Intelligent control management platform for power supply and demand matching

Abstract

The present invention provides an intelligent control management platform for matching power supply and demand, which relates to the technical field of matching power supply and demand, including: a trend analysis module for generating regional power consumption forecast data; a feature extraction module for collecting power supply data of the power grid, performing common feature extraction to generate regional power supply forecast data; a power supply decision module for making power supply decisions to generate an initial power supply control plan; an environmental prediction module for performing environmental prediction to obtain regional environmental prediction data; a power supply impact analysis module for performing power supply impact analysis to obtain environmental-power supply impact analysis results; a control scheme adjustment module for adjusting the initial power supply control plan to obtain an adjusted power supply control plan; and a power supply control module for performing power supply control. The present invention solves the technical problem that the traditional method of matching power supply and demand is often based on fixed models or historical data, which makes it difficult to cope with real-time changes in power consumption and power supply, resulting in an imbalance between supply and demand.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply and demand matching, and in particular to an intelligent control management platform for power supply and demand matching. Background Art

[0002] There are still some problems with the existing technology for matching electricity supply and demand. On the one hand, traditional electricity supply and demand matching is often based on fixed models or historical data, which makes it difficult to cope with real-time changes in electricity consumption and power supply, leading to problems such as supply and demand imbalance or energy waste. On the other hand, environmental factors have a great impact on the power supply system. Changes in weather, temperature, etc. may cause the power supply system to become less efficient or even fail. Traditional methods are often unable to effectively deal with these impacts, resulting in poor stability and flexibility of the power supply system. Summary of the invention

[0003] This application provides an intelligent control management platform for electricity supply and demand matching, aiming to solve the technical problem that traditional methods of electricity supply and demand matching are often based on fixed models or historical data, which are difficult to cope with real-time changes in electricity consumption and power supply, resulting in an imbalance in supply and demand.

[0004] The present application discloses an intelligent control management platform for matching power supply and demand, and the platform includes: a trend analysis module, the trend analysis module is used to connect to the power consumption side, collect regional power consumption historical data of the target area in a preset historical time zone, perform trend analysis on the regional power consumption historical data, and generate regional power consumption forecast data for a preset future time zone according to the trend analysis results; a feature extraction module, the feature extraction module is used to connect to the power supply side, collect power supply data of the target area, perform common feature extraction on the power supply data of the power grid, and generate regional power supply forecast data; a power supply decision module, the power supply decision module is used to make the power supply of the target area in the preset future time zone according to the regional power consumption forecast data and the regional power supply forecast data. decision-making, generating an initial power supply control plan; an environment prediction module, the environment prediction module is used to perform environment prediction on the target area according to the preset future time zone, and obtain regional environment prediction data; a power supply impact analysis module, the power supply impact analysis module is used to perform power supply impact analysis on the regional environment prediction data through an environment impact topology network, and obtain an environment-power supply impact analysis result; a control scheme adjustment module, the control scheme adjustment module is used to adjust the initial power supply control plan based on the environment-power supply impact analysis result, and obtain an adjusted power supply control plan; a power supply control module, the power supply control module is used to perform power supply control of the target area in the preset future time zone according to the adjusted power supply control plan.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] By connecting the power consumption side and the power supply side, collecting historical data and conducting trend analysis and feature extraction, generating forecast data and making power supply decisions, the dynamic matching of power consumption and power supply is realized, and the balance of supply and demand and energy utilization efficiency are improved; through environmental prediction and impact analysis, combined with topological network for impact analysis and adjustment, the power supply system can respond to environmental changes in a timely manner, improving the stability and reliability of the power supply system; through the analysis of environmental impact and supply and demand conditions, combined with intelligent algorithms to adjust and optimize the power supply control scheme, the power supply control is made more intelligent and flexible, and the response speed and adaptability of the power supply system are improved. In general, the intelligent control management platform for power supply and demand matching effectively solves the problems of static, inflexible and insensitive to environmental changes in traditional power supply and demand matching through technical means such as data collection, forecast analysis, impact analysis and intelligent control, and improves the reliability, stability and energy utilization efficiency of the power supply system.

[0007] 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

[0008] Figure 1 A schematic diagram of the structure of an intelligent control management platform for matching power supply and demand is provided for the embodiment of the present application.

[0009] Figure 2 A schematic diagram of the execution flow of a power supply impact analysis module in an intelligent control management platform for power supply and demand matching is provided for an embodiment of the present application.

[0010] Explanation of the reference numerals: trend analysis module 10 , feature extraction module 20 , power supply decision module 30 , environment prediction module 40 , power supply impact analysis module 50 , control scheme adjustment module 60 , power supply control module 70 . DETAILED DESCRIPTION

[0011] The embodiments of the present application provide an intelligent control management platform for power supply and demand matching, thereby solving the technical problem that traditional power supply and demand matching methods are often based on fixed models or historical data, which are difficult to cope with real-time changes in power consumption and power supply, resulting in an imbalance in supply and demand.

[0012] 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.

[0013] like Figure 1 As shown, the embodiment of the present application provides an intelligent control management platform for power supply and demand matching, and the platform includes:

[0014] The trend analysis module 10 is used to connect to the power consumption side, collect the regional power consumption historical data of the target area in the preset historical time zone, perform trend analysis on the regional power consumption historical data, and generate regional power consumption forecast data for the preset future time zone according to the trend analysis results.

[0015] Establish a data collection system and connect it to various sensors on the electricity consumption side. These sensors are used to record electricity consumption data in real time and collect regional electricity consumption data of the target area in a preset historical time zone. The historical time zone can be a period of time in the past, such as daily electricity consumption or monthly electricity consumption in the past year. Clean the collected electricity consumption data to remove outliers and noise data, for example, remove abnormal electricity consumption data caused by external interference.

[0016] The processed electricity consumption data is arranged in chronological order for time series analysis. Commonly used methods include moving average, exponential smoothing, autoregressive model, etc. For example, a regression model is established, with electricity consumption data as the dependent variable and time as the independent variable, to analyze the changing trend of electricity consumption. Based on the results of trend analysis, the electricity consumption in the preset future time zone, such as the next week or month, is predicted to generate regional electricity consumption forecast data, providing reliable data support for electricity supply and demand matching.

[0017] The feature extraction module 20 is used to connect to the power supply side, collect power supply data of the target area, extract common features of the power supply data, and generate regional power supply prediction data.

[0018] Establish power system connections related to the power supply side, including data sources such as substations, distribution networks, and power stations, and collect power supply data from the power grid in the target area. These data include but are not limited to power generation data, distribution data, transmission data, real-time power supply parameters, historical power supply data, etc. Clean the collected power supply data to remove noise and outliers.

[0019] Extract useful features from the original data, such as using principal component analysis to reduce dimensionality, extract main features, and reduce data dimensions. The extracted features include time features, load features, power quality features, equipment status features, etc. Analyze the correlation between the features, screen out common features that have a greater impact on power supply, and select appropriate prediction models based on the common features, such as time series models, regression models, machine learning models, etc. For example, establish a regression model, use common features as independent variables, and power supply as dependent variable for prediction, use the trained model to predict the power supply in the preset future time zone, and generate regional power supply prediction data.

[0020] The power supply decision module 30 is used to make a power supply decision for the target area in the preset future time zone according to the regional power consumption forecast data and the regional power supply forecast data, and generate an initial power supply control plan.

[0021] Compare and analyze the regional electricity consumption forecast data with the regional power supply forecast data to determine the supply and demand relationship in the future time zone, including the following three situations: supply and demand balance, that is, the power supply capacity is roughly equal to the electricity demand. In this case, the existing power supply control plan can be maintained; supply exceeds demand, that is, the power supply capacity is greater than the electricity demand. In this case, the power generation capacity of the generator set can be appropriately reduced or the number of generator sets can be reduced to reduce resource waste, or the excess electricity can be used to charge the energy storage system for future use; supply is less than demand, that is, the power supply capacity is less than the electricity demand. In this case, the power load can be adjusted through peak shaving and valley filling measures, such as time-sharing power supply, peak-shifting power consumption, etc., or standby generator sets can be activated or the power generation capacity of existing generator sets can be increased.

[0022] Exemplarily, an optimization algorithm can be used to determine the optimal power supply plan and establish an objective function with the goal of minimizing the total power supply cost or maximizing the power supply benefit. Based on constraints such as power supply capacity, energy storage system capacity, and load demand, the power system simulation model can be used to simulate the effects of different power supply plans to seek the optimal plan. Based on the optimization results, an initial power supply control plan can be designed, including power generation scheduling, energy storage system management, load regulation, and other contents.

[0023] The environment prediction module 40 is used to perform environment prediction on the target area according to the preset future time zone to obtain regional environment prediction data.

[0024] Clarify the main objectives of environmental forecasting, such as predicting environmental factors that have an important impact on electricity demand and supply, such as temperature, humidity, wind speed, rainfall, solar radiation, etc., and collect historical environmental data of the target area. These data can be obtained from sources such as meteorological departments, environmental monitoring stations, and satellite remote sensing data.

[0025] Establish a prediction model, such as a time series model, a machine learning model, etc. Use historical environmental data to train the selected model, optimize the prediction performance by adjusting the model parameters, use a portion of the historical data as a validation set, evaluate the prediction performance of the model, and adjust the model parameters based on the evaluation results to improve the prediction accuracy. Use the trained model to predict the environmental data of the preset future time zone and generate regional environmental prediction data for the future time zone, including temperature, humidity, wind speed, rainfall, solar radiation, etc. in the next few days or weeks.

[0026] The power supply impact analysis module 50 is used to perform power supply impact analysis on the regional environmental prediction data through an environmental impact topology network to obtain an environment-power supply impact analysis result.

[0027] Collect historical environmental data and corresponding power supply and demand data, including environmental variables such as temperature, humidity, wind speed, rainfall, solar radiation, and power data such as power load, power generation, and power supply stability, and integrate environmental data with power data to form an environmental power supply impact record data set, which includes timestamps, environmental variables, and power variables.

[0028] The environmental power supply impact record data set is preprocessed, including data cleaning, normalization and standardization. The preprocessed data is subjected to principal component analysis to extract the main influencing factors, reduce the data dimension, improve the efficiency and accuracy of subsequent analysis, and obtain the environmental power supply impact characteristic data set.

[0029] Nodes are defined in the topological network, and each node represents an environmental variable or power variable, such as temperature, humidity, wind speed, power generation, load, etc. Edges are defined in the topological network, and each edge represents the influence relationship between two nodes, which can be expressed by correlation or causality. The correlation coefficient between each pair of nodes is calculated to determine the edge weight. The edge weight represents the intensity of the influence. Based on the definition of nodes and edges, an environmental impact topological network is constructed.

[0030] The regional environmental prediction data is input into the environmental impact topological network, and the topological network is used for propagation analysis to calculate the impact of environmental variables on power variables. Graph propagation algorithms, such as the influence propagation algorithm, can be used to analyze how changes in environmental variables affect power supply and obtain environmental-power supply impact analysis results. These results quantify the specific impact of environmental variables on power load, power generation, and power supply stability.

[0031] A control scheme adjustment module 60 is used to adjust the initial power supply control scheme based on the environment-power supply impact analysis result to obtain an adjusted power supply control scheme.

[0032] Based on the results of the environment-power supply impact analysis, determine the strategies that need to be adjusted. For example, if the temperature is expected to be high, the demand for electricity will increase, and it is necessary to increase power generation and adjust the power generation plan to ensure sufficient power supply; if the temperature is expected to be low, the demand for electricity will increase, similar to the high temperature weather strategy; and, based on wind speed and solar radiation forecasts, adjust wind and solar power generation plans.

[0033] Furthermore, the optimization algorithm is used to optimize the adjustment strategy, establish the objective function, such as minimizing the total power generation cost, maximizing the power supply reliability, etc., set the constraints, including power generation capacity, energy storage system capacity, load demand, etc., to optimize the adjusted power supply control plan, and output the optimized adjusted power supply control plan, including power generation plan, load management strategy, etc., to ensure the stable and efficient operation of the power supply system in the preset future time zone.

[0034] The power supply control module 70 is used to control the power supply of the target area in the preset future time zone according to the adjusted power supply control scheme.

[0035] In the preset future time zone, power supply control is executed according to the adjusted power supply control plan. The power generation plan is dynamically adjusted according to real-time data and environmental changes. For example, if the temperature is expected to rise sharply on a certain day, the power generation during peak hours will be increased, so as to realize scientific and effective power supply control of the target area in the preset future time zone and ensure the stability and efficiency of the power system.

[0036] Furthermore, if Figure 2 As shown, the power supply impact analysis module 50 is used to perform the following operation steps:

[0037] Retrieve an environmental power supply impact record data set; perform principal component analysis based on the environmental power supply impact record data set to obtain an environmental power supply impact feature data set; construct the environmental impact topology network based on the environmental power supply impact feature data set; input the regional environmental prediction data into the environmental impact topology network to obtain the environmental-power supply impact analysis result.

[0038] Principal component analysis (PCA) is a commonly used data dimension reduction and feature extraction method that can convert the original data set into a set of linearly independent principal components to reduce data dimensions and reveal the correlation between data. The environmental power supply impact record data set is standardized to ensure that the numerical range of each feature is similar to avoid the influence of different dimensions. Based on the standardized data set, the covariance matrix between the features is calculated. The covariance measures the degree of linear relationship between two variables. The covariance matrix is ​​decomposed by eigenvalue to obtain the eigenvalue and the corresponding eigenvector. The eigenvalue represents the variance of the principal component, and the eigenvector represents the direction of the principal component. The number of principal components retained is selected according to the size of the eigenvalue. Usually, the number of principal components retained can explain most of the data variance, such as retaining a cumulative variance contribution rate of 80% or 90%. Based on the selected number of principal components, the eigenvector is used to construct a transformation matrix, and the original data set is mapped to the new principal component space. The original data set is transformed by the principal component to obtain a new feature data set. These feature data sets are linear combinations of the principal components and can be used to describe the main characteristics of the original data.

[0039] The environmental impact topological network is constructed. Specifically, each environmental impact feature is taken as a node to represent the impact feature of an environmental factor. The connection relationship between the nodes is determined according to the correlation or impact relationship between the environmental factors. According to the correlation between the nodes, the structure of the environmental impact topological network is constructed, which can be a fully connected, partially connected or hierarchically connected structure. For the connected edges, the weight of the edge is determined according to the correlation to represent the degree of association between the environmental factors.

[0040] The environmental prediction data is standardized to ensure that it has the same data standard as the environmental characteristic data set used when constructing the environmental impact topological network. The standardized environmental prediction data is input into the constructed environmental impact topological network. Each node represents the impact characteristic of an environmental factor. The network propagation calculation is performed through the node and edge weights in the topological network. The degree of influence of each environmental factor on the power supply is calculated according to the network structure and weight. According to the result of the network propagation calculation, the result of the environment-power supply impact analysis is obtained, that is, the degree of influence or influence trend of different environmental factors on the power supply.

[0041] Furthermore, the initial power supply control scheme further includes a power supply node selection decision, and the platform further includes a power supply node selection decision module to perform the following operation steps:

[0042] Acquire power consumption equipment information on the power consumption side, wherein the power consumption equipment information includes equipment distribution information; divide the target area into a regional power grid grid according to the equipment distribution information, and obtain a regional power grid grid division result, wherein the regional power grid grid division result corresponds to the power supply node; evaluate the power supply economy of the power supply node according to the regional power consumption forecast data and the regional power grid grid division result; and obtain a selection decision of the power supply node by screening according to the power supply economy evaluation result.

[0043] Through monitoring equipment or data acquisition systems, relevant information of each electrical equipment in the target area is obtained, including equipment type, capacity, location, etc. Among them, equipment distribution information refers to the location and layout of each electrical equipment in the target area.

[0044] According to the geographical characteristics of the target area, the distribution of power equipment and the power supply requirements, the regional power grid division method is determined, including square grid division, hexagonal grid division, etc. According to the equipment distribution information and division method, the target area is divided into multiple power grids, each grid contains a certain number or type of power equipment, so as to facilitate the management of power supply. The divided power grids are matched with power supply nodes. Usually, each power grid corresponds to one or more power supply nodes, which are responsible for supplying power to the power equipment in the grid.

[0045] Determine the economic evaluation indicators of the power supply nodes, including cost indicators, efficiency indicators, etc., calculate the economic evaluation indicators of each power supply node according to the regional electricity consumption forecast data and the grid division results, for example, calculate the power supply cost, power loss, load balancing degree, etc. of the power supply node, compare the economic evaluation results of each power supply node, determine the economic level of the power supply node, screen out a candidate set of power supply nodes with better economy according to the economic evaluation results, and determine the final power supply node selection plan according to the optimization decision results.

[0046] Furthermore, the platform also includes a power supply economy evaluation module to perform the following operation steps:

[0047] According to the regional power consumption forecast data and the regional power grid division result, the power supply nodes are randomly allocated to generate multiple power supply node selection schemes; and a power supply economic evaluation function is constructed, wherein the power supply economic evaluation function is as follows:

[0048] ;

[0049] in, is the power supply economic evaluation coefficient, m is the number of power supply nodes, is the distance from the ith power supply node to the power-consuming device, is the power loss of the i-th power supply node, , are respectively the first weight and the second weight, and the sum of the two is 1; the multiple power supply node selection schemes are evaluated according to the power supply economy evaluation function, and the selection decision of the power supply node is obtained by screening according to the evaluation result.

[0050] Based on the grid division results, power supply nodes are randomly assigned to each power grid. A range or rule can be set to ensure the rationality of the random assignment. For example, only one node is assigned to each grid or nodes are assigned according to load size. According to different random assignment schemes, multiple power supply node selection schemes are generated. Each scheme contains different power supply node allocation situations, forming a diverse set of selection schemes.

[0051] The power supply economy evaluation function is as follows:

[0052] ;

[0053] in, , are the first weight and the second weight, respectively, which are used to adjust the weight of distance and power loss in the evaluation. When it is larger, it means that more attention is paid to the distance factor; When it is larger, more attention is paid to the power loss factor. Overall, this evaluation function gives a comprehensive economic evaluation value based on the set weights after considering the two factors of the distance from the power supply node to the power-consuming equipment and the power loss. By adjusting the proportion of the weights, the power supply plan can be optimized according to the specific situation to achieve a balance between economy and efficiency.

[0054] According to the constructed power supply economic evaluation function, each power supply node selection scheme is calculated and evaluated, that is, the distance and power loss from each power supply node to the power-consuming equipment in each scheme are calculated, and the economic evaluation coefficient of each scheme is calculated according to the evaluation function. The evaluation results are sorted to obtain the power supply node selection scheme with the best economic evaluation, so as to improve the economy and efficiency of the power system.

[0055] Furthermore, the platform also includes an energy storage side management module to perform the following operation steps:

[0056] Connect to the energy storage side to obtain the energy storage battery status parameters of the energy storage system; analyze the energy storage battery status parameters through the threshold control analysis model to obtain multiple dynamic charge and discharge threshold control schemes; collect basic data of the energy storage system to obtain a basic data set of the energy storage system; simulate and model the energy storage system based on the basic data set of the energy storage system to obtain a simulation model of the energy storage system; simulate the multiple dynamic charge and discharge threshold control schemes multiple times based on the energy storage system simulation model to obtain multiple groups of energy storage simulation operating condition data; screen the multiple dynamic charge and discharge threshold control schemes based on the multiple groups of energy storage simulation operating condition data to obtain dynamic charge and discharge threshold control decisions; and perform dynamic charge and discharge threshold control of the energy storage system based on the dynamic charge and discharge threshold control decisions.

[0057] Connected to the energy storage side, including the control interface or sensor data acquisition interface of the energy storage system, through the connected interface, obtain the status parameters of the battery in the energy storage system, including but not limited to current, voltage, temperature, charge and discharge status, SOC (State of Charge, battery charging status) and other parameters.

[0058] A threshold control analysis model for energy storage battery status parameters is established. This model includes multiple dynamic charge and discharge thresholds, which can be set according to the characteristics of the energy storage battery and actual needs, including charging threshold, discharging threshold, SOC threshold, temperature threshold, etc.

[0059] The acquired energy storage battery status parameters are input into the threshold control analysis model for analysis. The model performs real-time analysis on the battery status according to the set threshold. Based on the analysis results, multiple dynamic charge and discharge threshold control schemes are obtained. These schemes include adjusting the charge and discharge thresholds, SOC control, temperature control and other schemes according to actual conditions to achieve dynamic control of the energy storage system.

[0060] Collect basic parameters of the energy storage system, including but not limited to battery capacity, rated voltage, rated current, charge and discharge efficiency, battery type, charging rate, discharging rate, temperature characteristics, etc.; collect environmental conditions required for the operation of the energy storage system, such as temperature, humidity, air pressure, etc. These environmental factors will affect the performance of the energy storage system; collect data during the actual operation of the energy storage system, including the charging process, discharging process, load changes, environmental changes, etc. These data are used to establish a real simulation model.

[0061] The collected basic data is processed, including data cleaning, data classification, data format conversion, etc. According to the sorted data, a simulation model of the energy storage system is established using simulation software. This model can include a battery model, a charge and discharge control module, an environmental model, etc., to simulate the operation of the energy storage system under different working conditions.

[0062] Taking multiple dynamic charge and discharge threshold control schemes as the input parameters of the simulation, the simulation model of the energy storage system is simulated multiple times according to the set threshold control scheme. Each simulation can simulate different working conditions, including load changes, environmental changes, charge and discharge strategy changes, etc. The simulation results of each simulation are recorded, including battery status, charge and discharge efficiency, temperature changes, electric energy storage and release conditions, etc., to obtain multiple sets of energy storage simulation working condition data for evaluating the performance and control strategy of the energy storage system.

[0063] The collected multiple sets of energy storage simulation operating condition data are compared, and according to the comparison results, the dynamic charge and discharge threshold control scheme with excellent performance and high applicability is screened out to determine the final dynamic charge and discharge threshold control decision.

[0064] According to the dynamic charge and discharge threshold control decision, the charge and discharge threshold parameters in the energy storage system are set, including the charge threshold, discharge threshold, SOC control, temperature control, etc., to ensure that the energy storage system maintains high efficiency during the dynamic charge and discharge process.

[0065] Furthermore, the platform also includes a power dispatching control module to perform the following operation steps:

[0066] Generate a peak power consumption constraint based on the regional power consumption history data; obtain the predicted peak power consumption data for the peak power consumption time zone in the regional power consumption forecast data; determine whether the predicted peak power consumption data is greater than or equal to the peak power consumption constraint, and when greater than or equal to, generate a power dispatch control instruction, and perform power dispatch for the peak power consumption time zone according to the power dispatch control instruction.

[0067] The historical electricity consumption data of the area is analyzed, including the daily peak electricity consumption period, electricity consumption distribution, etc. Based on the historical data analysis results, peak electricity consumption constraints are formulated, including determining the peak electricity consumption period, peak electricity consumption threshold, etc.

[0068] Obtain the regional electricity consumption forecast data, including the forecast data for electricity consumption in a future period of time; determine the predicted peak electricity consumption time zone based on the electricity consumption forecast data, that is, predict the time period when future peak electricity consumption will occur; within the predicted peak electricity consumption time zone, obtain the predicted peak electricity consumption data, that is, predict the value of future peak electricity consumption.

[0069] The predicted peak power consumption data is compared with the peak power consumption constraint. If the predicted peak power consumption data is greater than or equal to the peak power consumption constraint, a power dispatching control instruction is generated. This instruction includes measures such as adjusting power supply, dispatching energy storage systems, and increasing power generation. According to the generated power dispatching control instruction, corresponding power dispatching operations are performed to meet the power demand in the peak power consumption time zone.

[0070] Furthermore, the platform also includes an early warning information generation module to perform the following operation steps:

[0071] When the predicted peak power consumption data is less than the peak power consumption constraint, a difference calculation is performed between the predicted peak power consumption data and the peak power consumption constraint to obtain the remaining peak power consumption data; and it is determined whether the remaining peak power consumption data meets the warning interval, and if so, a warning message is generated.

[0072] If the predicted peak power consumption data is less than the peak power consumption constraint, calculate the difference between the two to obtain the remaining peak power consumption data, set the warning interval of the remaining peak power consumption data, including the upper limit and the lower limit. The interval can be set according to the system requirements and actual conditions, and judge whether the calculated remaining peak power consumption data is within the warning interval. If the remaining peak power consumption data is not within the warning interval, it means that the system still has a certain amount of spare capacity and no immediate measures are needed. When the remaining peak power consumption data is within the warning interval, generate a warning message to remind relevant personnel or systems to make corresponding adjustments so that corresponding measures can be taken in time to ensure the safety and stability of the system operation.

[0073] Furthermore, the platform also includes a remaining time determination module to perform the following operation steps:

[0074] Determine whether the remaining time of the current time node in the peak power consumption time zone meets the preset time threshold; if so, do not generate the warning information.

[0075] Get the current time node, calculate the remaining time from the current time to the end of the peak power consumption time zone, and determine whether the remaining time meets the preset time threshold. If the remaining time is long enough and exceeds the preset time threshold, a warning message is generated. If the remaining time meets the preset time threshold, it means that there is not much time left and the peak power consumption time zone is about to be passed. In this case, no warning message is generated.

[0076] In summary, the intelligent control management platform for power supply and demand matching provided by the embodiments of the present application has the following technical effects:

[0077] 1. By connecting the power consumption side and the power supply side, collecting historical data and conducting trend analysis and feature extraction, generating forecast data and making power supply decisions, the dynamic matching of power consumption and power supply is achieved, and the balance of supply and demand and energy utilization efficiency are improved;

[0078] 2. Through environmental prediction and impact analysis, combined with topological network impact analysis and adjustment, the power supply system can respond to environmental changes in a timely manner, improving the stability and reliability of the power supply system;

[0079] 3. Through the analysis of environmental impact and supply and demand conditions, the power supply control scheme is adjusted and optimized in combination with intelligent algorithms, making the power supply control more intelligent and flexible, and improving the response speed and adaptability of the power supply system.

[0080] In general, this intelligent control management platform for electricity supply and demand matching effectively solves the problems of staticness, inflexibility and insensitivity to environmental changes in traditional electricity supply and demand matching through technical means such as data collection, predictive analysis, impact analysis and intelligent control, and improves the reliability, stability and energy utilization efficiency of the power supply system.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Intelligent control management platform for power supply and demand matching, characterized by: The platform includes: A trend analysis module, the trend analysis module is used to connect to the power consumption side, collect the regional power consumption historical data of the target area in the preset historical time zone, perform trend analysis on the regional power consumption historical data, and generate regional power consumption forecast data of the preset future time zone according to the trend analysis results; A feature extraction module, wherein the feature extraction module is used to connect to the power supply side, collect power supply data of the target area, extract common features of the power supply data of the target area, and generate regional power supply prediction data; A power supply decision module, the power supply decision module is used to make a power supply decision for the target area in the preset future time zone according to the regional power consumption forecast data and the regional power supply forecast data, and generate an initial power supply control plan; An environment prediction module, the environment prediction module is used to perform environment prediction on the target area according to the preset future time zone to obtain regional environment prediction data; A power supply impact analysis module, the power supply impact analysis module is used to perform power supply impact analysis on the regional environmental prediction data through an environmental impact topology network to obtain an environment-power supply impact analysis result; A control scheme adjustment module, the control scheme adjustment module is used to adjust the initial power supply control scheme based on the environment-power supply impact analysis result to obtain an adjusted power supply control scheme; A power supply control module, the power supply control module is used to perform power supply control of the target area in the preset future time zone according to the adjusted power supply control scheme; The platform also includes an energy storage side management module to perform the following operation steps: Connect to the energy storage side to obtain the energy storage battery status parameters of the energy storage system; Analyzing the state parameters of the energy storage battery through a threshold control analysis model to obtain multiple dynamic charge and discharge threshold control schemes; Collecting basic data of the energy storage system to obtain a basic data set of the energy storage system; Perform simulation modeling of the energy storage system based on the energy storage system basic data set to obtain an energy storage system simulation model; Based on the energy storage system simulation model, multiple simulations are performed on the multiple dynamic charge and discharge threshold control schemes to obtain multiple sets of energy storage simulation operating condition data; Screening the multiple dynamic charge and discharge threshold control schemes based on the multiple groups of energy storage simulation operating condition data to obtain a dynamic charge and discharge threshold control decision; Dynamic charge and discharge threshold control of the energy storage system is performed based on the dynamic charge and discharge threshold control decision.

2. The intelligent control management platform according to claim 1, characterized in that: The power supply impact analysis module is used to perform the following operation steps: Retrieve environmental power supply impact record data set; Performing principal component analysis based on the environmental power supply impact record data set to obtain an environmental power supply impact feature data set; Constructing the environmental impact topology network based on the environmental power supply impact feature data set; The regional environmental prediction data is input into the environmental impact topology network to obtain the environmental-power supply impact analysis result.

3. The intelligent control management platform according to claim 1, characterized in that: The initial power supply control scheme also includes a power supply node selection decision, and the platform also includes a power supply node selection decision module to perform the following operation steps: Acquiring power-consuming equipment information of the power-consuming side, wherein the power-consuming equipment information includes equipment distribution information; Performing regional power grid division of the target area according to the device distribution information to obtain a regional power grid division result, wherein the regional power grid division result corresponds to the power supply node; According to the regional power consumption forecast data and the regional power grid division result, the power supply economic efficiency evaluation of the power supply node is performed; The selection decision of the power supply node is obtained by screening according to the power supply economy evaluation result.

4. The intelligent control management platform according to claim 3, characterized in that: The platform also includes a power supply economic evaluation module to perform the following operation steps: According to the regional power consumption forecast data and the regional power grid division result, the power supply nodes are randomly allocated to generate multiple power supply node selection schemes; Construct a power supply economic evaluation function, wherein the power supply economic evaluation function is as follows: ； in, is the power supply economic evaluation coefficient, m is the number of power supply nodes, is the distance from the ith power supply node to the power-consuming device, is the power loss of the i-th power supply node, , are the first weight and the second weight respectively, and their sum is 1; The multiple power supply node selection schemes are evaluated according to the power supply economy evaluation function, and the selection decision of the power supply node is obtained by screening according to the evaluation result.

5. The intelligent control management platform according to claim 1, characterized in that: The platform also includes a power dispatch control module to perform the following operation steps: generating a peak power consumption constraint according to the power consumption history data of the area; Obtaining predicted peak power consumption data of the peak power consumption time zone in the regional power consumption prediction data; Determine whether the predicted peak power consumption data is greater than or equal to the peak power consumption constraint. If so, generate a power dispatch control instruction, and perform power dispatch in the peak power consumption time zone according to the power dispatch control instruction.

6. The intelligent control management platform according to claim 5, characterized in that: The platform also includes an early warning information generation module to perform the following operation steps: When the predicted peak power consumption data is less than the peak power consumption constraint, performing a difference calculation between the predicted peak power consumption data and the peak power consumption constraint to obtain remaining peak power consumption data; It is determined whether the remaining peak power consumption data meets the warning interval, and if so, a warning message is generated.

7. The intelligent control management platform according to claim 6, characterized in that: The platform also includes a remaining time judgment module to perform the following operation steps: Determine whether the remaining time of the current time node in the peak power consumption time zone meets the preset time threshold; If the conditions are met, the warning information will not be generated.

Images