A smart decision-making management method for power grid load

Abstract

The present invention discloses a smart decision-making management method for power grid load, which belongs to the field of smart grid, wherein the method includes: performing digital twin modeling according to the power grid side; determining the corresponding load line when the power grid twin model receives multiple concurrent load management requests; performing overlap analysis on multiple load lines based on the power grid twin model; fitting multiple identified load lines to obtain the fitted load line network; determining an electric load control device for power grid load regulation, and determining a load tolerance interval according to the electric load control device; inputting the load tolerance interval into the smart path decision model, and optimizing in the load line network, and the electric load control device adjusts the load of the load line network according to the optimized route. The present application solves the technical problems in the prior art that the power grid load management has a slow response speed, low prediction accuracy and limited regulation capability, which leads to low power grid operation efficiency and insufficient stability.

Description

Technical Field

[0001] The present invention relates to the field of smart grids, and in particular to a smart decision-making management method for grid loads. Background Art

[0002] With the continuous increase in global energy demand and the increasing complexity of power systems, load management and regulation of power grids have become important tasks to ensure the stability and reliability of power supply. The challenges faced by modern power systems include rapid changes in load demand, volatility of renewable energy access, and complexity of power grid structure. These factors make it difficult for traditional load management methods to cope with complex situations in practical applications.

[0003] At present, power grid load management mainly relies on regular manual regulation and traditional load forecasting methods. These methods have problems such as slow response speed and low prediction accuracy, and are difficult to adapt to the rapidly changing load demands of modern power grids. Especially when facing multiple concurrent load management requests, existing load regulation strategies are often difficult to achieve global optimization, resulting in low power grid operation efficiency. In addition, the regulation capacity of power load control devices is limited, and the control range of load fluctuations is narrow, which further limits the flexible dispatching capabilities of the power grid. Summary of the invention

[0004] This application provides an intelligent decision-making management method for power grid load, aiming to solve the technical problems in the prior art of slow power grid load management response speed, low prediction accuracy and limited regulation ability, which lead to low power grid operation efficiency and insufficient stability.

[0005] In view of the above problems, the present application provides a smart decision-making management method for power grid load.

[0006] The present application provides a smart decision-making management method for power grid load, the method comprising performing digital twin modeling based on the power grid side and outputting a power grid twin model; when the power grid twin model receives multiple concurrent load management requests, determining the load lines corresponding to the multiple concurrent load management requests respectively, and outputting multiple load lines; performing overlap analysis on the multiple load lines based on the power grid twin model to obtain multiple identified load lines, wherein the identified load lines are load lines with overlapping relationships; fitting the multiple identified load lines to obtain a fitted load line network; determining an electric load control device for power grid load regulation, and determining a load tolerance interval based on the electric load control device; inputting the load tolerance interval into a smart path decision model, performing optimization in the load line network, and outputting a first optimized route, and the electric load control device performs load adjustment on the load line network according to the first optimized route.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Due to the adoption of digital twin modeling based on the power grid side, the output of the power grid twin model, and when receiving multiple concurrent load management requests, the load line corresponding to each request is determined, and the overlap analysis is performed to obtain the technical solution of the identified load line and the non-identified load line, which solves the technical problems of slow response speed, low prediction accuracy and limited regulation capacity of power grid load management in the prior art, resulting in low efficiency and insufficient stability of power grid operation. Through real-time monitoring and simulation of the digital twin model, load management requests can be quickly identified and processed, load adjustment paths can be optimized, and the accuracy and efficiency of load adjustment can be improved. In addition, through overlap analysis, overload and potential bottlenecks of load lines can be avoided to ensure the stable operation of the power grid. In the end, this technical solution achieved the technical effect of improving the efficiency of power grid operation, improving the reliability of power supply and response speed.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a smart decision-making management method for power grid load is provided for an embodiment of the present application;

[0011] Figure 2 A schematic flow chart of overlap analysis in a smart decision-making management method for power grid load is provided for an embodiment of the present application; DETAILED DESCRIPTION

[0012] The overall idea of ​​the technical solution provided by this application is as follows:

[0013] An embodiment of the present application provides a smart decision-making management method for power grid load.

[0014] By building a digital twin model of the power grid, the operation status of the power grid is reflected in real time, and when multiple concurrent load management requests are received, the load line corresponding to each request is determined. Then, overlap analysis is used to identify load lines with overlapping relationships and independent load lines, and the load management strategy is optimized. In this way, multiple load management requests can be quickly responded to and processed, the accuracy and efficiency of power grid load regulation can be improved, and the stable operation of the power grid under high load and emergency conditions can be ensured.

[0015] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0016] Examples, such as Figure 1 As shown, an embodiment of the present application provides a smart decision-making management method for power grid load, the method comprising:

[0017] Step S100: Perform digital twin modeling based on the power grid side and output the power grid twin model.

[0018] Specifically, the grid side refers to the power supply side of the power system, including the overall structure consisting of power plants, substations, transmission lines and distribution networks, which are used for the production and transmission of electricity.

[0019] First, by deploying sensors and data acquisition equipment on the grid side, the operating data of each part of the grid, such as voltage, current, load, etc., are obtained in real time. These data are transmitted to the data center for storage and processing through the Internet of Things technology. Next, the collected grid operation data is sorted, analyzed and modeled using big data analysis technology to form a virtual grid model, namely the grid twin model. When building the grid twin model, a variety of technologies and tools are used. For example, sensors are used to monitor the operating status of the grid in real time; Internet of Things technology is used for data transmission; big data analysis and machine learning algorithms are used for data processing and modeling. In addition, 3D modeling software and simulation tools (such as MATLAB and Simulink) can be used to create and verify virtual models.

[0020] Specifically, sensors are installed at key nodes such as power plants, substations, and transmission lines to collect data such as voltage, current, and temperature. For example, smart meters are installed at substations to monitor current and voltage in real time. Data is transmitted to a central data processing system using IoT technologies (such as LoRa and NB-IoT). For example, sensor data distributed in different locations is centralized in a data center using a LoRa network. Massive data is cleaned and analyzed using big data processing platforms (such as Hadoop and Spark), and modeled using machine learning algorithms (such as neural networks and support vector machines). For example, historical data is used to train machine learning models to predict load changes in the power grid. Models are verified and optimized using simulation tools (such as MATLAB and Simulink) to ensure that the models accurately reflect the actual conditions of the power grid. For example, Simulink is used to simulate power grid failure scenarios to verify the responsiveness of the model.

[0021] Through this step, the final generated grid twin model can reflect the operating status of the grid in real time, help grid operators to monitor status, predict faults and optimize scheduling, and improve the operating efficiency and reliability of the grid.

[0022] Step S200: When the power grid twin model receives multiple concurrent load management requests, it determines the load lines corresponding to the multiple concurrent load management requests respectively, and outputs multiple load lines.

[0023] Specifically, concurrent load management requests refer to multiple load adjustment requests from different users or different regions in the same time period, which are triggered by load increase or decrease. Load lines refer to the lines used to transmit electricity in the power grid, including transmission lines and distribution lines.

[0024] The power grid twin model receives load management requests from different regions or users in real time. These requests include requests for load increase, load reduction, or load transfer. For each load management request, its specific content is parsed, including the type of request (such as load increase, load reduction), request time window, load demand, and abnormal line location. According to the parsed request content, the load line corresponding to each request is determined. First, the abnormal line location corresponding to the request is identified, and the line start node and end node are determined. According to the line start node and end node, the load line corresponding to each request is calculated.

[0025] The calculated load lines are output as response results to the power dispatch center or load management system. Multiple concurrent load management requests correspond to different load lines, and the system needs to record and manage these line information separately.

[0026] Through this step, the power grid can efficiently and accurately respond to multiple concurrent load management requests to ensure stable and reliable power supply.

[0027] Step S300: performing an overlap analysis on the multiple load lines based on the power grid twin model to obtain multiple identified load lines, wherein the identified load lines are load lines with overlapping relationships.

[0028] Specifically, overlap analysis refers to analyzing multiple load lines to determine which lines have crossover or common relationships physically or electrically. Identified load lines refer to those load lines with overlapping relationships determined by overlap analysis, that is, lines that share resources or paths at certain nodes or sections.

[0029] First, the line network structure of the power grid is extracted from the power grid twin model, including information on all transmission lines and distribution lines. This information usually includes the starting point, end point, nodes passed through, and capacity of the line. Based on the extracted power grid line network, multiple load lines are analyzed for overlap. The specific method is to analyze the intersection or overlap of each line in terms of space and electrical characteristics. The overlap index of each line is calculated, which is a quantitative indicator to measure the extent to which two lines have an overlapping relationship. Lines with an overlap index greater than a preset threshold are identified, and the identified load lines with overlapping relationships are identified.

[0030] This step can identify the load lines with overlapping relationships in the power grid, thereby optimizing load regulation and management to avoid large-scale grid instability caused by load changes or failures. The power grid twin model provides precise data support, making overlap analysis more accurate and efficient.

[0031] Step 400: Fit the multiple identified load lines to obtain a fitted load line network.

[0032] Specifically, first, collect the information of all identified load lines from the results of overlap analysis. This information includes the starting point, end point, nodes passed, path length, load capacity, etc. of each line. For example, obtain the detailed data of these lines from the identified load lines A, B, and C. Use mathematical models or optimization algorithms to fit the identified load lines. Common methods include least squares method, linear regression, network optimization algorithm, etc. The purpose of these methods is to find a set of optimal paths so that the load line network of the power grid has the lowest loss and the highest stability while meeting the load demand. According to the established mathematical model, the identified load lines are fitted and calculated. Specifically, first, clarify the definition and objectives of the problem, such as optimizing the load lines of the power grid to reduce losses and improve efficiency. Then, collect relevant data, such as the starting point, end point, path length, and load capacity of each line. Next, select a suitable mathematical method or algorithm, such as least squares method, linear regression, or network optimization algorithm. According to the characteristics of the problem, set constraints and objective functions, such as minimizing the total line length or maximizing the load balance. Next, establish equations or inequalities to represent these constraints and objectives to form a complete mathematical model. Finally, the optimal solution is obtained through calculations using a solution algorithm (such as iterative optimization or linear programming), and the accuracy and reliability of the model are verified, and adjustments and optimizations are made based on actual data and simulation results. The entire process requires continuous iteration and improvement to ensure the practical application effect of the model.

[0033] The results of the fitting calculations are integrated to generate an optimized load line network. This new network structure should reduce redundancy and overlap and improve the efficiency and reliability of power transmission. For example, through fitting, the lines A, B, and C that originally passed through three different substations are integrated into an optimized line that passes through two substations.

[0034] By fitting the identified load lines, the load line network of the power grid can be effectively simplified and the operation efficiency and stability of the power grid can be improved. This process uses mathematical modeling and optimization algorithms to make the design of load lines more scientific and reasonable.

[0035] Step S500: determining an electric load control device for regulating the load of a power grid, and determining a load tolerance range according to the electric load control device.

[0036] Specifically, power load control devices refer to equipment used to monitor and adjust power grid loads, such as automatic regulators, load controllers, and intelligent switches. These devices can automatically adjust power supply and load demand according to the operating status of the power grid. Load tolerance range refers to the load fluctuation range allowed by power load control devices during the adjustment process.

[0037] First, according to the actual needs and regulation targets of the power grid, select appropriate power load control devices. Collect relevant technical parameters of the selected power load control devices. Determine the load fluctuation range of each power load control device based on the collected parameters. The load fluctuation range indicates the allowable range of variation of the device when adjusting the load. Combined with the load fluctuation range of each device, calculate the load tolerance range of the entire power grid. The load tolerance range indicates the total load variation range allowed by the power grid system during the load regulation process.

[0038] Through this step, the power load control device can be reasonably selected and configured, and the load tolerance range can be accurately calculated to ensure the flexibility and stability of power grid load regulation.

[0039] Step S600: input the load tolerance interval into the intelligent path decision model, perform optimization in the load line network, output a first optimal route, and the power load control device adjusts the load of the load line network according to the first optimal route.

[0040] Specifically, the first optimization route refers to the optimal load regulation path calculated by the intelligent path decision model, which is used to guide the power load control device to perform load adjustment.

[0041] First, the calculated load tolerance interval is input as a constraint into the smart path decision model. The smart path decision model is based on an optimization algorithm and is used to find the optimal load regulation path in the load line network. Through iterative optimization, the first optimal path is finally output. The first optimal path is the optimized optimal load regulation path, which is used to guide the power load control device to adjust the load. The power load control device adjusts the load of the load line network according to the first optimal path.

[0042] Through this step, the power grid can achieve the optimal load regulation path selection under complex load change conditions, thereby improving the power grid operation efficiency and stability.

[0043] Furthermore, the load lines corresponding to the multiple concurrent load management requests are determined, and the method includes: identifying the abnormal line positions corresponding to the multiple concurrent load management requests; determining the line start node and the line end node according to the abnormal line positions; and calculating the load lines corresponding to the multiple concurrent load management requests according to the line start node and the line end node.

[0044] Specifically, the line start node refers to the starting point of the load line, which is usually the location where the load demand occurs or the access point of the substation. The line termination node refers to the end point of the load line, which is usually the main transmission line of the power grid or the end user.

[0045] First, for each concurrent load management request, identify the corresponding abnormal line location. The abnormal line location refers to the specific line that needs to be loaded due to changes in load demand or failures. For example, a residential area needs to increase load management requests because the load during peak hours exceeds the normal range. The power supply line of the residential area is the abnormal line location.

[0046] Based on the identified abnormal line location, determine the starting node and ending node of the load line. The starting node is usually the location where the load demand occurs, such as a distribution transformer in a residential area or a substation in an industrial area; the ending node is the connection point of the load line, usually a main transmission line or substation. For example, if the request comes from an industrial park, the starting node is the main substation of the park, and the ending node is the substation connected to the main transmission line.

[0047] According to the determined start and end nodes, the load lines corresponding to each concurrent load management request are calculated. Line calculation and analysis are performed using the Geographic Information System (GIS) and the power grid topology map. For example, the GIS system is used to determine the optimal path from the residential distribution transformer to the main transmission line and calculate the load capacity on the path.

[0048] For example, the power grid twin model receives concurrent load management requests from three areas. Residential area A requests to increase the load, and the abnormal line location is the main power supply line of residential area A. Industrial park B requests to reduce the load, and the abnormal line location is the substation line of park B. Commercial area C requests load transfer, and the abnormal line location is the power supply line of commercial area C. Residential area A: The starting node is the distribution transformer of residential area A, and the ending node is the main transmission line. Industrial park B: The starting node is the substation of park B, and the ending node is the substation connected to the main transmission line. Commercial area C: The starting node is the distribution station of commercial area C, and the ending node is the main transmission line. Using the GIS system and the power grid topology map, the optimal path from the distribution transformer of residential area A to the main transmission line is calculated, and load line 1 is obtained. The path from the substation of park B to the main transmission line is calculated to obtain load line 2. The path from the distribution station of commercial area C to the main transmission line is calculated to obtain load line 3.

[0049] Through this step, the power grid can efficiently identify and process multiple concurrent load management requests to ensure the stability and reliability of power supply. This process uses GIS technology, power grid topology analysis and digital twin models to calculate and optimize load lines in real time and accurately.

[0050] Further, such as Figure 2 As shown, based on the power grid twin model, the multiple load lines are analyzed for overlap, and the method includes: obtaining a power grid line network corresponding to the power grid twin model; performing overlap analysis on the multiple load lines according to the power grid line network to obtain a line overlap index; marking the lines that are greater than the preset line overlap index to obtain multiple marked load lines and non-marked load lines, wherein the marked load lines are load lines with overlapping relationships, and the non-marked load lines are load lines with independent relationships.

[0051] Specifically, the power grid line network refers to the topological structure of all transmission lines and distribution lines in the power grid, including the starting point, end point, nodes passed through, and capacity of the line. Non-identified load lines refer to load lines that are determined to be independent in the overlap analysis, that is, lines that do not share resources or paths with other lines.

[0052] First, the line network structure of the power grid is extracted from the power grid twin model, including the information of all transmission lines and distribution lines. This information usually includes the starting point, end point, nodes passed through, and capacity of the line. For example, the topological structure of all transmission lines and distribution lines in a city is obtained from the power grid twin model of a city. Based on the extracted power grid line network, multiple load lines are analyzed for overlap. The specific method is to analyze the intersection or overlap of each line in terms of space and electrical characteristics. For example, if two lines share the same substation or transmission tower on a certain path, they have an overlapping relationship on this path.

[0053] Overlap analysis can be performed using matrix operations or graph theory algorithms to identify the degree of overlap between each pair of routes. The overlap index of each route is calculated, which is a quantitative indicator to measure the extent to which two routes overlap. For example, if two routes overlap on 10% of the path, their overlap index can be set to 0.1.

[0054] Lines with overlapping indexes greater than the preset threshold are marked to identify the marked load lines with overlapping relationships. For example, if the overlapping index threshold is set to 0.05, all lines with overlapping indexes greater than 0.05 are marked as load lines with overlapping relationships. At the same time, lines with overlapping indexes less than or equal to 0.05 are regarded as non-marked load lines, indicating that they are independent in the power grid and do not share resources or paths with other lines.

[0055] For example, detailed information of all transmission and distribution lines in a city is extracted from the power grid twin model of a city. Assume that the extracted information includes the topological structure of line A, line B, and line C. Perform overlap analysis on line A, line B, and line C. Assume that the analysis finds that line A and line B share the same substation on a certain path, while line B and line C share the same transmission tower on another path. The overlap index of line A and line B is calculated to be 0.1, and the overlap index of line B and line C is 0.08. The overlap index threshold is set to 0.05, so line A and line B, as well as line B and line C are identified as load lines with overlapping relationships, while other lines with overlap indexes less than or equal to 0.05 are identified as non-identified load lines.

[0056] Through this step, load lines with overlapping relationships in the power grid can be identified, thereby optimizing load regulation and management to avoid large-scale grid instability caused by load changes or failures. The power grid twin model provides precise data support, making overlap analysis more accurate and efficient.

[0057] Furthermore, based on the power load control device, a load tolerance range is determined, and the method includes: collecting relevant parameters of the power load control device, including maximum load capacity, minimum load capacity, rated load capacity and load response speed; determining the load fluctuation range of the power load control device based on the relevant parameters; calculating the load tolerance range based on the load fluctuation range, wherein the load tolerance range represents the load fluctuation range allowed by the power load control device during the adjustment process.

[0058] Specifically, the maximum load capacity refers to the maximum power load that the power load control device can withstand under its normal operating conditions. The minimum load capacity refers to the minimum power load that the power load control device can withstand under its normal operating conditions. The rated load capacity refers to the power load that the power load control device can withstand under its optimal performance. The load response speed refers to the reaction speed of the power load control device when adjusting the power load, that is, the amount of load that can be adjusted per unit time. The load fluctuation range refers to the range within which the load can vary during the normal operation of the power load control device. The load tolerance range refers to the load fluctuation range allowed by the power load control device during the adjustment process, that is, the range from the minimum load to the maximum load.

[0059] First, all technical parameters of the power load control device are obtained. These parameters include maximum load capacity, minimum load capacity, rated load capacity and load response speed. Based on the collected parameters, the load fluctuation range of each power load control device is calculated. Combined with the load fluctuation range of each power load control device, the overall load tolerance range of the power grid is calculated.

[0060] According to the parameters of the power load control device, the load fluctuation range is calculated. The load fluctuation range indicates the load variation range allowed during the regulation process, and its calculation formula is: in, is the load fluctuation range, is the maximum load capacity, is the minimum load capacity.

[0061] According to the determined load fluctuation range, calculate the load tolerance range. The calculation formula is: in, is the load tolerance range, is the rated load capacity, is the load fluctuation range.

[0062] Through this step, the power load control device can be reasonably selected and configured, and the load tolerance range can be accurately calculated to ensure the flexibility and stability of the power grid load regulation. This process uses detailed technical parameters and mathematical calculations to ensure the scientificity and effectiveness of load regulation.

[0063] Furthermore, the load tolerance interval is input into the intelligent path decision model, and optimization is performed in the load line network. The method includes: generating a coordinate position set according to the node positions in the load line network; the intelligent path decision model uses the load tolerance interval as a constraint condition and the coordinate position set as an optimization space, and introduces an objective function to calculate the load regulation effect of the initialized line; when the load regulation effect does not meet the preset load regulation effect, iterative optimization is performed until a preset number of rounds is reached, and then the first optimization route is output.

[0064] Specifically, the node location refers to a specific location point in the load line network, usually representing a substation, load center or other key node. The coordinate location set refers to the coordinate set of all node locations in the load line network, which is used for path optimization calculation.

[0065] According to the node positions in the load line network, a coordinate set containing all node positions is generated. The calculated load tolerance interval is input into the smart path decision model as a constraint. In the smart path decision model, an objective function is introduced to evaluate the load regulation effect of the initial line. The objective function usually considers the following factors: Load utilization: evaluates the efficiency of load use on the path. Line capacity: ensures that the line is not overloaded during the load regulation process. Load demand matching: ensures that the regulation path can meet the load demand.

[0066] Use the objective function to evaluate the generated initial load regulation line and calculate its load regulation effect. For example, the initial line is from node A to node D, and the load utilization, line capacity and load demand matching degree of the path are evaluated. If the load regulation effect of the initial line does not meet the preset load regulation effect standard, iterative optimization is performed. By adjusting the path and parameters, the load regulation effect is gradually optimized until the preset optimization rounds are reached or the load regulation effect standard is met. After multiple iterative optimizations, the first optimal route is finally output. This route is the optimal path in terms of load regulation effect, and is used to guide the power load control device to perform actual load adjustment. For example, the first optimal route finally determined is from node A to node B and then to node D.

[0067] Through this step, an optimal path can be found in the load line network. Through load adjustment on this path, the load management efficiency and stability of the entire network can be improved. The intelligent path decision model introduces load tolerance intervals and objective functions in the load adjustment process. Through iterative optimization, it ensures that the final selected path can effectively improve the load condition of the entire power grid.

[0068] Furthermore, the expression of the intelligent path decision model is as follows: ;in, is the first optimal route, which is the optimal path after optimization by the intelligent path decision model. is the current path, is the objective function, which is used to evaluate the load regulation effect of the current path considering load utilization and load demand. For the The load demand of a load management request, is the load capacity of line k, indicating the path The maximum load that the middle line k can carry, is the sum of all load requests in the current path, is the minimum value of the load tolerance range, is the maximum value of the load tolerance interval. Specifically, the calculated load tolerance interval Input as constraints into the smart path decision model. Generate the initial path: Generate a set of coordinate positions based on the node positions in the load line network, and generate the initial load regulation line on this basis. Calculate the load regulation effect: Use the objective function to evaluate the generated initial load regulation line and calculate its load regulation effect. The objective function considers factors such as load utilization and load demand matching. If the load regulation effect of the initial line does not meet the preset standard, iterative optimization is performed to optimize the load regulation effect by continuously adjusting the path until the preset rounds are reached or the load regulation effect standard is met. Finally, the first optimal route is output This line is the optimal path in terms of load regulation effect and is used to guide the power load control device to perform actual load adjustment.

[0069] Furthermore, the method also includes: establishing a load adjustment list based on the non-identification load lines; obtaining load impact indicators of each non-identification load line in the non-identification load lines; sequentially updating the load adjustment list according to the load impact indicators to obtain an updated load adjustment list; and the power load control device independently adjusts the load of the non-identification load lines according to the updated load adjustment list.

[0070] Specifically, the load impact index refers to an indicator that measures the impact of each load line in the power grid, usually considering the impact of load demand, line capacity and load changes on the stability of the power grid. Independent load adjustment refers to the separate load adjustment operation of non-identified load lines to ensure that the load changes of these lines will not have an adverse impact on other lines.

[0071] First, based on the results of the overlap analysis, all non-identified load lines are recorded in the load adjustment list. This list contains each non-identified load line and its basic information, such as the line start point, end point, load demand, etc. The load impact index is calculated for each non-identified load line. The load impact index measures the impact of the line in the power grid, usually based on factors such as load demand, line capacity, and the impact of load changes on power grid stability. For example, lines with larger load demands have higher load impact indexes. According to the calculated load impact index, the load adjustment list is updated sequentially. Lines with higher load impact indexes are prioritized at the front of the list so that they can be adjusted first. The power load control device performs independent load adjustments on the non-identified load lines one by one according to the updated load adjustment list. This process ensures that the load adjustment of each non-identified load line will not have an adverse effect on other lines, improving the operational stability and reliability of the power grid.

[0072] Through this step, the load regulation of non-identified load lines can be efficiently managed to ensure the stability and efficient operation of the power grid. This method can effectively respond to grid load changes and improve the reliability of power supply by establishing and updating the load regulation list and adjusting independent loads according to priority.

[0073] Furthermore, when the power grid twin model receives multiple concurrent load management requests, each concurrent load management request includes request content, load demand, request time window, and abnormal line location.

[0074] Specifically, the power grid twin model receives multiple load management requests from different users or regions in real time. These requests are usually issued in the same time period and involve different load adjustment requirements. For example, during peak power consumption periods, multiple regions simultaneously issue requests for load increase. For each concurrent load management request, parse its specific content. The request content usually includes the type of load adjustment (such as increasing load, reducing load), the purpose (such as meeting peak power demand or responding to sudden failures), etc. According to the parsed request content, determine the specific load demand for each request. For example, a residential area requests to increase the load by 500kW from 2pm to 4pm. Each request has a time window that needs to be met, that is, the load adjustment must be completed within this time period. For example, an industrial park requests to reduce the load by 300kW from 8pm to 10pm. Determine the abnormal line location involved in each load management request. The abnormal line location refers to the specific line that requires load management due to changes in load demand or failures. For example, a load adjustment request for a commercial area involves the main power supply line of the area.

[0075] Based on the parsed request content, load demand, time window and abnormal line location, multiple concurrent load management requests are processed comprehensively. Based on this information, the power grid twin model can optimize the load adjustment plan to ensure that the power grid remains stable and efficient while meeting all requests.

[0076] In summary, the intelligent decision-making management method for power grid load provided by the embodiment of the present application has the following technical effects:

[0077] 1. By conducting digital twin modeling based on the power grid side and outputting a power grid twin model, the operating status of the power grid can be reflected in real time and accurately. The digital twin model uses a large amount of real-time data and advanced simulation technology to provide a virtual power grid operating environment. This enables power grid operators to test and optimize various load management strategies without interfering with the actual power grid operation, thereby improving the operating efficiency and reliability of the power grid. In addition, when multiple concurrent load management requests are received, the model can quickly identify and process these requests to ensure the stability and response speed of the power grid under high load and emergency situations.

[0078] 2. By identifying the abnormal line locations corresponding to concurrent load management requests and determining the starting and ending nodes of the lines, the load lines that need to be adjusted can be accurately located. The load lines are calculated according to these nodes, making the processing of load management requests more efficient and accurate. This can effectively avoid errors in the load adjustment process, reduce the risks of power grid operation, and improve the reliability of power supply. Especially in the face of complex power grid structures and diverse load requests, the speed and accuracy of load adjustment can be significantly improved.

[0079] 3. Based on the grid twin model, overlap analysis can identify load lines with overlapping relationships and obtain marked load lines and non-marked load lines. Through this analysis, the load management strategy of the grid can be optimized to avoid overload and potential power transmission bottlenecks, thereby improving the overall efficiency and stability of the grid. In addition, as an independent load management object, non-marked load lines can perform independent load adjustments, further improving the flexibility and response speed of load management.

[0080] 4. Through the expression of the intelligent path decision model, the load regulation path can be accurately optimized, taking into account multiple factors such as load utilization, load demand and line capacity. The application of the objective function makes the evaluation of the load regulation effect more comprehensive and scientific. Through iterative optimization, the efficiency and reliability of the load regulation path can be continuously improved. The first optimal route finally output provides clear operating guidance for the power load control device to ensure the optimization of the actual load adjustment effect.

[0081] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0082] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A smart decision-making management method for power grid load, characterized in that: The method comprises: Conduct digital twin modeling based on the power grid side and output the power grid twin model; When the power grid twin model receives multiple concurrent load management requests, it determines the load lines corresponding to the multiple concurrent load management requests respectively, and outputs multiple load lines; Based on the power grid twin model, an overlap analysis is performed on the multiple load lines to obtain multiple identified load lines, wherein the identified load lines are load lines with overlapping relationships; Fitting the multiple identified load lines to obtain a fitted load line network; Determining an electric load control device for performing grid load regulation, and determining a load tolerance range according to the electric load control device; The load tolerance interval is input into the intelligent path decision model, optimization is performed in the load line network, and a first optimal route is output, and the power load control device adjusts the load of the load line network according to the first optimal route; Wherein, according to the power load control device, the load tolerance interval is determined, and the method includes: Collecting relevant parameters of the power load control device, including maximum load capacity, minimum load capacity, rated load capacity and load response speed; Determining a load fluctuation range of the power load control device according to the relevant parameters; Calculating a load tolerance interval according to the load fluctuation range, wherein the load tolerance interval represents a load fluctuation range allowed by the power load control device during the adjustment process; The load tolerance interval is input into the intelligent path decision model, and optimization is performed in the load line network. The method includes: generating a set of coordinate positions according to node positions in the load line network; The intelligent path decision model uses the load tolerance range as a constraint condition, uses the coordinate position set as an optimization space, and introduces an objective function to calculate the load regulation effect of the initialization line; When the load regulation effect does not meet the preset load regulation effect, iterative optimization is performed until a preset round is reached, and a first optimization route is output.

2. The method according to claim 1, characterized in that Determining the load lines corresponding to the multiple concurrent load management requests, respectively, the method comprising: Identifying abnormal line locations corresponding to the multiple concurrent load management requests respectively; According to the abnormal line position, determining the line starting node and the line ending node; According to the line start node and the line end node, load lines corresponding to the multiple concurrent load management requests are calculated.

3. The method according to claim 1, characterized in that Based on the power grid twin model, overlapping analysis is performed on the multiple load lines, and the method includes: Obtaining a power grid line network corresponding to the power grid twin model; Performing overlap analysis on the multiple load lines according to the power grid line network to obtain a line overlap index; Lines with a value greater than a preset line overlap index are identified to obtain a plurality of identified load lines and non-identified load lines, wherein the identified load lines are load lines with an overlapping relationship, and the non-identified load lines are load lines with an independent relationship.

4. The method according to claim 1, characterized in that The expression of the intelligent path decision model is as follows: ;in, is the first optimal route, which is the optimal path after optimization by the intelligent path decision model. is the current path, is the objective function, which is used to evaluate the load regulation effect of the current path considering load utilization and load demand. For the The load demand of a load management request, For Line The load capacity of the path Middle Line The maximum load that can be carried, is the sum of all load requests in the current path, is the minimum value of the load tolerance range, is the maximum value of the load tolerance range.

5. The method according to claim 3, characterized in that The method further comprises: Establishing a load adjustment list according to the non-identified load lines; Obtaining a load impact index of each non-identification load line in the non-identification load lines; The load adjustment list is sequentially updated according to the load impact index to obtain an updated load adjustment list; The electric power load control device performs independent load adjustment on the non-identified load line according to the updated load adjustment list.

6. The method according to claim 1, characterized in that When the power grid twin model receives multiple concurrent load management requests, each concurrent load management request includes request content, load demand, request time window, and abnormal line location.

Images