CN117878925B - A method and system for controlling power transmission data of a smart grid - Google Patents

Abstract

The invention relates to a power transmission data control method and system of a smart grid. The method comprises the following steps: acquiring real-time power data and smart grid environment data; carrying out data fusion on the real-time power data and the intelligent power grid environment data to generate a comprehensive power environment data set; performing dynamic load curve conversion on the comprehensive power environment data set so as to generate a real-time comprehensive energy load curve; carrying out load peak value data extraction on the real-time comprehensive energy load curve based on a preset peak value screening quantity to obtain dynamic power load peak value data; and performing model training on the dynamic power load peak data to generate a power demand prediction model. According to the intelligent power grid, the accuracy, stability and reliability of the intelligent power grid are improved through comprehensive data processing, dynamic load curve conversion, load peak value data extraction and prediction models, equipment information acquisition and power grid adjustment, power grid nonlinear control and data visualization.

Description

A method and system for controlling power transmission data of a smart grid

Technical Field

The present invention relates to the technical field of power data control, and in particular to a power transmission data control method and system for a smart grid.

Background technique

Traditional power systems are the starting point for the development of smart grid technology. These systems rely on centralized power plants to deliver electricity to consumers, have limited data control methods, and rely mainly on manual operations and simple automation technologies. Such systems have problems such as energy waste and slow response. With the advancement of information technology and communication technology, smart grids have begun to emerge. Through big data analysis and machine learning, grid managers can better predict load demand, optimize supply chains, reduce operating costs, and improve the reliability and stability of the grid. At the same time, the widespread application of SCADA systems (supervisory control and data acquisition systems) enables grid managers to monitor the status of the entire grid in real time and quickly identify and respond to faults. However, the current traditional transmission data control methods may be relatively passive in terms of equipment information collection and grid regulation, lack intelligence and real-time performance, and have limitations in the complexity of grid control and data presentation methods, resulting in low control accuracy and real-time performance.

Summary of the invention

Based on this, it is necessary to provide a method and system for controlling power transmission data of a smart grid to solve at least one of the above technical problems.

To achieve the above object, a method for controlling power transmission data of a smart grid is provided, the method comprising the following steps:

Step S1: acquiring real-time power data and smart grid environment data; fusing the real-time power data and the smart grid environment data to generate a comprehensive power environment data set; performing dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve;

Step S2: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; performing model training on the dynamic power load peak data to generate a power demand forecasting model; dynamically allocating power to the dynamic power load peak data through the power demand forecasting model to generate an optimal power allocation plan;

Step S3: Collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid according to the edge device deployment information data to generate grid edge computing control data; perform power control stability regulation on the grid edge computing control data to generate power transmission stability data;

Step S4: convert the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear power grid control based on the three-dimensional power transmission model to generate power grid transmission intelligent control data; visualize the power grid transmission intelligent control data to generate a smart grid transmission data control report.

The present invention uses a real-time integrated energy load curve, and the smart grid can more accurately predict and manage energy demand, thereby optimizing energy scheduling and distribution and improving energy utilization efficiency. Comprehensive consideration of power data and smart grid environmental data can help the smart grid system better cope with changing environmental factors and improve the reliability and stability of the power supply system. Through dynamic load curve conversion, the smart grid can more accurately predict load demand and adjust the energy supply strategy in a targeted manner, thereby reducing the cost of energy production and distribution. The real-time integrated energy load curve provides decision makers with an accurate data basis, which can be used for making energy policies, planning energy facility construction, optimizing energy market operations and other decisions. Through comprehensive analysis of power data and environmental data, the smart grid can better support the integration and utilization of renewable energy and promote the sustainable development of the energy system. Through dynamic power distribution, the system can respond to changing load demands in real time and improve the flexibility of power distribution. Through accurate power demand prediction, over-distribution of power can be avoided, energy waste can be reduced, and energy utilization efficiency can be improved. The use of the optimal power distribution plan can effectively balance the supply and demand relationship and improve the stability and robustness of the power system. By reducing over-distribution and improving system efficiency, the operating cost of the power system can be reduced and the overall economic benefits can be improved. Through real-time grid regulation and edge computing control, the system can respond to changes in power demand more quickly, improving the real-time response capability of the power system. Through power control stability regulation, stable power transmission data is generated, which helps to improve the stability and reliability of power transmission. Equipment adjustment according to the optimal power distribution plan helps to optimize equipment utilization, extend equipment life, and reduce equipment operating costs. Through grid nonlinear control, refined management of grid operation is achieved, and the operating efficiency and stability of the grid are improved. The optimized grid control strategy helps to reduce the loss of transmission lines, improve transmission efficiency, and reduce energy waste. The implementation of intelligent control strategies can timely discover and handle grid faults, improve the safety and reliability of the grid. Intelligent grid management reduces the need for manual intervention, reduces operation and maintenance costs, and improves operation and maintenance efficiency. Therefore, the present invention improves the accuracy, stability and reliability of the smart grid through comprehensive data processing, dynamic load curve conversion, load peak data extraction and prediction model, equipment information collection and grid regulation, grid nonlinear control and data visualization.

In this specification, a power transmission data control system of a smart grid is provided, which is used to execute the power transmission data control method of the smart grid described above, and the power transmission data control system of the smart grid includes:

The load analysis module is used to obtain real-time power data and smart grid environment data; perform data fusion on the real-time power data and smart grid environment data to generate a comprehensive power environment data set; perform dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve;

The power distribution module is used to extract load peak data from the real-time comprehensive energy load curve based on a preset peak screening number to obtain dynamic power load peak data; perform model training on the dynamic power load peak data to generate a power demand prediction model; perform dynamic power distribution on the dynamic power load peak data through the power demand prediction model to generate an optimal power distribution plan;

The stability control module is used to collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid based on the edge device deployment information data to generate grid edge computing control data; perform power control stability control on the grid edge computing control data to generate power transmission stability data;

The linear control module is used to convert the power transmission stability data into three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear control of the power grid based on the three-dimensional power transmission model to generate intelligent control data for power grid transmission; and visualize the intelligent control data for power grid transmission to generate a smart grid transmission data control report.

The beneficial effect of the present invention is that by integrating real-time power data and smart grid environment data, a comprehensive power environment data set is generated, which helps to improve the integrity and accuracy of the data. Through dynamic load curve conversion, a comprehensive energy load curve is generated in real time, providing a basis for subsequent power demand prediction and optimization. Through model training, a power demand prediction model is generated, which can help predict future power demand and provide a basis for power distribution. Based on the power demand prediction model, dynamic power distribution is realized, and the optimal power distribution plan is generated, which helps to improve energy utilization efficiency and reduce the cost caused by supply and demand imbalance. According to the optimal power distribution plan, real-time power grid adjustment is carried out, and the optimal management of the smart grid is realized by deploying information data of edge devices. Through the generation and regulation of power grid edge computing control data, the stability and reliability of the power grid are improved, and energy waste and loss are reduced. Through three-dimensional point cloud conversion, a three-dimensional model of power transmission is generated, providing a visualization basis for nonlinear control of the power grid. Based on the three-dimensional model of power transmission, nonlinear control and intelligent management of the power grid are realized, and the operation efficiency and safety of the power grid are improved. Through the visualization of the intelligent control data of power grid transmission, a smart grid transmission data control report is generated to provide decision support and management reference for the power management department. Therefore, the present invention improves the accuracy, stability and reliability of the smart grid through comprehensive data processing, dynamic load curve conversion, load peak data extraction and prediction model, equipment information collection and grid regulation, grid nonlinear control and data visualization.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a process flow of a method for controlling power transmission data of a smart grid;

FIG2 is a schematic diagram of a detailed implementation process of step S2 in FIG1 ;

FIG3 is a schematic diagram of a detailed implementation process of step S24 in FIG2 ;

FIG4 is a schematic diagram of a detailed implementation process of step S243 in FIG3 ;

The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings.

Detailed ways

The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor methods and/or microcontroller methods.

It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and/or" used herein includes any and all combinations of one or more of the listed associated items.

To achieve the above object, please refer to FIG. 1 to FIG. 4 , a method for controlling power transmission data of a smart grid, the method comprising the following steps:

Step S1: acquiring real-time power data and smart grid environment data; fusing the real-time power data and the smart grid environment data to generate a comprehensive power environment data set; performing dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve;

Step S2: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; performing model training on the dynamic power load peak data to generate a power demand forecasting model; dynamically allocating power to the dynamic power load peak data through the power demand forecasting model to generate an optimal power allocation plan;

Step S3: Collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid according to the edge device deployment information data to generate grid edge computing control data; perform power control stability regulation on the grid edge computing control data to generate power transmission stability data;

Step S4: convert the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear power grid control based on the three-dimensional power transmission model to generate power grid transmission intelligent control data; visualize the power grid transmission intelligent control data to generate a smart grid transmission data control report.

The present invention uses a real-time integrated energy load curve, and the smart grid can more accurately predict and manage energy demand, thereby optimizing energy scheduling and distribution and improving energy utilization efficiency. Comprehensive consideration of power data and smart grid environmental data can help the smart grid system better cope with changing environmental factors and improve the reliability and stability of the power supply system. Through dynamic load curve conversion, the smart grid can more accurately predict load demand and adjust the energy supply strategy in a targeted manner, thereby reducing the cost of energy production and distribution. The real-time integrated energy load curve provides decision makers with an accurate data basis, which can be used for making energy policies, planning energy facility construction, optimizing energy market operations and other decisions. Through comprehensive analysis of power data and environmental data, the smart grid can better support the integration and utilization of renewable energy and promote the sustainable development of the energy system. Through dynamic power distribution, the system can respond to changing load demands in real time and improve the flexibility of power distribution. Through accurate power demand prediction, over-distribution of power can be avoided, energy waste can be reduced, and energy utilization efficiency can be improved. The use of the optimal power distribution plan can effectively balance the supply and demand relationship and improve the stability and robustness of the power system. By reducing over-distribution and improving system efficiency, the operating cost of the power system can be reduced and the overall economic benefits can be improved. Through real-time grid regulation and edge computing control, the system can respond to changes in power demand more quickly, improving the real-time response capability of the power system. Through power control stability regulation, stable power transmission data is generated, which helps to improve the stability and reliability of power transmission. Equipment adjustment according to the optimal power distribution plan helps to optimize equipment utilization, extend equipment life, and reduce equipment operating costs. Through grid nonlinear control, refined management of grid operation is achieved, and the operating efficiency and stability of the grid are improved. The optimized grid control strategy helps to reduce the loss of transmission lines, improve transmission efficiency, and reduce energy waste. The implementation of intelligent control strategies can timely discover and handle grid faults, improve the safety and reliability of the grid. Intelligent grid management reduces the need for manual intervention, reduces operation and maintenance costs, and improves operation and maintenance efficiency. Therefore, the present invention improves the accuracy, stability and reliability of the smart grid through comprehensive data processing, dynamic load curve conversion, load peak data extraction and prediction model, equipment information collection and grid regulation, grid nonlinear control and data visualization.

In the embodiment of the present invention, referring to FIG. 1 , it is a schematic flow chart of the steps of a method for controlling power transmission data of a smart grid of the present invention. In this example, the method for controlling power transmission data of a smart grid includes the following steps:

Step S1: acquiring real-time power data and smart grid environment data; fusing the real-time power data and the smart grid environment data to generate a comprehensive power environment data set; performing dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve;

In the embodiment of the present invention, power data is collected in real time by using sensors, smart meters and other devices. The real-time data interface provided by the power company is used to obtain information such as the power grid operation status and power load. Environmental sensors, weather stations and other devices are used to collect meteorological data, such as temperature, humidity, wind speed, and other environmental factors that affect power demand. Environmental information, such as equipment operation status, fault information, etc., is obtained from smart grid equipment. Real-time power data and smart grid environmental data are cleaned, and missing values, abnormal values, etc. are processed. Time synchronization is performed on the data to ensure the temporal consistency of the data. The cleaned real-time power data and smart grid environmental data are fused. The association can be performed based on timestamps or other key information. Data fusion algorithms are used, such as database association query, time series merging, etc. The fused data is integrated into a comprehensive power environment data set, including power data and environmental data. Data processing is performed on the comprehensive power environment data set to extract key features, such as power load, ambient temperature, humidity, etc. Filtering technology is used to smooth the curve and reduce noise interference. Time series analysis methods, such as moving average, exponential smoothing, etc., are used to generate dynamic load curves. Consider the association between power data and environmental data to ensure that the generated load curve reflects the changes of the power system under different environmental conditions. The generated dynamic load curves are integrated to obtain the real-time comprehensive energy load curve, taking into account the changes in different time scales to meet the analysis of different granularities of real-time energy demand.

Step S2: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; performing model training on the dynamic power load peak data to generate a power demand forecasting model; dynamically allocating power to the dynamic power load peak data through the power demand forecasting model to generate an optimal power allocation plan;

In an embodiment of the present invention, by formulating a preset peak screening number, load peak data is identified and extracted according to the real-time integrated energy load curve. Technologies such as sliding windows and peak detection algorithms can be used. Select a suitable power demand forecasting model, such as a time series model (ARIMA, Prophet), a machine learning model (regression model, decision tree) or a deep learning model (LSTM, GRU, Transformer). Use historical dynamic power load peak data as a training set, divide the data into a training set and a validation set, and train and tune the model. Use the trained model to predict the dynamic power load peak data for a period of time in the future. Ensure that the model can capture the trend, periodicity and other characteristics of the load curve. The prediction results obtained by the power demand forecasting model are used for dynamic power distribution. Formulate an optimal power distribution algorithm, consider factors such as power supply capacity, cost, and renewable energy utilization, and generate an optimal power distribution plan. Implement the optimal power distribution plan to allocate power resources to different parts to meet the actual needs of the system. Monitor real-time power data and adjust the distribution plan as needed.

Step S3: Collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid according to the edge device deployment information data to generate grid edge computing control data; perform power control stability regulation on the grid edge computing control data to generate power transmission stability data;

In the embodiment of the present invention, sensors and monitoring equipment are deployed to collect data such as status information, grid parameters, and energy consumption of edge devices. Data collection protocols and communication methods are designed to ensure that the equipment can transmit data to the central control system in real time. The collected equipment information is cleaned, processed, and integrated to obtain accurate and available edge device deployment information data. Using edge device deployment information data to adjust the smart grid in real time involves controlling distributed energy, energy storage systems, frequency modulation equipment, etc. Formulate a grid adjustment algorithm, consider factors such as the maximum capacity of the equipment, energy supply and demand balance, voltage and frequency control, and generate a real-time grid adjustment strategy. According to the results of real-time grid adjustment, grid edge computing control data is generated, and the data includes grid status information, equipment operating parameters, load distribution, etc., which are used to guide the next step of power control. Grid edge computing control data is used to control power control stability. Advanced control algorithms are used to ensure that the power system can maintain stable voltage and frequency under different load conditions. In response to possible sudden load changes or equipment failures, corresponding response strategies are implemented to ensure the stability of the power grid. According to the results of power control, power transmission stability data is generated, which reflects the stable state of the power system after adjustment, including information such as voltage, frequency, and load balance.

Step S4: convert the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear power grid control based on the three-dimensional power transmission model to generate power grid transmission intelligent control data; visualize the power grid transmission intelligent control data to generate a smart grid transmission data control report.

In an embodiment of the present invention, a laser scanner or other three-dimensional scanning technology is used to scan the power transmission line and equipment to obtain point cloud data. The point cloud data is processed and analyzed to generate a three-dimensional model of power transmission. It is ensured that the three-dimensional model accurately reflects the geometry, equipment layout and environmental characteristics of the power transmission line. Based on the three-dimensional model of power transmission, a nonlinear control algorithm for the power grid is developed. Considering the nonlinear characteristics of the power system, including factors such as load changes, line impedance, and equipment limitations, a control strategy is designed to optimize the efficiency and stability of power transmission. Intelligent control data for power grid transmission is generated, including information such as equipment adjustment parameters and power flow distribution. The three-dimensional model of power transmission and the intelligent control data for power grid transmission are visualized using three-dimensional visualization software or library. The status and control strategy of power transmission lines and equipment are visualized so that users can intuitively understand the operation of the power grid and the control effect. Based on the visualization results, a smart grid transmission data control report is generated. The report includes information such as the geometry of the power transmission line, equipment layout, control parameters, real-time operation status, and evaluation and suggestions on the efficiency and stability of the power grid operation.

Preferably, step S1 comprises the following steps:

Step S11: using sensors to obtain real-time power data and smart grid environment data;

Step S12: standardizing the data formats of the real-time power data and the smart grid environment data to generate real-time power standard data and smart grid standard environment data; filling missing values of the real-time power standard data and the smart grid standard environment data to generate real-time power complete data and smart grid complete environment data;

Step S13: fusing the real-time power complete data and the smart grid complete environment data to generate a comprehensive power environment data set; filtering the power grid operation dynamic load data for the comprehensive power environment data set to generate a comprehensive power dynamic load data set;

Step S14: Performing data dimensionality reduction on the comprehensive power dynamic load data set by principal component analysis method to generate a comprehensive power dynamic load reduced dimensionality data set; performing curve conversion on the comprehensive power dynamic load reduced dimensionality data set to generate a real-time comprehensive energy load curve.

Through steps S11 and S12, the system of the present invention can obtain power data and smart grid environmental data in real time, standardize them, fill in missing values, and ensure the accuracy and completeness of the data. Through step S13, the system merges the power data and environmental data to generate a comprehensive power environment data set, providing comprehensive data support for power grid operation, and generates a comprehensive power dynamic load data set by screening to provide a basis for subsequent analysis. Through step S14, the system uses the principal component analysis method to reduce the dimension of the comprehensive power dynamic load data set, simplify the data structure, improve the processing efficiency, and convert it into a real-time comprehensive energy load curve to make the data more intuitive and easy to understand. The automated processing of the entire process can improve the processing speed and accuracy of energy data, provide more reliable support for power system operation and energy management, and thus improve the efficiency and accuracy of energy management.

In an embodiment of the present invention, a sensor network is deployed to obtain real-time power data and smart grid environment data. The sensors may include power metering devices, temperature sensors, humidity sensors, wind speed sensors, etc., which are used to collect various data related to power production and distribution and environmental data. Develop algorithms and programs for data format standardization, standardize the real-time data collected by sensors, and ensure the consistency and compatibility of data formats. Implement a data missing value filling algorithm, fill in data according to data characteristics and historical data, and ensure the integrity of real-time power data and smart grid environment data. Design a data fusion algorithm to fuse real-time power data and smart grid environment data to generate a comprehensive power environment data set. Develop a grid operation dynamic load data screening algorithm, screen the comprehensive power environment data set according to the grid operation status and demand, and generate a comprehensive power dynamic load data set. Implement the principal component analysis (PCA) method to reduce the dimension of the comprehensive power dynamic load data set, extract the main features of the data, and reduce the data dimension. Develop a curve conversion algorithm to convert the comprehensive power dynamic load dimension reduction data set into a real-time comprehensive energy load curve to more intuitively display the load situation of the power system.

Preferably, step S2 comprises the following steps:

Step S21: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; collecting historical data of the dynamic power load peak data to generate historical dynamic power load peak data;

Step S22: dividing the historical dynamic power load peak data into data sets to generate a model training set and a model test set; training the model training set according to the long short-term memory network algorithm to generate a power demand training model; optimizing and iterating the power demand training model using the model test set to generate a power demand prediction model;

Step S23: importing the dynamic power load peak data into the power demand forecasting model to perform power demand forecasting and generate power demand forecasting data;

Step S24: quantify the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; dynamically allocate power to the power demand forecast data according to the power supply and demand value, thereby generating an optimal power allocation plan.

The present invention helps the system to better understand the volatility and periodicity of power load by extracting dynamic power load peak data from the real-time comprehensive energy load curve and generating historical dynamic power load peak data through historical data collection. The system uses the long short-term memory network (LSTM) algorithm for model training to generate a power demand training model. Through iterative optimization of the model test set, a more accurate power demand forecasting model is generated, which improves the ability to accurately predict power demand. Importing dynamic power load peak data into the power demand forecasting model to generate power demand forecasting data helps to understand the trend and changes of future power demand in real time and prepare for power supply. The system uses the power supply and demand analysis formula to quantify the power demand forecasting data to obtain the power supply and demand value, provides a real-time quantitative evaluation of power demand, enables the system to dynamically allocate power according to the power supply and demand value, and generates the optimal power allocation plan. Through dynamic power allocation, the system can adjust power allocation according to the real-time power demand situation to meet the demand to the greatest extent and avoid resource waste, which helps to improve the efficiency and sustainability of the power system and maximize the use of available resources.

As an example of the present invention, referring to FIG. 2 , in this example, step S2 includes:

Step S21: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; collecting historical data of the dynamic power load peak data to generate historical dynamic power load peak data;

In an embodiment of the present invention, by obtaining the data of the real-time comprehensive energy load curve, a monitoring system, a sensor or other data acquisition device is involved to obtain the load conditions of various energy sources (such as electricity, natural gas, solar energy, etc.) in real time. Based on the preset peak screening number, the real-time comprehensive energy load curve is analyzed and processed to extract the load peak data, which can be achieved through algorithms or data processing techniques, such as sliding window method, peak detection algorithm, etc. Filtering out dynamic power load peak data from the extracted load peak data involves classifying and processing the load data of different energy sources to ensure that the extracted data meets the characteristics of the power load. Saving the dynamic power load peak data and collecting historical data can be achieved through a database, a data warehouse or other data storage system to ensure the persistent storage and management of historical data. Based on the collected historical data, historical dynamic power load peak data is generated, which involves steps such as data cleaning, data preprocessing and data analysis to ensure the quality and accuracy of the generated historical data.

Step S22: dividing the historical dynamic power load peak data into data sets to generate a model training set and a model test set; training the model training set according to the long short-term memory network algorithm to generate a power demand training model; optimizing and iterating the power demand training model using the model test set to generate a power demand prediction model;

In an embodiment of the present invention, the historical dynamic power load peak data is divided into a model training set and a model test set. Generally, the sliding window method or random sampling method in the time series data can be used for division to ensure that the data of the training set and the test set are representative and have a certain degree of randomness. The model training set is trained using the long short-term memory network (LSTM) algorithm. LSTM is a recurrent neural network (RNN) variant suitable for processing and predicting time series data, which can effectively capture long-term dependencies in time series data. During the model training process, it is necessary to determine the network structure, hyperparameters (such as learning rate, number of hidden layer nodes, etc.) and loss function, etc. The model parameters can be updated using the back propagation algorithm and optimizer (such as Adam, SGD, etc.) to minimize the loss function. The power demand training model is evaluated and optimized iteratively using the model test set. By verifying on the test set, the performance and generalization ability of the model can be evaluated, and the structure and parameters of the model can be adjusted accordingly to improve the prediction accuracy and stability of the model. The model can be further optimized by cross-validation, hyperparameter search and other techniques to find the best model configuration. After multiple rounds of iterative optimization, the final power demand forecasting model is generated. The model can accurately predict the electricity demand within a certain period of time in the future based on the historical dynamic power load peak data.

Step S23: importing the dynamic power load peak data into the power demand forecasting model to perform power demand forecasting and generate power demand forecasting data;

In an embodiment of the present invention, by ensuring that the format and structure of the dynamic power load peak data match the data format of the model input, the data needs to be preprocessed to ensure the quality and integrity of the data. The prepared dynamic power load peak data is input into the power demand forecasting model for prediction, which usually involves inputting the data into a trained model and obtaining the prediction results of the model output. The dynamic power load peak data is predicted using the power demand forecasting model to generate power demand forecasting data. The forecast data may include the power demand value at each time point in the future, usually presented in the form of a time series. The generated power demand forecasting data is used for practical applications, including adjusting power production plans, optimizing power supply chains, formulating power market strategies, etc., to meet future power demand.

Step S24: quantify the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; dynamically allocate power to the power demand forecast data according to the power supply and demand value, thereby generating an optimal power allocation plan.

In the embodiment of the present invention, by determining the formula for power supply and demand analysis, multiple factors are considered, such as power supply capacity, predicted power demand, system reliability requirements, etc. Common formulas include supply and demand balance equations, load curves, etc. Quantifying the power demand forecast data according to the selected power supply and demand analysis formula involves converting the forecast data into appropriate units (such as power, energy) to match the requirements of the formula. Using the power supply and demand analysis formula, the quantified power demand forecast data is combined with the existing power supply situation to calculate the power supply and demand value, which reflects the supply and demand relationship of power in the current period. According to the calculated power supply and demand value, a dynamic power distribution plan is formulated, which involves adjusting the production capacity of power production facilities, optimizing the configuration of the transmission network, adjusting the distribution of power loads, and other measures to ensure the balance of power supply and demand and meet the power demand of each part of the system as much as possible. By dynamically analyzing and optimizing the power supply and demand value, the optimal power distribution plan is generated, which needs to consider multiple factors, including cost, system reliability, environmental impact, etc., as well as various constraints, such as equipment capacity, power supply area requirements, etc.

Preferably, step S24 includes the following steps:

Step S241: quantifying the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; simulating power transmission of the power demand forecast data according to the power supply and demand value to generate simulated power transmission data; extracting transmission grid nodes from the simulated power transmission data to generate power transmission grid node data, wherein the power transmission grid node data includes central power node data and edge power node data;

Step S242: Perform distributed calculation on edge power node data to generate distributed intelligent power transmission path data; perform local power distribution adjustment on power transmission grid node data based on the distributed intelligent power transmission path data to generate local power adjustment data; transmit the local power adjustment data to the central power node data through a preset communication protocol for global power scheduling to generate global circuit adjustment data;

Step S243: performing power constraint condition analysis on the global circuit adjustment data to generate global power constraint condition data;

Step S244: Dynamically allocate power to the power demand forecast data according to the global power constraint data and the local power adjustment data, thereby generating an optimal power allocation plan.

The present invention can more accurately understand the power supply and demand situation by quantifying the power demand forecast data and simulating the transmission data generation, and provide a reliable data basis for subsequent power allocation. Extracting the transmission grid node data and generating distributed intelligent power transmission path data can optimize the power transmission efficiency and improve the reliability and stability of power transmission. By performing distributed calculations on the edge power node data, generating distributed intelligent power transmission path data, and performing local power distribution adjustments, power transmission can be made more flexible and efficient. By performing global power scheduling at the central power node and generating global circuit adjustment data, power distribution can be optimized throughout the power network. Power constraint analysis of global circuit adjustment data helps to identify and deal with potential power constraint problems and ensure the feasibility and safety of the power distribution plan. Based on the global power constraint data and local power adjustment data, the optimal power distribution plan can be generated to meet power demand and maximize the efficiency and reliability of the power system.

As an example of the present invention, referring to FIG. 3 , in this example, step S24 includes:

Step S241: quantifying the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; simulating power transmission of the power demand forecast data according to the power supply and demand value to generate simulated power transmission data; extracting transmission grid nodes from the simulated power transmission data to generate power transmission grid node data, wherein the power transmission grid node data includes central power node data and edge power node data;

In an embodiment of the present invention, by statistically analyzing historical power demand data and combining current economic, social and environmental factors, a power supply and demand analysis formula can be established, which includes various factors such as seasonal changes, weather conditions, industrial production activities, etc., to quantify power demand. Using simulation software or self-developed simulation tools, the power demand forecast data is simulated for power transmission according to the power supply and demand value. The tool considers the physical characteristics of power transmission, such as voltage loss, line capacity, load balance, etc., to generate simulated power transmission data. By simulating power transmission data, nodes in the transmission grid can be identified and extracted. The nodes can be power plants, substations, distribution stations or other important power facilities. The extracted nodes can be divided into central nodes and edge nodes. The central nodes are usually the core of the power grid, and the edge nodes are located at the periphery or edge of the power grid. Using data processing and analysis technology, the simulated power transmission data is processed and node information is extracted, involving data cleaning, feature extraction, cluster analysis and other methods to effectively extract power transmission grid node data.

Step S242: Perform distributed calculation on edge power node data to generate distributed intelligent power transmission path data; perform local power distribution adjustment on power transmission grid node data based on the distributed intelligent power transmission path data to generate local power adjustment data; transmit the local power adjustment data to the central power node data through a preset communication protocol for global power scheduling to generate global circuit adjustment data;

In an embodiment of the present invention, distributed computing is performed on edge power node data, involving the use of a distributed computing framework, such as Apache Hadoop or Spark, to process large-scale data and perform parallel computing. In this process, intelligent algorithms, such as genetic algorithms, simulated annealing algorithms, or deep learning models, can be used to determine the optimal power transmission path to minimize energy loss and improve the efficiency of the power grid. Based on the generated distributed intelligent power transmission path data, local power distribution adjustment is performed on the power transmission grid node data, involving making local power distribution decisions at each node to ensure balanced power distribution and stable operation of the power grid, and factors such as load conditions, line capacity, and voltage stability between nodes need to be considered. Transmitting local power adjustment data to the central power node through a preset communication protocol involves the use of network communication technologies, such as message queues, Socket communications, or HTTP protocols, to ensure secure and reliable data transmission. Global power scheduling is performed in the central power node, that is, the received local power adjustment data is integrated and optimized to generate global circuit adjustment data, involving the use of optimization algorithms, such as linear programming, integer programming, or optimization methods based on heuristic algorithms, to maximize the overall efficiency and stability of the power grid.

Step S243: performing power constraint condition analysis on the global circuit adjustment data to generate global power constraint condition data;

In the embodiment of the present invention, starting from the global circuit adjustment data obtained in step S242, including information such as power transmission path, node load condition, line capacity, etc., for the analysis of power constraints. The analysis of power constraints on the global circuit adjustment data involves checking and evaluating various constraints of the power system to ensure that the adjusted power distribution meets the safety, stability and reliability requirements of the system. The constraints include: node voltage limit: ensure that the voltage of each node is within a safe range; line capacity limit: ensure that the current of each power line does not exceed its rated capacity; system stability: by considering factors such as power balance and flow direction between nodes, ensure that the system remains stable under various operating conditions; node load balance: ensure that the load of each node is within a reasonable range to avoid overload or load imbalance. According to the results of the power constraint analysis, global power constraint data is generated. The global power constraint data describes various constraints of the system under different operating conditions, as well as the specific limitations of each constraint. These data need to be organized and recorded in a structured format for subsequent power dispatching and operation management.

Step S244: Dynamically allocate power to the power demand forecast data according to the global power constraint data and the local power adjustment data, thereby generating an optimal power allocation plan.

In the embodiment of the present invention, before performing dynamic power distribution, it is necessary to prepare the forecast data of power demand, and to make forecasts based on historical power consumption, seasonal changes, weather conditions and other factors to determine the power demand of each region or node in the future. The required information is obtained from the global power constraint data and the local power adjustment data obtained in step S243. The global power constraint data describes various constraints of the system, while the local power adjustment data provides power adjustment information for specific regions or nodes. Design a power distribution algorithm suitable for a dynamic environment. The algorithm needs to take into account the continuous changes in power demand, the dynamic adjustment of system constraints and the impact of local power adjustment. Common algorithms include dynamic power distribution based on load prediction, optimal scheduling based on optimization algorithms, etc. According to the power demand forecast data, the global power constraint data and the local power adjustment data, the optimal power distribution plan is generated using the designed dynamic power distribution algorithm. The process involves reasonably allocating power resources to meet the needs of each region or node under the premise of meeting the system constraints.

Preferably, the power supply and demand analysis formula in step S241 is as follows:

In the formula, Expressed as time/> The power supply and demand value, /> Expressed as time/> The power demand, Expressed as time/> of renewable energy supply,/> Expressed as time/> The voltage, /> Expressed as time/> The current, Expressed as the response speed of the power system, /> Represents the time range for power supply and demand analysis.

The present invention analyzes and integrates a power supply and demand analysis formula, in which the time The amount and time of electricity demand/> of renewable energy supply, when/> When it increases, it means that the power demand increases, and the system needs more power supply to meet the demand, so /> will also increase accordingly. At the same time, when/> When it increases, the renewable energy available in the system increases and can partially meet the electricity demand, thus reducing/> Yes/> The contribution of The changes in voltage and current will directly affect the energy transmission and supply capacity of the system, thus affecting the balance of power supply and demand. It can be understood as the power transmission efficiency of the system. When this value tends to negative infinity, the system's response to power demand will become very fast. When this value tends to positive infinity, the system's response to power demand will become very slow. /> The smaller it is, the faster the system responds, and the faster the system can adjust and balance the power supply and demand. The larger the value is, the slower the system response speed is, and the system will adjust the power demand relatively slowly. When using the conventional power supply and demand analysis formula in the field, it can be obtained that in time/> The power supply and demand value can be calculated more accurately at time / > by applying the power supply and demand analysis formula provided by the present invention. The formula takes into account multiple factors such as power demand, renewable energy supply, voltage and current, and can more comprehensively analyze the power supply and demand situation. Through the integral term in the formula, the balance between power supply and demand can be dynamically adjusted to make the system more flexible and responsive. Indicates the time/> The power supply and demand values can be predicted and analyzed to optimize the power distribution plan and improve the efficiency and stability of the system. The interaction between the parameters in the formula enables the system to adjust the power supply in real time, meet the power demand and maximize the use of renewable energy, which helps to reduce energy costs and reduce dependence on traditional energy.

Preferably, step S243 includes the following steps:

Step S2431: using the fast Fourier transform method to perform power transmission spectrum conversion on the global circuit adjustment data to generate a global circuit power transmission spectrum diagram; performing frequency period analysis on the global circuit power transmission spectrum diagram to generate a power transmission frequency curve; performing transmission time interval extraction on the power transmission frequency curve to obtain transmission time interval data;

Step S2432: performing transmission data packet sequence number detection on the global circuit adjustment data according to the transmission time interval data to generate power transmission data packet sequence data; performing network delay anomaly test according to the power transmission data packet sequence data to generate power transmission delay anomaly data;

Step S2433: comparing the power transmission delay abnormal data with the preset delay abnormal threshold, when the power transmission delay abnormal data is greater than or equal to the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication failure data; when the power transmission delay abnormal data is less than the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication delay data;

Step S2434: Integrate the network communication failure data and the network communication delay data to generate global power constraint condition data.

The present invention uses the fast Fourier transform method to convert the global circuit adjustment data into a transmission spectrum, which can more effectively analyze the spectrum characteristics of the circuit, thereby providing accurate transmission frequency curve data for the frequency cycle analysis of the power system. By extracting the transmission time interval of the transmission frequency curve, the transmission time interval data obtained can better reflect the time interval characteristics in the power transmission process, providing a basis for subsequent data analysis. According to the power transmission data packet sequence data generated by the transmission time interval data, a network delay anomaly test is performed, which can effectively detect the delay anomaly in the power transmission, and help to timely discover potential communication failures or delay problems. The power transmission delay anomaly data is compared with the preset delay anomaly threshold, and the data is marked as network communication failure data or network communication delay data according to the result, which helps to further analyze and process the abnormal situation. The network communication failure data and the network communication delay data are integrated to generate global power constraint condition data, providing basic data support for subsequent power system adjustment and optimization.

As an example of the present invention, referring to FIG. 4 , in this example, step S243 includes:

Step S2431: using the fast Fourier transform method to perform power transmission spectrum conversion on the global circuit adjustment data to generate a global circuit power transmission spectrum diagram; performing frequency period analysis on the global circuit power transmission spectrum diagram to generate a power transmission frequency curve; performing transmission time interval extraction on the power transmission frequency curve to obtain transmission time interval data;

In an embodiment of the present invention, the global circuit adjustment data is input into the fast Fourier transform (FFT) algorithm. The FFT algorithm is used to convert the time domain signal into a frequency domain signal to obtain a power transmission spectrum diagram of the global circuit. In the spectrum diagram, the frequency axis represents the intensity of different frequency components, and the amplitude axis represents the amplitude of the corresponding frequency components. The power transmission spectrum diagram of the global circuit is subjected to frequency periodic analysis, and the transmission frequency curve of the circuit can be determined by finding the main frequency components in the spectrum diagram. The main frequency components are usually peaks or significant energy concentration points in the frequency spectrum. Based on the generated power transmission frequency curve, the time interval between adjacent frequency components can be calculated. The time interval represents the time interval for data transmission in the power system, which can reflect the frequency and rate of data transmission.

Step S2432: performing transmission data packet sequence number detection on the global circuit adjustment data according to the transmission time interval data to generate power transmission data packet sequence data; performing network delay anomaly test according to the power transmission data packet sequence data to generate power transmission delay anomaly data;

In an embodiment of the present invention, the transmission time interval between data packets can be inferred based on the transmission time interval data. The transmission time point of the data packet can be determined by analyzing the change pattern of the transmission time interval data. According to the transmission time point, a sequence number is assigned to each data packet, thereby generating power transmission data packet sequence data. The generated power transmission data packet sequence data is used to simulate the data transmission process of the power system. The transmission time of each data packet and the time when the data packet arrives at the destination are monitored. The difference between the actual transmission time and the expected transmission time is analyzed to detect whether there is a network delay anomaly. The detection of anomalies can be based on threshold setting, statistical methods, machine learning and other technologies.

Step S2433: comparing the power transmission delay abnormal data with the preset delay abnormal threshold, when the power transmission delay abnormal data is greater than or equal to the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication failure data; when the power transmission delay abnormal data is less than the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication delay data;

In an embodiment of the present invention, during the system design phase, according to the characteristics and requirements of the power system, a suitable delay anomaly threshold is set, and the threshold is determined according to factors such as the system performance requirements and real-time requirements. For each generated power transmission delay anomaly data, it is compared with the preset delay anomaly threshold. It is determined whether the delay anomaly data is greater than or equal to the threshold, or less than the threshold. If the power transmission delay anomaly data is greater than or equal to the preset delay anomaly threshold: the data is marked as network communication fault data. If the power transmission delay anomaly data is less than the preset delay anomaly threshold: the data is marked as network communication delay data.

Step S2434: Integrate the network communication failure data and the network communication delay data to generate global power constraint condition data.

In an embodiment of the present invention, network communication fault data and network communication delay data are collected. The two types of data are integrated into a unified data structure to ensure data format consistency. In order to clearly identify and distinguish network communication fault data and network communication delay data, an identification field or a classification field may be added to the data structure. For example, a flag bit or a specific numerical value may be used to represent faults and delays. According to the power constraints and requirements of the system, the integrated data is further processed to generate global power constraint data, including weighting, normalization or other mathematical processing of different types of data to obtain comprehensive power constraints.

Preferably, step S3 comprises the following steps:

Step S31: deploying a power grid edge server based on the optimal power distribution solution, and collecting device information according to the power grid edge server to obtain edge device deployment information data;

Step S32: monitoring the actual power distribution data of the smart grid according to the edge device deployment information data to generate real-time power distribution monitoring data; performing data cleaning on the real-time power distribution monitoring data to generate real-time power distribution monitoring cleansing data;

Step S33: Use edge computing technology to control power equipment on real-time power distribution monitoring and cleaning data to generate power equipment control data; perform real-time grid adjustment on power equipment control data based on feedback control theory to generate grid edge computing control data;

Step S34: Perform a grid transmission security analysis on the grid edge computing control data to generate grid transmission security analysis data; perform power control stability regulation on the real-time power distribution monitoring data based on the grid transmission security analysis data to generate power transmission stability data.

The present invention can achieve optimal configuration of power resources and improve the overall efficiency and performance of the power grid by deploying edge servers of the power grid based on the optimal power distribution scheme. By generating and cleaning real-time power distribution monitoring data and real-time control and adjustment of power equipment in step S33, the real-time monitoring and regulation capabilities of the smart grid are realized, which helps to ensure the stable operation of the power grid. Using edge computing technology to control power equipment (step S33) can reduce data transmission delay, improve response speed, reduce the burden on the central server, and improve the overall performance and efficiency of the system. Security analysis of power grid edge computing control data helps to timely discover potential safety hazards and take corresponding measures to deal with them. Power control stability regulation (step S34) based on analysis data helps to ensure the safe and stable operation of the power grid. Through the organic combination of steps S31 to S34, intelligent management and regulation of power resources are realized, the utilization efficiency of power resources can be improved, and the system operation cost can be reduced, thereby achieving the purpose of energy saving and emission reduction. By adopting a real-time monitoring and regulation mechanism, the system can more flexibly respond to changes in the external environment and changes in the state of internal equipment, thereby improving the response speed and flexibility of the system.

In the embodiment of the present invention, the optimal power distribution scheme is determined through power grid planning and data analysis, and servers are deployed at the edge of the power grid according to the scheme, which involves the purchase and layout of server hardware to ensure that the coverage and performance meet the requirements. After the edge server is deployed, it is necessary to install and configure software or sensors for collecting device information on the server. The devices include smart meters, sensors, etc., which are used to collect data related to power grid operation, such as current, voltage, load and other information. The collected device information data is monitored in real time through software or applications installed on the edge server, which involves data transmission and processing to ensure the timeliness and accuracy of the data. The monitored data may have problems such as noise and outliers, and need to be cleaned and processed to ensure data quality. Cleaning data involves technologies such as anomaly detection and data filtering. The real-time monitoring data is processed and analyzed using edge computing technology to reduce data transmission delay and network load, including operations such as data compression and local data processing. Based on the processed data, the power equipment is controlled and adjusted to achieve optimization and stabilization of power distribution, which involves the design and implementation of control algorithms, as well as communication and interaction with power equipment. Security analysis is performed on edge computing control data to identify potential security threats and vulnerabilities, including technologies such as data encryption and access control. Based on the safety analysis results, the real-time power distribution monitoring data is used to regulate the power control stability to ensure the stability and reliability of power transmission. This involves the model and simulation of the power system, as well as the optimization and adjustment of control parameters.

Preferably, step S34 includes the following steps:

Step S341: extracting the response time of the power grid edge computing control data to obtain power transmission response time data; capturing abnormal logs of the power grid edge server according to the power transmission response time data to generate power transmission system paralysis analysis data;

Step S342: extracting data access logs of power grid edge computing control data to obtain power transmission data access behavior data; capturing abnormal traffic of the power grid edge server according to the power transmission access behavior data to generate power transmission information leakage analysis data;

Step S343: extracting power system parameters of the power grid edge computing control data model to obtain power transmission system data, wherein the power transmission system data includes power transmission current data and power transmission voltage data; capturing abnormal loads of equipment on the power grid edge server according to the power transmission current data and the power transmission voltage data, and generating power transmission stability analysis data;

Step S344: Merge the power transmission system paralysis analysis data, the power transmission information leakage analysis data and the power transmission stability analysis data in data time series to generate power grid transmission safety analysis data; perform power control stability regulation on the real-time power distribution monitoring data according to the power grid transmission safety analysis data to generate power transmission stability data.

By monitoring the response time of power transmission, the system can detect potential problems in time, such as response time delay or abnormality, so as to diagnose and handle faults more quickly, which is helpful to improve the stability and availability of the power transmission system and reduce the risk of system paralysis. The capture of abnormal logs is helpful to analyze and track the causes of system paralysis and prevent potential problems in advance. Monitoring the access behavior of power transmission data can help detect abnormal data traffic, including unusual access patterns or a large number of access requests. By capturing abnormal traffic, the system can quickly identify potential security threats, such as malicious attacks or unauthorized data access, which helps to improve the security of the power transmission system. Extracting parameters of the power transmission system, such as current and voltage data, can be used to monitor the working status and performance of the equipment. By capturing the abnormal load of the equipment, the system can respond in time when problems occur in the equipment, prevent the equipment from being overloaded or failing, and improve the stability of the power transmission system. Time-sequential merging of different types of analysis data can provide a more comprehensive analysis of power grid transmission security. The comprehensive analysis results help the system to understand the security status of power transmission more comprehensively, so as to take corresponding measures to optimize power control stability. By regulating the power control stability of real-time power distribution monitoring data, the system can achieve dynamic adjustment of power transmission and improve the responsiveness of the system. Generating stability data helps ensure the stability of the power transmission system under different loads and conditions, providing more reliable power service.

In an embodiment of the present invention, the response time of the grid edge computing control data is monitored in real time by using a special monitoring tool or software. A logging system is configured to capture abnormal logs of the grid edge server, and an automated program is established to analyze these log data. A data processing flow is designed to ensure that the process from extracting response time data to capturing abnormal logs is automated and efficient. A network monitoring tool is used to monitor the data access behavior of the grid edge server and record the access log. A traffic analysis system is deployed to detect abnormal traffic patterns and unusual data access behaviors. A real-time monitoring system is established to detect abnormal traffic in a timely manner and implement corresponding response measures, such as blocking malicious traffic or alerting relevant personnel. Sensors and monitoring equipment are configured to monitor parameters such as current and voltage of the grid edge server in real time. A data acquisition and processing system is built to extract and analyze power system parameter data and monitor the working status of the equipment in real time. An abnormal load detection algorithm is developed or adopted to identify abnormal load conditions of the equipment, such as overload or abnormal voltage. A data integration and analysis platform is deployed to perform time series merging and comprehensive analysis of analysis data from different sources. A power control system is designed and corresponding regulation strategies are formulated to ensure the stability and safety of the power transmission system. Establish a real-time monitoring and feedback mechanism so that the system can quickly respond to changes in the power transmission system and make corresponding adjustments.

Preferably, step S4 comprises the following steps:

Step S41: converting the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; designing an adaptive control system based on the three-dimensional power transmission model to generate power grid transmission control design data;

Step S42: Perform nonlinear control on the power grid transmission control design data through fuzzy control theory to generate power grid fuzzy controller data; perform reinforcement learning on the power grid fuzzy controller data to generate power grid transmission intelligent control data; perform data visualization on the power grid transmission intelligent control data to generate an intelligent power grid transmission data control report.

The present invention can generate a three-dimensional model of the power transmission system by converting the power transmission stability data into a three-dimensional point cloud. The model can provide more intuitive and comprehensive grid structure information, which helps to better understand the topological structure and layout characteristics of the power transmission system. Designing an adaptive control system based on the three-dimensional model of power transmission helps to design a more flexible and adaptable control system according to the actual situation of the power grid, which can improve the stability and safety of the power transmission system and optimize the energy utilization efficiency. Nonlinear control of the power transmission control design data of the power grid through fuzzy control theory can cope with the complex, fuzzy environment and uncertainty factors in the power transmission system. The control method can better adapt to the changes and fluctuations in the operation process of the power grid, and improve the stability and robustness of the system. Strengthening learning of the power grid fuzzy controller data can optimize the control strategy through continuous trial and error and learning, so that the system can make more intelligent and effective decisions when facing different situations, which helps to improve the energy utilization efficiency and system response speed in the power grid transmission process. Data visualization of the power grid transmission intelligent control data and generation of the intelligent power grid transmission data control report can help operation and maintenance personnel and decision makers to more intuitively understand the operation status and control effect of the power transmission system, help to timely discover problems, optimize operation strategies, and provide a scientific basis for decision-making.

In an embodiment of the present invention, the power transmission stability data is collected by using a suitable sensor (such as a laser radar). The collected data is converted into a three-dimensional point cloud using a point cloud processing algorithm to ensure the accuracy and integrity of the point cloud, so as to generate a reliable three-dimensional model of power transmission. Based on the generated three-dimensional model of power transmission, an adaptive control system is designed, which involves knowledge in the fields of control theory and system dynamics. The input, output and feedback loop of the control system are determined, and the characteristics of the power transmission system, including load, line loss, voltage stability, etc., are considered to generate power grid transmission control design data, including controller parameters, feedback strategy and other information. Fuzzy control theory is used to process the power grid transmission control design data, and considering the nonlinearity and fuzziness in the power system, fuzzy rules and membership functions are determined to establish a power grid fuzzy controller, which requires an in-depth analysis of the operating characteristics of the power system. Reinforcement learning algorithms, such as deep reinforcement learning, are used to optimize the power grid fuzzy controller data, define reward functions, train intelligent controllers to adapt to the dynamic environment of the power system, and repeatedly learn and optimize to improve the performance of the system in different scenarios. The power grid transmission intelligent control data optimized by reinforcement learning is visualized. Use appropriate visualization tools to display the operating status, control effects and other information of the power transmission system, and generate smart grid transmission data control reports, including key indicators, optimization results, etc., for subsequent analysis and decision-making.

In this specification, a power transmission data control system of a smart grid is provided, which is used to execute the power transmission data control method of the smart grid described above, and the power transmission data control system of the smart grid includes:

The load analysis module is used to obtain real-time power data and smart grid environment data; perform data fusion on the real-time power data and smart grid environment data to generate a comprehensive power environment data set; perform dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve;

The power distribution module is used to extract load peak data from the real-time comprehensive energy load curve based on a preset peak screening number to obtain dynamic power load peak data; perform model training on the dynamic power load peak data to generate a power demand prediction model; perform dynamic power distribution on the dynamic power load peak data through the power demand prediction model to generate an optimal power distribution plan;

The stability control module is used to collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid based on the edge device deployment information data to generate grid edge computing control data; perform power control stability control on the grid edge computing control data to generate power transmission stability data;

The linear control module is used to convert the power transmission stability data into three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear control of the power grid based on the three-dimensional power transmission model to generate intelligent control data for power grid transmission; and visualize the intelligent control data for power grid transmission to generate a smart grid transmission data control report.

The beneficial effect of the present invention is that by integrating real-time power data and smart grid environment data, a comprehensive power environment data set is generated, which helps to improve the integrity and accuracy of the data. Through dynamic load curve conversion, a comprehensive energy load curve is generated in real time, providing a basis for subsequent power demand prediction and optimization. Through model training, a power demand prediction model is generated, which can help predict future power demand and provide a basis for power distribution. Based on the power demand prediction model, dynamic power distribution is realized, and the optimal power distribution plan is generated, which helps to improve energy utilization efficiency and reduce the cost caused by supply and demand imbalance. According to the optimal power distribution plan, real-time power grid adjustment is carried out, and the optimal management of the smart grid is realized by deploying information data of edge devices. Through the generation and regulation of power grid edge computing control data, the stability and reliability of the power grid are improved, and energy waste and loss are reduced. Through three-dimensional point cloud conversion, a three-dimensional model of power transmission is generated, providing a visualization basis for nonlinear control of the power grid. Based on the three-dimensional model of power transmission, nonlinear control and intelligent management of the power grid are realized, and the operation efficiency and safety of the power grid are improved. Through the visualization of the intelligent control data of power grid transmission, a smart grid transmission data control report is generated to provide decision support and management reference for the power management department. Therefore, the present invention improves the accuracy, stability and reliability of the smart grid through comprehensive data processing, dynamic load curve conversion, load peak data extraction and prediction model, equipment information collection and grid regulation, grid nonlinear control and data visualization.

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 intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

The above description 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 (4)

1. A method for controlling power transmission data of a smart grid, characterized in that it comprises the following steps: Step S1: acquiring real-time power data and smart grid environment data; fusing the real-time power data and the smart grid environment data to generate a comprehensive power environment data set; performing dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve; Step S2: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; performing model training on the dynamic power load peak data to generate a power demand forecasting model; dynamically allocating power to the dynamic power load peak data through the power demand forecasting model to generate an optimal power allocation plan; Step S3: Collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid according to the edge device deployment information data to generate grid edge computing control data; perform power control stability regulation on the grid edge computing control data to generate power transmission stability data; Step S4: convert the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear power grid control based on the three-dimensional power transmission model to generate power grid transmission intelligent control data; visualize the power grid transmission intelligent control data to generate a smart grid transmission data control report; Step S2 includes the following steps: Step S21: extracting load peak data from the real-time integrated energy load curve based on a preset peak screening number to obtain dynamic power load peak data; collecting historical data of the dynamic power load peak data to generate historical dynamic power load peak data; Step S22: dividing the historical dynamic power load peak data into data sets to generate a model training set and a model test set; training the model training set according to the long short-term memory network algorithm to generate a power demand training model; optimizing and iterating the power demand training model using the model test set to generate a power demand prediction model; Step S23: importing the dynamic power load peak data into the power demand forecasting model to perform power demand forecasting and generate power demand forecasting data; Step S24: quantifying the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; dynamically allocating power to the power demand forecast data according to the power supply and demand value, thereby generating an optimal power allocation plan; Step S24 includes the following steps: Step S241: quantifying the power supply and demand of the power demand forecast data using the power supply and demand analysis formula to obtain the power supply and demand value; simulating power transmission of the power demand forecast data according to the power supply and demand value to generate simulated power transmission data; extracting transmission grid nodes from the simulated power transmission data to generate power transmission grid node data, wherein the power transmission grid node data includes central power node data and edge power node data; Step S242: Perform distributed calculation on edge power node data to generate distributed intelligent power transmission path data; perform local power distribution adjustment on power transmission grid node data based on the distributed intelligent power transmission path data to generate local power adjustment data; transmit the local power adjustment data to the central power node data through a preset communication protocol for global power scheduling to generate global power adjustment data; Step S243: performing power constraint condition analysis on the global power adjustment data to generate global power constraint condition data; Step S244: dynamically allocating power to the power demand forecast data according to the global power constraint condition data and the local power adjustment data, thereby generating an optimal power allocation plan; The power supply and demand analysis formula in step S241 is as follows: , In the formula, Expressed as time/> The power supply and demand value, /> Expressed as time/> The power demand, Expressed as time/> of renewable energy supply,/> Expressed as time/> The voltage, /> Expressed as time/> The current, Expressed as the response speed of the power system, /> It is expressed as the time frame for power supply and demand analysis; Step S243 includes the following steps: Step S2431: using the fast Fourier transform method to perform transmission spectrum conversion on the global power adjustment data to generate a global power transmission spectrum diagram; performing frequency cycle analysis on the global power transmission spectrum diagram to generate a transmission transmission frequency curve; extracting the transmission time interval from the transmission transmission frequency curve to obtain transmission time interval data; Step S2432: performing transmission data packet sequence number detection on the global power adjustment data according to the transmission time interval data to generate power transmission data packet sequence data; performing network delay anomaly test according to the power transmission data packet sequence data to generate power transmission delay anomaly data; Step S2433: comparing the power transmission delay abnormal data with the preset delay abnormal threshold, when the power transmission delay abnormal data is greater than or equal to the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication failure data; when the power transmission delay abnormal data is less than the preset delay abnormal threshold, marking the power transmission delay abnormal data as network communication delay data; Step S2434: integrating the network communication failure data and the network communication delay data to generate global power constraint condition data; Step S3 includes the following steps: Step S31: deploying a power grid edge server based on the optimal power distribution solution, and collecting device information according to the power grid edge server to obtain edge device deployment information data; Step S32: monitoring the actual power distribution data of the smart grid according to the edge device deployment information data to generate real-time power distribution monitoring data; performing data cleaning on the real-time power distribution monitoring data to generate real-time power distribution monitoring cleansing data; Step S33: Use edge computing technology to control power equipment on real-time power distribution monitoring and cleaning data to generate power equipment control data; perform real-time grid adjustment on power equipment control data based on feedback control theory to generate grid edge computing control data; Step S34: Performing a power grid transmission security analysis on the power grid edge computing control data to generate power grid transmission security analysis data; performing power control stability control on the real-time power distribution monitoring data according to the power grid transmission security analysis data to generate power transmission stability data; Step S34 includes the following steps: Step S341: extracting the response time of the power grid edge computing control data to obtain power transmission response time data; capturing abnormal logs of the power grid edge server according to the power transmission response time data to generate power transmission system paralysis analysis data; Step S342: extracting data access logs of power grid edge computing control data to obtain power transmission data access behavior data; capturing abnormal traffic of the power grid edge server according to the power transmission access behavior data to generate power transmission information leakage analysis data; Step S343: extracting power system parameters from the power grid edge computing control data to obtain power transmission system data, wherein the power transmission system data includes power transmission current data and power transmission voltage data; capturing abnormal loads of equipment on the power grid edge server according to the power transmission current data and the power transmission voltage data to generate power transmission stability analysis data; Step S344: Merge the power transmission system paralysis analysis data, the power transmission information leakage analysis data and the power transmission stability analysis data in data time series to generate power grid transmission safety analysis data; perform power control stability regulation on the real-time power distribution monitoring data according to the power grid transmission safety analysis data to generate power transmission stability data. 2. The method for controlling power transmission data of a smart grid according to claim 1, wherein step S1 comprises the following steps: Step S11: using sensors to obtain real-time power data and smart grid environment data; Step S12: standardizing the data formats of the real-time power data and the smart grid environment data to generate real-time power standard data and smart grid standard environment data; filling missing values of the real-time power standard data and the smart grid standard environment data to generate real-time power complete data and smart grid complete environment data; Step S13: fusing the real-time power complete data and the smart grid complete environment data to generate a comprehensive power environment data set; filtering the power grid operation dynamic load data for the comprehensive power environment data set to generate a comprehensive power dynamic load data set; Step S14: Performing data dimensionality reduction on the comprehensive power dynamic load data set by principal component analysis method to generate a comprehensive power dynamic load reduced dimensionality data set; performing curve conversion on the comprehensive power dynamic load reduced dimensionality data set to generate a real-time comprehensive energy load curve. 3. The method for controlling power transmission data of a smart grid according to claim 1, wherein step S4 comprises the following steps: Step S41: converting the power transmission stability data into a three-dimensional point cloud to generate a three-dimensional power transmission model; designing an adaptive control system based on the three-dimensional power transmission model to generate power grid transmission control design data; Step S42: Perform nonlinear control on the power grid transmission control design data through fuzzy control theory to generate power grid fuzzy controller data; perform reinforcement learning on the power grid fuzzy controller data to generate power grid transmission intelligent control data; perform data visualization on the power grid transmission intelligent control data to generate an intelligent power grid transmission data control report. 4. A power transmission data control system for a smart grid, characterized in that it is used to execute the power transmission data control method for a smart grid as claimed in claim 1, and the power transmission data control system for the smart grid comprises: The load analysis module is used to obtain real-time power data and smart grid environment data; perform data fusion on the real-time power data and smart grid environment data to generate a comprehensive power environment data set; perform dynamic load curve conversion on the comprehensive power environment data set to generate a real-time comprehensive energy load curve; The power distribution module is used to extract load peak data from the real-time comprehensive energy load curve based on a preset peak screening number to obtain dynamic power load peak data; perform model training on the dynamic power load peak data to generate a power demand prediction model; perform dynamic power distribution on the dynamic power load peak data through the power demand prediction model to generate an optimal power distribution plan; The stability control module is used to collect device information based on the optimal power distribution plan to obtain edge device deployment information data; perform real-time grid adjustment on the smart grid based on the edge device deployment information data to generate grid edge computing control data; perform power control stability control on the grid edge computing control data to generate power transmission stability data; The linear control module is used to convert the power transmission stability data into three-dimensional point cloud to generate a three-dimensional power transmission model; perform nonlinear control of the power grid based on the three-dimensional power transmission model to generate intelligent control data for power grid transmission; and visualize the intelligent control data for power grid transmission to generate a smart grid transmission data control report.