Transformer load adjusting method and device, equipment and storage medium

Abstract

The invention relates to the technical field of load regulation, in particular to a transformer load regulation method and device, equipment and a storage medium. The method comprises the following steps: identifying downstream electric equipment of a current transformer, and marking the downstream electric equipment as an electric equipment node; carrying out real-time load monitoring on the electric equipment nodes, and carrying out multi-period load characteristic analysis to obtain a multi-period load curve of each electric equipment node; carrying out multi-time-point discretization processing on the multi-period load curve of each power utilization node, and carrying out node-by-node load change trend analysis to generate load fluctuation trend data of each node; performing current flow direction logic analysis on the nodes of the electric equipment so as to generate node flow direction logic data; and performing topology connection reconstruction based on the node flow logic data, and constructing a node topology distribution network. According to the invention, efficient and balanced transformer load control is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of load regulation, and in particular to a transformer load regulation method, device, equipment and storage medium. Background Art

[0002] With the continuous development of industrial automation, transformers, as core equipment in power systems, are also facing new challenges in load management. Traditional transformer load regulation methods often rely on manual monitoring and fixed regulation strategies, which are difficult to adapt to the increasingly complex load characteristics of modern power systems. There is often a problem of low transformer load regulation efficiency, which leads to load imbalance.

[0003] In modern power systems, the power demand of various electrical equipment is uneven in time and space, resulting in load imbalance within the power supply range of the transformer. On the one hand, the load in some areas will increase suddenly, exceeding the power supply capacity of the transformer, resulting in load shortage; on the other hand, the load in other areas is low, resulting in resource waste. Traditional unified load control methods are difficult to accurately identify and adjust this local load imbalance problem.

[0004] At the same time, with the rapid increase in the types and number of power-consuming equipment, the load structure downstream of the transformer has become increasingly complex. Different types of power-consuming equipment have different requirements for power supply quality, and a single load control strategy is difficult to take into account the personalized needs of all users. In addition, the state of the power-consuming equipment itself also changes dynamically, bringing new difficulties to transformer load management. In order to meet the complex and changeable load characteristics of modern power systems, an intelligent transformer load adjustment method is urgently needed. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a transformer load adjustment method, device, equipment and storage medium to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a method for adjusting a transformer load, comprising the following steps: Step S1: Identify the downstream power consumption equipment of the current transformer and mark it as a power consumption equipment node; perform real-time load monitoring on the power consumption equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power consumption node; Step S2: Perform multi-time point discretization processing on the multi-period load curve of each power consumption node, and perform load change trend analysis on each node to generate load fluctuation trend data for each node; Step S3: Performing a current flow logic analysis on the nodes of the power-consuming equipment to generate node flow logic data; reconstructing the topological connection based on the node flow logic data to construct a node topology distribution network; Step S4: The load fluctuation trend data of each node is used to predict the node load demand of the node topology distribution network, and the load shortage area is divided to extract the load shortage area network; Step S5: performing load compensation calculation on the load shortage area network to obtain the demand compensation value of each shortage node; performing dynamic load scheduling priority analysis on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; Step S6: Perform iterative load scheduling analysis on the load shortage area network according to the shortage node scheduling priority, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

[0007] The present invention also provides a transformer load adjustment device, comprising: The load characteristic module is used to identify the downstream power-consuming equipment of the current transformer and mark it as a power-consuming equipment node; perform real-time load monitoring on the power-consuming equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power-consuming node; The load trend module is used to discretize the multi-period load curve of each power consumption node into multiple time points, analyze the load change trend of each node, and generate the load fluctuation trend data of each node; The topology reconstruction module is used to perform current flow logic analysis on the nodes of the power-consuming equipment, thereby generating node flow logic data; based on the node flow logic data, the topology connection is reconstructed to construct a node topology distribution network; The load demand prediction module is used to predict the node load demand of the node topology distribution network based on the load fluctuation trend data of each node, and divide the load shortage area to extract the load shortage area network; The load compensation module is used to calculate the load compensation for the load shortage area network to obtain the demand compensation value of each shortage node; the dynamic load scheduling priority analysis is performed on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; The load scheduling optimization module is used to perform iterative load scheduling analysis on the load-scarce regional network according to the scheduling priority of the scarce nodes, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

[0008] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above-mentioned transformer load adjustment methods when executing the computer program.

[0009] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods for adjusting the transformer load are implemented.

[0010] The beneficial effects of the present invention are as follows: by real-time monitoring of the load of the power-consuming equipment nodes, it helps to monitor the power consumption of the system, and promptly discovers load anomalies or overloads; by analyzing the load characteristics of multiple time periods, it understands the load conditions of each power-consuming node, and provides data support for subsequent load regulation; it discretizes the load curve and analyzes the load change trend to predict the development trend of the node load, and helps plan future load regulation measures; it generates load fluctuation trend data to help system administrators better understand the fluctuation of the node load, and provides a basis for load scheduling; it reveals the current transmission relationship between nodes through current flow logic analysis and topological connection reconstruction, optimizes load distribution and scheduling, and constructs a node topology distribution network to help the system understand the correlation and influence between nodes, and to provide a basis for load scheduling; Load scheduling provides more accurate information, and predicts load demand based on load fluctuation trend data to help predict areas with load shortages, take measures in advance to avoid load problems, and divide the network into load shortage areas to help system administrators focus on high-load areas, prioritize load adjustment and compensation, and determine the demand compensation value and scheduling priority of scarce nodes through load compensation calculation and priority analysis, reasonably allocate resources and optimize scheduling plans. Dynamic load scheduling priority analysis helps the system automatically adjust the load, improve the system's load balancing and stability, build a dynamic load scheduling engine to achieve automated load adjustment and scheduling, improve the system's response speed and efficiency, and continuously improve the load scheduling strategy through iterative load scheduling analysis and parameter optimization to ensure that the system runs in the best state. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of the steps of a transformer load adjustment method of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0012] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0013] The present application example provides a transformer load adjustment method, device, equipment and storage medium. The execution subjects of the transformer load adjustment method, device, equipment and storage medium include but are not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0014] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a transformer load adjustment method of the present invention. In this example, the steps of the method include: Step S1: Identify the downstream power consumption equipment of the current transformer and mark it as a power consumption equipment node; perform real-time load monitoring on the power consumption equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power consumption node; In this embodiment, the distribution of various types of electrical equipment within the power supply range of the transformer is fully understood through the topological information of the distribution system, and these electrical equipment are numbered and marked to establish a complete list of power nodes. These node information provides basic data support for subsequent load characteristic analysis and network topology modeling. Smart meters or sensor equipment are installed at each power node to collect power load data of the node in real time, continuously monitor changes in node load, and form complete time series data. The load data of each power node is segmented according to different time scales (such as day, week, and month), and the load change curve in each time period is analyzed for its characteristic indicators, such as peak value, mean value, fluctuation amplitude, etc.

[0015] Step S2: Perform multi-time point discretization processing on the multi-period load curve of each power consumption node, and perform load change trend analysis on each node to generate load fluctuation trend data for each node; In this embodiment, according to the time series data of the load of each node, discrete sampling is performed at fixed time intervals (such as 30 minutes or 1 hour) to form a set of discrete data sets reflecting the load status of the node at different time points. This discretization processing provides structured input data for subsequent load trend analysis. For each power consumption node, the change pattern of its load data at different time points is analyzed, and the fluctuation trend of the node load is identified by using statistical analysis, time series prediction and other methods. Characteristic indicators such as peak-to-valley changes and periodic fluctuations are extracted to describe the dynamic change characteristics of the node load. The analysis results of the above-mentioned node load change trend are organized into a structured data report. For each power consumption node, key indicators such as the fluctuation amplitude, periodicity, and correlation of its load are recorded. This load fluctuation trend data provides an important basis for subsequent load prediction and dynamic regulation.

[0016] Step S3: Performing a current flow logic analysis on the nodes of the power-consuming equipment to generate node flow logic data; reconstructing the topological connection based on the node flow logic data to construct a node topology distribution network; In this embodiment, the power system topology information and current measurement data are used to analyze the current flow relationship between each node, identify the "upstream" and "downstream" connection relationship of each node, and form a node flow logic diagram. This current flow analysis between nodes provides basic data support for subsequent topology reconstruction. According to the node flow logic relationship, the algorithm is used to integrate and connect them to construct a network model that fully describes the topological distribution of power nodes within the power supply range of the transformer. The network model not only contains the spatial location information of each node, but also reflects the power connection relationship between them. The network model obtained by reconstructing the above topological connection is further optimized and integrated into a visualized node topology distribution network. The network model intuitively displays the spatial layout and power connection relationship of each power node within the power supply range of the transformer.

[0017] Step S4: The load fluctuation trend data of each node is used to predict the node load demand of the node topology distribution network, and the load shortage area is divided to extract the load shortage area network; In this embodiment, a load demand analysis is performed on each power-consuming device node in the node topology distribution network, and the current power load demand of each node is estimated by comprehensively considering factors such as node type and power. A short-term load demand forecast is performed based on the load fluctuation trend data of each node and the current load demand of the node. Time series analysis, machine learning and other technologies are used to predict the load demand change trend of each node within a certain period of time in the future (such as 1 hour, 6 hours). Based on the node load demand prediction data, aggregation and analysis are performed according to spatial position to identify peak and valley areas of load demand within the power supply range of the transformer, forming a global distribution feature of the load demand. Combined with the obtained load demand distribution data, the node topology distribution network is analyzed and screened to identify regional node sets with current or short-term load demand shortages, and extract the sub-network topology structure of these load-scarce areas as the focus of subsequent dynamic adjustment.

[0018] Step S5: performing load compensation calculation on the load shortage area network to obtain the demand compensation value of each shortage node; performing dynamic load scheduling priority analysis on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; In this embodiment, in combination with the load shortage regional network, the specific load demand status of each node is further analyzed, and the nodes with serious load demand shortage at present or in the short term are identified according to the node load demand prediction data. The maximum load capacity of the transformer is calculated based on the capacity parameters and working environment conditions of the transformer, and the maximum load power data that the transformer can provide is obtained, which provides a basis for subsequent load compensation. According to the nodes with load demand shortage, a comparison analysis is performed with the maximum power data of the transformer. Through the optimization algorithm, the load compensation amount required for each shortage node is calculated to meet its actual needs. In combination with the obtained real-time parameters of the power node load and the node topology distribution network, the current load level of each node is analyzed and compared with its maximum load capacity, and the load margin of the node is calculated to form a data set describing the remaining space of the load of each node in the entire network. The demand compensation value of each shortage node obtained is comprehensively analyzed with the node load margin data. Through the optimization algorithm, the dynamic scheduling priority of each shortage node is determined to maximize the satisfaction of the actual needs, and a data describing the scheduling priority of each shortage node is generated to provide a decision basis for the subsequent dynamic adjustment of the load.

[0019] Step S6: Perform iterative load scheduling analysis on the load shortage area network according to the shortage node scheduling priority, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

[0020] In this embodiment, according to the scheduling priority data of each scarce node, different load scheduling schemes are simulated through an iterative algorithm. For the load-scarce regional network, a variety of scheduling combinations are explored to generate several alternative dynamic load scheduling strategies. These scheduling strategies not only need to meet the compensation requirements of each node, but also need to consider the overall load balancing. The generated scheduling strategies are substituted into the constructed node topology distribution network for simulation testing, and the load distribution within the transformer power supply range under each strategy is analyzed, and the corresponding load balancing index is calculated to form an evaluation data set describing the load balancing of each alternative scheduling strategy. Combined with the obtained load balancing evaluation data, a multi-objective optimization algorithm is used to select the optimal dynamic load scheduling scheme. This strategy can not only meet the node load compensation requirements, but also ensure the optimization of the load distribution in the entire transformer power supply area. Finally, an executable optimal dynamic load scheduling strategy is determined. The obtained optimal scheduling strategy is further optimized and adjusted to various scheduling parameters, such as node compensation power, scheduling priority, etc., to construct an intelligent algorithm engine that automatically performs transformer load dynamic adjustment. The engine monitors the load status in real time and takes corresponding compensation and adjustment measures according to the situation to ensure load balancing in the transformer power supply area.

[0021] In this embodiment, refer to Figure 2, is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Identify the downstream power consumption equipment of the current transformer and mark it as a power consumption equipment node; Step S12: Perform real-time load monitoring on the power-consuming device nodes to obtain real-time load parameters of the power-consuming nodes; Step S13: cutting the real-time load parameters of the power consumption node into different time periods to obtain the node load parameters of multiple time periods; Step S14: performing multi-period load characteristic analysis on the node load parameters in multiple time periods, thereby obtaining multi-period load characteristic data; Step S15: performing time stamp sequential fitting processing on the multi-period load characteristic data to obtain a multi-period load curve of each power consumption node.

[0022] In this embodiment, after obtaining authorization from the user and the relevant platform, a list of all downstream power-consuming devices is obtained from the access information of the transformer or the network topology, and a unique node ID is assigned to each power-consuming device to ensure that each node is accurately identified and tracked in the system. The basic information of each power-consuming device node, including device type, rated power, access time, etc., is sorted out to form a power-consuming device node database. The corresponding load monitoring device is installed at the transformer end to collect the load current, voltage, power factor and other parameters of each power node in real time. These real-time load parameter data are collected and stored to provide basic data for subsequent time period load analysis. This step realizes dynamic monitoring of power nodes by deploying distributed load sensing units. The time period is defined as: Determine the time period for cutting, such as dividing by hours, days or weeks. According to the defined time period, cut the real-time load parameters and extract the load data in each time period. Organize the cut data into load parameter sets for multiple time periods to ensure that the statistical information of each time period is complete. Perform in-depth feature extraction and analysis on the load parameter data of nodes in each time period, including load characteristic indicators in multiple dimensions such as load fluctuation amplitude, load curve slope, and load peak-valley difference. Combining these characteristic indicators, form a multi-time period load characteristic database for each power consumption node to ensure that the multi-time period load characteristic data has accurate timestamp information and is arranged in chronological order. Use curve fitting algorithms (such as polynomial fitting, spline interpolation, etc.) to process the multi-time period load characteristic data to generate a smooth load curve. Save the generated load curve of each power consumption node in a graphic or data format for visualization and subsequent analysis.

[0023] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing multi-time point discretization processing on the multi-period load curve of each power consumption node to generate multiple node load sequences; Step S22: performing wavelet transform decomposition on multiple node load sequences to generate multi-scale node load features; Step S23: Calculating frequency components of different scales for the multi-scale node load characteristics to extract frequency components at multiple time-frequency levels; Step S24: performing frequency fluctuation analysis on frequency components at multiple time-frequency levels to obtain frequency fluctuation data of different scales; Step S25: Based on the frequency fluctuation data of different scales, the load change trend of each node is analyzed for each of the multiple node load sequences, and the load fluctuation trend data of each node is generated.

[0024] In this embodiment, a discretized time interval is determined, such as minutes, hours or other suitable time granularities, and the corresponding load value is extracted from the load curve of each power consumption node according to the set time interval to form a discretized load sequence. The generated multiple node load sequences are sorted and stored as structured data for subsequent analysis. A suitable mother wavelet (such as Haar wavelet, Daubechies wavelet, etc.) is selected to perform wavelet transform on the load sequence, and wavelet transform is applied to the load sequence of each power consumption node to decompose different scales and frequency components, and multi-scale node load characteristics are extracted from the wavelet transform results, and the coefficients at each scale are recorded. For each scale coefficient obtained by wavelet transform, its corresponding frequency component is calculated, and a time-frequency analysis tool (such as short-time Fourier transform) is used. Transformation) further analyzes the frequency components, extracts time-frequency features of different scales, organizes the extracted frequency components into structured data for subsequent analysis, extracts the fluctuation characteristics of each frequency level, and calculates the corresponding frequency fluctuation parameters, including fluctuation amplitude, fluctuation frequency, fluctuation stability and other indicators, to comprehensively characterize the frequency fluctuation characteristics of load changes. These frequency fluctuation data of different scales are the key basis for analyzing load trend changes. Select a suitable trend analysis model (such as moving average, linear regression, etc.) to analyze the load change trend. For each power node, calculate the load change trend based on the frequency fluctuation data, identify the rising, falling or stable state of the trend, and organize the generated load fluctuation trend data of each node into a structured format for subsequent visualization and reporting.

[0025] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: performing device type cluster analysis on the power-consuming device nodes to obtain the device node types; Step S32: performing inter-node connection analysis on the power-consuming device nodes based on the device node type to obtain the inter-node connection relationship; Step S33: performing a current flow logic analysis on the nodes of the power-consuming device, thereby generating node flow logic data; Step S34: performing logical dependency identification on the node flow logic data according to the connection relationship between the nodes to generate a node connection logic path; Step S35: performing global distribution analysis on the power-consuming device nodes to generate a device node location layout diagram; Step S36: Reconstruct the topological connection of the device node location layout diagram using the node connection logic path to construct a node topology distribution network.

[0026] In this embodiment, characteristic data of power-consuming device nodes are collected, including power, working status, usage time, etc., and features used for cluster analysis, such as device power and type, are determined to ensure that different types of devices can be effectively distinguished. Clustering algorithms (such as K-means, hierarchical clustering, etc.) are used to analyze power-consuming device nodes, identify different types of devices, organize clustering analysis results into data sets, mark the type of each device node, and analyze the connection patterns between nodes of different types. For example, lighting device nodes are concentrated on the same loop, while production equipment nodes have a more complex connection structure. Through this analysis of the connection relationship between nodes, a connection relationship data describing the node topology is formed, combined with the power supply topology of the transformer. , analyze the current flow logic of each power-consuming device node, including the inflow and outflow directions of the current, as well as the transmission path of the current between different nodes, etc., obtain the geographical location or layout information of the power-consuming device nodes, including X, Y coordinates, etc., use distribution analysis methods (such as heat map analysis) to evaluate the global distribution of device nodes, identify dense and sparse areas of equipment, and generate a device node location layout diagram based on the analysis results to display the distribution of each node in space. According to the connection logic path between nodes, design the topological structure of the device nodes, draw the connection relationship between nodes on the device node location layout diagram, form a topological distribution network, verify the accuracy of the constructed topological distribution network, and ensure that it reflects the actual device connection and flow relationship.

[0027] In this embodiment, step S4 includes the following steps: Step S41: Analyze the node power load demand of the node topology distribution network to generate the power load demand of each node; Step S42: performing node load demand prediction on the power load demand of each node based on the load fluctuation trend data of each node, and generating node load demand prediction data; Step S43: performing load demand distribution analysis on the node load demand prediction data to generate load demand distribution data; Step S44: dividing the node topology distribution network into load shortage areas according to the load demand distribution data to extract the load shortage area network.

[0028] In this embodiment, the indicators required for load demand analysis, such as average load, peak load and minimum load, are determined. For each node, its power load demand is calculated. Considering the equipment type, operating status and historical power consumption, the power load demand of each node is recorded in the data set for subsequent analysis. According to the load fluctuation trend data of each node, combined with the current load demand of the node, short-term load demand forecasting is performed. Time series analysis, machine learning and other technologies are used to predict the load demand change trend of each node within a certain period of time in the future (such as 1 hour, 6 hours). The point load demand forecast data is aggregated and analyzed according to the spatial position, and the peak and valley areas of the load demand within the power supply range of the transformer are identified to form the global distribution characteristics of the load demand. A data report describing the load demand distribution status of the entire network is generated, and the identification criteria for the load shortage area are determined, such as the load demand is lower than a certain threshold or the low percentile of the load demand distribution. According to the load demand distribution data, the node topology distribution network is divided to identify the load shortage area, and the identified load shortage area is organized into structured data to form a load shortage area network for subsequent optimization and resource allocation.

[0029] In this embodiment, step S5 includes the following steps: Step S51: marking load demand shortage nodes in the load shortage area network, and extracting multiple load demand shortage nodes; Step S52: Calculate the maximum load power of the transformer to obtain maximum load power data; Step S53: performing load compensation calculation on multiple load demand shortage nodes based on the maximum load power data to obtain a demand compensation value for each shortage node; Step S54: Calculating the load margin of each node in the node topology distribution network based on the real-time parameters of the power node load to obtain node load margin data; Step S55: Perform dynamic load scheduling priority analysis on the demand compensation value of each scarce node based on the node load margin data to obtain the scarce node scheduling priority. In this embodiment, according to the load shortage regional network, the specific load demand status of each node is further analyzed, and according to the node load demand prediction data, the nodes with serious load demand shortage at present or in the short term are identified, and these nodes with load demand shortage are marked and extracted as the key objects of subsequent dynamic adjustment. Based on the capacity parameters and working environment conditions of the transformer, the maximum load capacity of the transformer is calculated, and the maximum load power data that the transformer can provide is obtained to provide a basis for subsequent load compensation. The load compensation calculation model is determined, and the maximum load power of the transformer and the load demand of the shortage node are considered. For each load demand shortage node, its demand compensation value is calculated, which is usually the difference between its load demand and the current load. The current load level of each node is analyzed and compared with its maximum load capacity, and the load margin of the node is calculated. The analysis standard of the dynamic load scheduling priority is determined, such as load margin, demand compensation value and historical load fluctuation, etc. For each load demand shortage node, its scheduling priority is calculated using the analysis standard, and a weighted scoring method is usually adopted. Through the optimization algorithm, the dynamic scheduling priority of each shortage node is determined to maximize the actual demand.

[0030] In this embodiment, step S6 includes the following steps: Step S61: performing iterative load scheduling analysis on the load-scarce regional network according to the scheduling priority of the shortage nodes to generate multiple dynamic load scheduling strategies; Step S62: performing load balancing evaluation on multiple dynamic load scheduling strategies to generate a load balancing evaluation result for each strategy; Step S63: extracting the optimal dynamic load scheduling strategy based on the load balancing evaluation results of each strategy; Step S64: Optimize the load scheduling parameters of the optimal dynamic load scheduling strategy and build a dynamic load scheduling engine to perform transformer load adjustment operations.

[0031] In this embodiment, according to the scheduling priority of the scarce nodes, an initial load scheduling strategy is formulated, the load distribution target of each node is clarified, the load distribution is iteratively adjusted through simulation or algorithm (such as genetic algorithm, particle swarm optimization, etc.), the scheduling strategy is gradually improved, and evaluation indicators of load balancing are defined, such as the standard deviation of load distribution, the ratio of maximum load to minimum load, etc. For each dynamic load scheduling strategy, the corresponding load balancing evaluation index is calculated, and its load balancing effect is evaluated. The optimal dynamic load scheduling scheme is selected by a multi-objective optimization algorithm. This strategy can not only meet the node load compensation requirements, but also ensure the optimization of the load distribution in the entire transformer power supply area. A load scheduling parameter optimization model is designed, considering the operating characteristics and load regulation requirements of the transformer, and using optimization algorithms (such as gradient descent, simulated annealing, etc.) to adjust the parameters of the optimal dynamic load scheduling strategy to improve the flexibility and efficiency of scheduling. Based on the optimization results, a dynamic load scheduling engine is constructed, integrating scheduling logic and execution mechanism to ensure real-time response to load changes, execute the load regulation operation of the transformer, monitor the regulation effect and make necessary adjustments.

[0032] In this embodiment, the present invention further provides a transformer load adjustment device, comprising: The load characteristic module is used to identify the downstream power-consuming equipment of the current transformer and mark it as a power-consuming equipment node; perform real-time load monitoring on the power-consuming equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power-consuming node; The load trend module is used to discretize the multi-period load curve of each power consumption node into multiple time points, analyze the load change trend of each node, and generate the load fluctuation trend data of each node; The topology reconstruction module is used to perform current flow logic analysis on the nodes of the power-consuming equipment, thereby generating node flow logic data; based on the node flow logic data, the topology connection is reconstructed to construct a node topology distribution network; The load demand prediction module is used to predict the node load demand of the node topology distribution network based on the load fluctuation trend data of each node, and divide the load shortage area to extract the load shortage area network; The load compensation module is used to calculate the load compensation for the load shortage area network to obtain the demand compensation value of each shortage node; the dynamic load scheduling priority analysis is performed on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; The load scheduling optimization module is used to perform iterative load scheduling analysis on the load-scarce regional network according to the scheduling priority of the scarce nodes, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

[0033] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above-mentioned methods for adjusting the transformer load when executing the computer program.

[0034] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method steps for adjusting the transformer load described in any one of the above items are implemented.

[0035] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0036] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks. Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0037] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for adjusting transformer load, characterized in that: The following steps are involved: Step S1: Identify the downstream power consumption equipment of the current transformer and mark it as a power consumption equipment node; perform real-time load monitoring on the power consumption equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power consumption node; Step S2: Perform multi-time point discretization processing on the multi-period load curve of each power consumption node, and perform load change trend analysis on each node to generate load fluctuation trend data for each node; Step S3: Performing a current flow logic analysis on the nodes of the power-consuming equipment to generate node flow logic data; reconstructing the topological connection based on the node flow logic data to construct a node topology distribution network; Step S4: The load fluctuation trend data of each node is used to predict the node load demand of the node topology distribution network, and the load shortage area is divided to extract the load shortage area network; Step S5: performing load compensation calculation on the load shortage area network to obtain the demand compensation value of each shortage node; performing dynamic load scheduling priority analysis on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; Step S6: Perform iterative load scheduling analysis on the load shortage area network according to the shortage node scheduling priority, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

2. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Identify the downstream power consumption equipment of the current transformer and mark it as a power consumption equipment node; Step S12: Perform real-time load monitoring on the power-consuming device nodes to obtain real-time load parameters of the power-consuming nodes; Step S13: cutting the real-time load parameters of the power consumption node into different time periods to obtain the node load parameters of multiple time periods; Step S14: performing multi-period load characteristic analysis on the node load parameters in multiple time periods, thereby obtaining multi-period load characteristic data; Step S15: performing time stamp sequential fitting processing on the multi-period load characteristic data to obtain a multi-period load curve of each power consumption node.

3. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing multi-time point discretization processing on the multi-period load curve of each power consumption node to generate multiple node load sequences; Step S22: performing wavelet transform decomposition on multiple node load sequences to generate multi-scale node load features; Step S23: Calculating frequency components of different scales for the multi-scale node load characteristics to extract frequency components at multiple time-frequency levels; Step S24: performing frequency fluctuation analysis on frequency components at multiple time-frequency levels to obtain frequency fluctuation data of different scales; Step S25: Based on the frequency fluctuation data of different scales, the load change trend of each node is analyzed for each of the multiple node load sequences, and the load fluctuation trend data of each node is generated.

4. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing device type cluster analysis on the power-consuming device nodes to obtain the device node types; Step S32: performing inter-node connection analysis on the power-consuming device nodes based on the device node type to obtain the inter-node connection relationship; Step S33: performing a current flow logic analysis on the nodes of the power-consuming device, thereby generating node flow logic data; Step S34: performing logical dependency identification on the node flow logic data according to the connection relationship between the nodes to generate a node connection logic path; Step S35: performing global distribution analysis on the power-consuming device nodes to generate a device node location layout diagram; Step S36: Reconstruct the topological connection of the device node location layout diagram using the node connection logic path to construct a node topology distribution network.

5. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: Analyze the node power load demand of the node topology distribution network to generate the power load demand of each node; Step S42: performing node load demand prediction on the power load demand of each node based on the load fluctuation trend data of each node, and generating node load demand prediction data; Step S43: performing load demand distribution analysis on the node load demand prediction data to generate load demand distribution data; Step S44: dividing the node topology distribution network into load shortage areas according to the load demand distribution data to extract the load shortage area network.

6. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: marking load demand shortage nodes in the load shortage area network, and extracting multiple load demand shortage nodes; Step S52: Calculate the maximum load power of the transformer to obtain maximum load power data; Step S53: performing load compensation calculation on multiple load demand shortage nodes based on the maximum load power data to obtain a demand compensation value for each shortage node; Step S54: Calculating the load margin of each node in the node topology distribution network based on the real-time parameters of the power node load to obtain node load margin data; Step S55: Perform dynamic load scheduling priority analysis on the demand compensation value of each scarce node based on the node load margin data to obtain the scarce node scheduling priority.

7. The transformer load adjustment method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing iterative load scheduling analysis on the load-scarce regional network according to the scheduling priority of the shortage nodes to generate multiple dynamic load scheduling strategies; Step S62: performing load balancing evaluation on multiple dynamic load scheduling strategies to generate a load balancing evaluation result for each strategy; Step S63: extracting the optimal dynamic load scheduling strategy based on the load balancing evaluation results of each strategy; Step S64: Optimize the load scheduling parameters of the optimal dynamic load scheduling strategy and build a dynamic load scheduling engine to perform transformer load adjustment operations.

8. A transformer load adjustment device, characterized in that: The method for adjusting the transformer load according to claim 1 comprises: The load characteristic module is used to identify the downstream power-consuming equipment of the current transformer and mark it as a power-consuming equipment node; perform real-time load monitoring on the power-consuming equipment node and perform multi-period load characteristic analysis to obtain a multi-period load curve for each power-consuming node; The load trend module is used to discretize the multi-period load curve of each power consumption node into multiple time points, analyze the load change trend of each node, and generate the load fluctuation trend data of each node; The topology reconstruction module is used to perform current flow logic analysis on the nodes of the power-consuming equipment, thereby generating node flow logic data; based on the node flow logic data, the topology connection is reconstructed to construct a node topology distribution network; The load demand prediction module is used to predict the node load demand of the node topology distribution network based on the load fluctuation trend data of each node, and divide the load shortage area to extract the load shortage area network; The load compensation module is used to calculate the load compensation for the load shortage area network to obtain the demand compensation value of each shortage node; the dynamic load scheduling priority analysis is performed on the demand compensation value of each shortage node to obtain the shortage node scheduling priority; The load scheduling optimization module is used to perform iterative load scheduling analysis on the load-scarce regional network according to the scheduling priority of the scarce nodes, optimize the load scheduling parameters, and build a dynamic load scheduling engine to perform transformer load adjustment operations.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the transformer load adjustment method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the transformer load adjustment method according to any one of claims 1 to 7 are implemented.

Images