consumption comparison database. The energy consumption output layer is a functional layer. The energy consumption identification layer, the energy consumption comparison layer, and the energy consumption output layer are cascaded sequentially to generate the energy consumption analysis model, providing a model foundation for data processing.

[0037] To further explain, the multi-level power operation data is used as input data and input into the constructed equipment energy consumption analysis model. Based on the energy consumption identification layer within the model, energy consumption identification tags are set internally to mark and identify the multi-level power operation data (identifying data in the multi-level power operation data whose physical characteristics match the corresponding energy consumption identification tags, and marking the data with the same physical characteristics). The output of the energy consumption identification layer is the real-time energy consumption data, which consists of the data with the same physical characteristics. According to the data, the real-time energy consumption data is tagged; through the serial cascading of the energy consumption identification layer and the energy consumption comparison layer, the real-time energy consumption data is input into the energy consumption comparison layer, and the energy consumption difference is compared through the energy consumption comparison database. The energy consumption comparison layer outputs the difference energy consumption data; the difference energy consumption data is set as the energy consumption analysis result. Based on the serial cascading of the energy consumption comparison layer and the energy consumption output layer, the energy consumption analysis result is output through the energy consumption output layer, which limits the input and output of the equipment energy consumption analysis model and improves the convenience of subsequent use of the equipment energy consumption analysis model.

[0038] To further elaborate, all equipment in the target power grid includes transformers, circuit breakers, surge arresters, current-limiting reactors, voltage transformers, current transformers, power lines, wall bushings, and other basic power infrastructure equipment. Through a power grid simulation platform operated by the power grid operation optimization management system, the topology of the power grid simulation model is completed using all the equipment in the target power grid to generate the power grid simulation model. The initial performance refers to the initial performance of the equipment, which characterizes the energy consumption that should be generated initially, distinguishing it from the performance after a period of use. During the operation of the power grid simulation model, equipment operation simulation tests are conducted to obtain simulation test data. This simulation test data constitutes the equipment operation simulation test data. During the testing process, the data obtained is recorded and converted into multi-level power operation data. This converted data is then input into the energy consumption identification layer of the equipment energy consumption analysis model. Energy consumption is evaluated on the converted data, and the energy consumption identification layer outputs simulated energy consumption data. This simulated energy consumption data is based on initial performance conditions. The simulated energy consumption data is used as the energy consumption comparison database for energy consumption difference comparison. The simulated energy consumption data obtained in the initial lossless state is imported into the energy consumption comparison database for energy consumption comparison, providing support for maintaining the stability of the equipment energy consumption analysis model.

[0039] To further specify, the embodiments of this application also include:

[0040] Step S441: Perform deviation analysis on the differential energy consumption data to obtain a deviation set, wherein the deviation set corresponds to the device corresponding to the differential energy consumption data;

[0041] Step S442: Obtain N energy consumption data points with differences greater than or equal to a preset deviation set;

[0042] Step S443: Identify the corresponding N power grid devices based on the N differential energy consumption data;

[0043] Step S444: Output the N power grid devices as the energy consumption analysis results.

[0044] Specifically, if the energy consumption of the target power grid is too high, targeted optimization is required. Specifically, deviation analysis is performed on the differential energy consumption data. This deviation analysis is calculated as (real-time energy consumption data - simulated energy consumption data) / simulated energy consumption data, yielding a deviation set. This deviation set corresponds to the equipment corresponding to the differential energy consumption data. A preset deviation set is set (the preset deviation set is a preset parameter index; different power grid equipment corresponds to multiple preset deviations, which are merged to obtain the preset deviation set). This preset deviation set corresponds to the equipment corresponding to the differential energy consumption data. The deviation set is compared with a preset deviation set to obtain N (N∈N*) differential energy consumption data that are greater than or equal to the preset deviation set (the N differential energy consumption data are the differential energy consumption data corresponding to the equipment with excessive energy consumption in the target power grid); the N differential energy consumption data are used as labeling information to identify the corresponding N power grid equipment in the target power grid. After the labeling is completed, the N power grid equipment are output as the energy consumption analysis result. The energy consumption in the target power grid is filtered by the preset deviation set to determine the N power grid equipment, which provides a basis for targeted optimization of the equipment with excessive energy consumption in the target power grid.

[0045] Step S500: Input the energy consumption analysis results into the optimization decision tree, and obtain the optimization decision results based on the optimization decision tree;

[0046] Step S600: Optimize the target power grid based on the optimization decision results.

[0047] Furthermore, the energy consumption analysis results are input into the optimization decision tree, and the optimization decision results are obtained based on the optimization decision tree. Step S500 includes:

[0048] Step S510: Input the energy consumption analysis results into the optimization decision tree, wherein the optimization decision tree includes equipment performance degradation characteristics, equipment environmental overheating characteristics, and equipment overload characteristics;

[0049] Step S520: Analyze the input energy consumption analysis results based on the optimized decision tree to obtain the equipment performance degradation index, equipment environmental overheating index, and equipment overload index;

[0050] Step S530: Obtain the optimization decision result based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index.

[0051] Furthermore, such as Figure 2 As shown, based on the optimization decision results, the target power grid is optimized. Step S600 further includes:

[0052] Step S610: Based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index, determine the features to be optimized;

[0053] Step S620: Calculate the cost required for optimization based on the features to be optimized, and obtain the optimization cost;

[0054] Step S630: Perform simulation testing using the optimized parameters of the feature to be optimized, and output the optimized value-added;

[0055] Step S640: When the optimization cost is less than the optimization increment, obtain the optimization execution instruction.

[0056] Specifically, a multi-level classification decision feature is set. The classification decision feature indicates that the feature is used to make decisions in a hierarchical manner during the decision-making process. Specifically, the equipment performance degradation feature is used as the first classification decision feature, which is the additional energy consumption caused by equipment aging (the additional energy consumption caused by equipment aging leading to performance degradation). The equipment environmental overheating feature is used as the second classification decision feature, which is the equipment heating up due to long-term operation, and the heat accumulation increases energy consumption (without considering equipment overload operation, based on Joule's law, the heat generated by the current during long-term operation of the equipment causes the equipment to heat up, and the heat dissipation is calculated using Joule's law, which is the additional energy consumption corresponding to the equipment environmental overheating feature). The equipment overload feature is used as the third classification decision feature, which is the increased energy consumption caused by excessive load data (the additional energy consumption generated by equipment overload operation).

[0057] Information entropy is often used to measure the degree of difference between information. A large degree of difference corresponds to a large feature information entropy, indicating that the feature can be further divided into more features. A small degree of difference corresponds to a small feature information entropy, indicating that the feature can be further divided into fewer features. The specific calculation process of the information theory coding operation is not described here. Based on the first classification decision feature, the second classification decision feature, and the third classification decision feature, the first feature information entropy, the second feature information entropy, and the third feature information entropy are obtained.

[0058] The first, second, and third classification decision features can serve as internal nodes of the optimized decision tree. By calculating their information entropy, the feature with the highest entropy value can be prioritized for decision-making, thus determining the level of the multi-level classification decision features. This method is used to recursively construct the optimized decision tree until the last feature leaf node can no longer be further divided, indicating that the classification decision has ended. This constitutes the optimized decision tree. Based on the first, second, and third feature information entropy, the root node feature information is determined, ensuring that the optimized decision tree is divided to the smallest unit, providing a foundation for subsequent accurate analysis.

[0059] Using the energy consumption analysis results as input data, the energy consumption analysis results are input into the optimization decision tree. Hierarchical decision evaluation is performed based on the optimization decision tree to obtain the optimization decision tree output, which is the optimization decision result. Based on the optimization decision result, the consistency between the optimization direction and the additional energy consumption is ensured, and the target power grid is optimized in a targeted manner to effectively improve the accuracy of the operation optimization of the target power grid.

[0060] More specifically, the optimization decision tree includes equipment performance degradation characteristics, equipment environmental overheating characteristics, and equipment overload characteristics. The energy consumption analysis results are input into the optimization decision tree. The optimization decision tree analyzes the input energy consumption analysis results to obtain the equipment performance degradation index, equipment environmental overheating index, and equipment overload index, respectively. Based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index, the optimization decision result is obtained (based on the levels of multi-level classification decision features; for example, if the equipment performance degradation characteristic and the equipment environmental overheating characteristic are determined to be sequential features through the first feature information entropy, the second feature information entropy, and the third feature information entropy, and the equipment overload characteristic is determined to be parallel to the sequential features, i.e., the intersection of the equipment performance degradation index and the equipment environmental overheating index is found, and the intersection of the equipment performance degradation index and the equipment environmental overheating index is merged with the equipment overload index to determine the optimization decision result). The optimization decision tree is then determined and substituted into the calculations to provide a reference for subsequent calculations.

[0061] More specifically, correspondingly, based on the optimization decision results, the characteristics to be optimized are determined to provide support for targeted optimization of the target power grid (the characteristics to be optimized correspond to the optimization methods, which can be any optimization method such as software upgrades, hardware modifications, or the addition of maintenance software); the cost required for optimization of the characteristics to be optimized is statistically analyzed (the cost required for optimization is the cost generated by the optimization method, such as the cost of software upgrades, hardware modifications, or the cost of adding maintenance software), and the optimization cost is obtained after the cost statistics are completed; based on the power grid simulation model, the parameters after optimization of the characteristics to be optimized are simulated and tested, and data is recorded during the simulation test to obtain the optimization value-added, which is the benefit generated by the energy consumption reduction after executing the optimization method; when the optimization cost is less than the optimization value-added (indicating that after the corresponding optimization method is executed, the optimization cost is lower than the optimization gain, and the corresponding optimization method is an effective means), an optimization execution instruction is obtained, and the cost generated by the optimization method is compared with the benefit generated by the energy consumption reduction after optimization to determine the effective means and ensure the feasibility of optimizing the operation of the target power grid.

[0062] Furthermore, such as Figure 3 As shown, embodiments of this application also include;

[0063] Step S641: Based on the optimization decision results, obtain a set of optimizable methods;

[0064] Step S642: Obtain the set of optimization costs based on the set of optimizable methods;

[0065] Step S643: Obtain the preset optimized value-added;

[0066] Step S644: Based on the preset optimization increment, determine the optimization cost set and obtain the optimization method that satisfies the preset optimization increment;

[0067] Step S645: Send the optimization method that satisfies the preset optimization value-added to the relevant management personnel for decision-making, and obtain the optimization execution instruction based on the feedback information from the relevant management personnel.

[0068] To elaborate further, before obtaining the optimization execution instruction, it is necessary to further select the optimal optimization method. Based on the optimization decision result, a set of optimizable methods is obtained. The cost required for optimizing each optimization method in the set of optimizable methods is statistically analyzed to obtain an optimization cost set. A preset optimization increment (the preset optimization increment is a preset parameter index) is obtained. Based on the preset optimization increment, the optimization cost set is judged to obtain the optimization method that satisfies the preset optimization increment (the optimization method that satisfies the preset optimization increment and has the lowest cumulative optimization cost). For example, the preset optimization increment is 10 (the preset optimization increment of 10 is a proportional conversion for ease of understanding of the solution; similar expressions exist in the example and can be used for analogy). The first method has a cost of 9, and its cost optimization increment is 10; the second method has a cost of 5, and its cost optimization increment is 7; the third method has a cost of 3, and its cost optimization increment is 4. A preferred combination of the second and third methods is determined (the cost of combining the second and third methods is 8, and the cost optimization increment is 11; the combination of the second and third methods satisfies the preset optimization increment). The optimization method satisfying the preset optimization increment is sent to relevant management personnel for decision-making. Feedback from these personnel yields the optimization execution instruction. Further selection is performed to determine the optimization method satisfying the preset optimization increment, providing support for ensuring the rationality of the optimization execution instruction.

[0069] In summary, the power grid operation optimization method and system based on electronic dispatch provided in this application have the following technical effects:

[0070] By employing a grid operation optimization management system, this application provides a grid operation optimization method and system based on electronic dispatch. This method achieves the technical effect of improving the accuracy of grid operation optimization management by conducting energy consumption assessment based on field data, determining targeted optimization schemes, selecting the best optimization scheme, and optimizing the target grid. It acquires basic equipment components of the target grid, monitors data, obtains real-time power operation data, performs visualization distribution, acquires multi-level power operation data, inputs it into the equipment energy consumption analysis model to obtain energy consumption analysis results, inputs it into the optimization decision tree to obtain optimization decision results, and optimizes the target grid.

[0071] By performing deviation analysis on the differential energy consumption data to obtain a deviation set, and then acquiring N differential energy consumption data points that are greater than or equal to the preset deviation set, identifying the corresponding N power grid devices, and determining the output of the energy consumption analysis results, a foundation is provided for targeted optimization of devices with excessive energy consumption in the target power grid.

[0072] By employing methods such as determining the characteristics to be optimized based on equipment performance degradation index, equipment environmental overheating index, and equipment overload index, and then calculating the cost required for optimization, the optimization cost is obtained. The optimized parameters are then simulated and tested to output the optimization increment. When the optimization cost is less than the optimization increment, an optimization execution command is obtained. Effective measures are identified to ensure the feasibility of optimizing the target power grid operation.

[0073] Example 2

[0074] Based on the same inventive concept as the electronic dispatch-based power grid operation optimization method in the foregoing embodiments, such as Figure 4 As shown, this application provides a power grid operation optimization system based on electronic dispatching, wherein the system includes:

[0075] Equipment component acquisition unit 11, the equipment component acquisition unit 11 is used to connect to the power grid operation optimization management system to acquire the basic equipment components of the target power grid;

[0076] Data monitoring unit 12 is used to monitor the basic equipment components based on the data acquisition device and obtain real-time power operation data;

[0077] The operation data acquisition unit 13 is used to acquire multi-level power operation data by visualizing the distribution of the real-time power operation data;

[0078] Energy consumption analysis unit 14 is used to input the multi-level power operation data into the equipment energy consumption analysis model and obtain energy consumption analysis results based on the equipment energy consumption analysis model.

[0079] The decision result acquisition unit 15 is used to input the energy consumption analysis results into the optimization decision tree and acquire the optimization decision results according to the optimization decision tree.

[0080] The optimization execution unit 16 is used to optimize the target power grid based on the optimization decision result.

[0081] Furthermore, the system includes:

[0082] The operation data input unit is used to input the multi-level power operation data into the equipment energy consumption analysis model, wherein the equipment energy consumption analysis model includes an energy consumption identification layer, an energy consumption comparison layer, and an energy consumption output layer.

[0083] An energy consumption data identification unit is used to identify energy consumption data of the multi-level power operation data according to the energy consumption identification layer in the equipment energy consumption analysis model, and output real-time energy consumption data.

[0084] The energy consumption difference comparison unit is used to compare the real-time energy consumption data with the energy consumption comparison database embedded in the energy consumption comparison layer, and output the difference energy consumption data.

[0085] An analysis result output unit is used to output the energy consumption analysis result through the energy consumption output layer, using the difference energy consumption data as the result.

[0086] Furthermore, the system includes:

[0087] A simulation model generation unit is used to generate a power grid simulation model by performing initial performance modeling on all devices in the target power grid.

[0088] A simulation test unit is used to perform equipment operation simulation tests based on the power grid simulation model and obtain simulation test data.

[0089] An energy consumption data acquisition unit is used to acquire simulated energy consumption data based on the simulated test data, wherein the simulated energy consumption data is energy consumption data based on initial performance conditions;

[0090] An energy consumption difference comparison unit is used to compare energy consumption differences using the simulated energy consumption data as the energy consumption comparison database.

[0091] Furthermore, the system includes:

[0092] A deviation analysis unit is used to perform deviation analysis on the differential energy consumption data to obtain a deviation set, wherein the deviation set corresponds to the device corresponding to the differential energy consumption data;

[0093] A differential energy consumption acquisition unit is used to acquire N differential energy consumption data that are greater than or equal to a preset deviation set.

[0094] A data identification unit is used to identify N corresponding power grid devices based on the N differential energy consumption data.

[0095] The result output unit is used to output the energy consumption analysis results of the N power grid devices.

[0096] Furthermore, the system includes:

[0097] An analysis result input unit is used to input the energy consumption analysis results into an optimization decision tree, wherein the optimization decision tree includes equipment performance degradation characteristics, equipment environmental overheating characteristics, and equipment overload characteristics;

[0098] An index acquisition unit is used to analyze the input energy consumption analysis results based on the optimization decision tree to obtain the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index.

[0099] The decision result acquisition unit is used to acquire the optimization decision result based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index.

[0100] Furthermore, the system includes:

[0101] The feature acquisition unit is used to determine the features to be optimized based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index.

[0102] A cost statistics unit is used to perform cost statistics for optimization based on the feature to be optimized, and to obtain the optimization cost.

[0103] A simulation testing unit is used to perform simulation testing with the optimized parameters of the feature to be optimized, and output the optimized value-added.

[0104] An execution instruction acquisition unit is configured to acquire an optimization execution instruction when the optimization cost is less than the optimization increment.

[0105] Furthermore, the system includes:

[0106] An optimization method acquisition unit is configured to acquire a set of optimizable methods based on the optimization decision result.

[0107] An optimization cost acquisition unit is configured to acquire an optimization cost set based on the set of optimizable methods.

[0108] An optimized value-added acquisition unit is used to acquire a preset optimized value-added.

[0109] An optimization method acquisition unit is used to determine the optimization cost set based on the preset optimization increment, and to acquire an optimization method that satisfies the preset optimization increment.

[0110] The decision feedback execution unit is used to send the optimization method that satisfies the preset optimization value-added to the relevant management personnel for decision-making, and obtain the optimization execution instruction from the feedback information of the relevant management personnel.

[0111] This specification and accompanying drawings are merely illustrative examples of this application, and various modifications and combinations can be made thereto without departing from the spirit and scope of this application. If such modifications and variations fall within the scope of the claims and their equivalents, this application intends to include these modifications and variations.

Claims

1. A power grid operation optimization method based on electronic dispatching, characterized in that, The method is applied to a power grid operation optimization management system, the system being communicatively connected to a data acquisition device, and the method includes: Connect to the power grid operation optimization management system to obtain the basic equipment components of the target power grid; Based on the data acquisition device, the basic equipment components are monitored to obtain real-time power operation data; By visualizing and distributing the real-time power operation data, multi-level power operation data can be obtained; The multi-level power operation data is input into the equipment energy consumption analysis model. Based on the equipment energy consumption analysis model, the energy consumption analysis results are obtained. The equipment energy consumption analysis model includes an energy consumption identification layer, an energy consumption comparison layer, and an energy consumption output layer. Based on the energy consumption identification layer in the equipment energy consumption analysis model, energy consumption data is identified for the multi-level power operation data, and real-time energy consumption data is output. The real-time energy consumption data is compared with the energy consumption comparison database obtained by power grid simulation model embedded in the energy consumption comparison layer, and the difference energy consumption data is output. The energy consumption difference data is used as the energy consumption analysis result and output through the energy consumption output layer; The energy consumption analysis results are input into the optimization decision tree, and the optimization decision results are obtained based on the optimization decision tree, including: The energy consumption analysis results are input into an optimization decision tree, which includes equipment performance degradation characteristics, equipment environmental overheating characteristics, and equipment overload characteristics. Equipment performance degradation characteristics are used as the first classification decision characteristics, equipment environmental overheating characteristics as the second classification decision characteristics, and equipment overload characteristics as the third classification decision characteristics. The first, second, and third classification decision characteristics are used as internal nodes of the optimization decision tree. By calculating their information entropy, the feature with the highest entropy value is prioritized for decision-making, and the level of the multi-level classification decision characteristics is determined. The optimization decision tree is recursively constructed in this way until the last feature leaf node cannot be further divided, indicating that the classification decision is completed, thus forming the optimization decision tree. The energy consumption analysis results are analyzed based on the optimized decision tree to obtain the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index. Find the intersection of the equipment performance degradation index and the equipment environmental overheating index, and combine the intersection of the equipment performance degradation index and the equipment environmental overheating index with the equipment overload index to determine the optimization decision result; Based on the optimization decision results, the target power grid is optimized.

2. The method as described in claim 1, characterized in that, The method further includes: A power grid simulation model is generated by performing initial performance modeling on all devices in the target power grid. Based on the power grid simulation model, equipment operation simulation tests are conducted to obtain simulation test data; Based on the simulated test data, simulated energy consumption data is obtained, wherein the simulated energy consumption data is energy consumption data based on initial performance conditions; The simulated energy consumption data is used as the energy consumption comparison database for energy consumption difference comparison.

3. The method as described in claim 1, characterized in that, The method further includes: Deviation analysis is performed on the differential energy consumption data to obtain a deviation set, wherein the deviation set corresponds to the device corresponding to the differential energy consumption data; Obtain N energy consumption data points with deviation values ​​greater than or equal to a preset deviation set; Based on the N differential energy consumption data, identify the corresponding N power grid devices; The energy consumption analysis results of the N power grid devices are output.

4. The method as described in claim 1, characterized in that, Based on the optimization decision results, the target power grid is optimized, and the method further includes: Based on the equipment performance degradation index, the equipment environmental overheating index, and the equipment overload index, the features to be optimized are determined. The cost required for optimization is calculated based on the features to be optimized, and the optimization cost is obtained. The optimized parameters based on the features to be optimized are used for simulation testing, and the optimized value-added is output. When the optimization cost is less than the optimization increment, an optimization execution instruction is obtained.

5. The method as described in claim 4, characterized in that, The method further includes: Based on the optimization decision results, obtain a set of optimizable methods; Based on the set of optimizable methods, obtain the set of optimization costs; Obtain preset optimized value-added features; Based on the preset optimization increment, the set of optimization costs is judged to obtain the optimization method that satisfies the preset optimization increment; The optimization method that satisfies the preset optimization value is sent to the relevant management personnel for decision-making, and the optimization execution instruction is obtained from the feedback information of the relevant management personnel.

6. A power grid operation optimization system based on electronic dispatch, used to implement the method according to any one of claims 1-5, characterized in that, The system includes: An equipment component acquisition unit is used to connect to the power grid operation optimization management system to acquire the basic equipment components of the target power grid. A data monitoring unit is used to monitor the basic equipment components based on a data acquisition device and obtain real-time power operation data. The operation data acquisition unit is used to acquire multi-level power operation data by visualizing and distributing the real-time power operation data; An energy consumption analysis unit is used to input the multi-level power operation data into the equipment energy consumption analysis model and obtain energy consumption analysis results based on the equipment energy consumption analysis model. A decision result acquisition unit is used to input the energy consumption analysis results into an optimization decision tree and acquire optimization decision results based on the optimization decision tree. An optimization execution unit is configured to optimize the target power grid based on the optimization decision results.

Images