A power grid load forecasting method and system based on stochastic power flow calculation

Abstract

The present invention relates to the technical field of power grid load forecasting, and particularly to a power grid load forecasting method and system based on stochastic power flow calculation. The method includes the following steps: obtaining the operation data of the regional power grid; performing data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; performing a multi-level impact analysis on the influence of the new power grid energy supply stage on the operation data of the regional power grid to generate a fluctuation impact factor for the energy generation stage; performing a power transmission path analysis on the standard operation data of the regional power grid to generate power transmission path data; calculating the transmission distance for the power transmission path data to obtain power transmission distance data; comparing the power transmission distance data with a preset standard power transmission distance threshold to generate long-distance power transmission path data. The present invention improves the accuracy of power grid load forecasting through meticulous data integration and complex simulation.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid load forecasting, and particularly to a power grid load forecasting method and system based on stochastic power flow calculation. Background Art

[0002] With the expansion of the power system and the growth of load demand, people began to attempt load forecasting methods based on statistical models. With the progress of computer technology, time series analysis became the mainstream, and load forecasting was achieved through pattern recognition of historical data. With the introduction of artificial neural networks (ANNs), which brought a revolutionary change to load forecasting, ANNs were able to handle non-linear relationships and complex data, improving the forecasting accuracy. Entering the 21st century, with the development of machine learning technologies such as support vector machines (SVMs), load forecasting models have become more diverse and refined. With the rise of big data technology, load forecasting began to integrate multi-source data, such as weather, economic activities and other factors, further improving the forecasting accuracy and reliability. In recent years, the application of deep learning technologies such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs) has enabled load forecasting to handle more complex time series data and made significant progress in real-time and accuracy. At the same time, integrated forecasting methods such as model fusion and ensemble learning have gradually become important means to improve the forecasting robustness and resilience. However, traditional forecasting methods often do not consider in detail the stability of power flow and stroboscopic losses during long-distance transmission in power transmission path analysis, resulting in low forecasting accuracy. At the same time, the dependence on the analysis of distribution system capacity and regional electricity consumption patterns is relatively low, and the possibility of load overload cannot be fully predicted, thus leading to low accuracy of power grid load forecasting. Summary of the Invention

[0003] Based on this, it is necessary to provide a power grid load forecasting method and system based on stochastic power flow calculation to solve at least one of the above technical problems.

[0004] To achieve the above object, a power grid load forecasting method based on stochastic power flow calculation, the method includes the following steps:

[0005] Step S1: Obtain the operation data of the regional power grid; perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; perform a multi-level new power grid energy supply stage impact analysis on the operation data of the regional power grid to generate an energy generation stage fluctuation impact factor;

[0006] Step S2: Analyze the power transmission path of the standard regional power grid operation data to generate power transmission path data; calculate the transmission distance of the power transmission path data to obtain power transmission distance data; compare the power transmission distance data with the preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the fluctuation influence factor in the power transmission stage.

[0007] Step S3: Obtain the distribution system capacity data; analyze the regional power consumption pattern of the standard regional power grid operation data to generate regional power consumption pattern data; perform load overload analysis on the distribution system capacity data according to the regional power consumption pattern data to generate regional distribution load overload data; calculate the power consumption demand of the regional distribution load overload data to obtain the fluctuation influence factor in the regional distribution stage.

[0008] Step S4: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation influence factor in the energy generation stage, the fluctuation influence factor in the power transmission stage, and the fluctuation influence factor in the regional distribution stage to generate a power grid fluctuation simulation data set; perform power grid load forecasting on the power grid fluctuation simulation data set to generate power grid load forecasting data.

[0009] Through preprocessing, the present invention can ensure the consistency of data in structure and format, facilitating subsequent analysis and comparison. Remove noise and outliers in the data to improve the accuracy and reliability of the data. By analyzing the influence of different energy supply stages on the power grid operation at multiple levels, it helps to understand the impact of fluctuations in the energy generation stage on the power grid stability. Analyze the power transmission path, especially the long-distance transmission path, to optimize the efficiency and stability of power transmission. By analyzing the stability performance of power flow, the stroboscopic phenomenon in power transmission can be reduced, improving the stability of the power grid. Calculating the loss of the power transmission path helps to reduce the energy loss during energy transmission, improving the energy utilization efficiency. Analyzing the regional power consumption pattern and the overload situation of the distribution load can optimize the capacity configuration of the distribution system, improving the stability and reliability of power supply. By accurately calculating the power consumption demand, the risk of power supply interruption caused by load overload in the distribution system can be reduced, ensuring the continuity of power supply. Based on the simulation data set, power grid load forecasting can improve the forecasting accuracy, supporting power grid operators to make more accurate decisions, such as power dispatch and equipment operation optimization. Therefore, through meticulous data integration and complex simulation, the present invention improves the accuracy of power grid load forecasting.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain the operation data of the regional power grid;

[0012] Step S12: Perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid, where the data preprocessing includes data cleaning, filling of missing data values, and data standardization;

[0013] Step S13: Classify the power supply energy types of the regional power grid to obtain the classified data of the power supply energy types of the regional power grid, where the classified data of the power supply energy types of the regional power grid includes traditional energy power supply data and new energy power supply data;

[0014] Step S14: Perform a multi-level analysis on the new energy power supply data and the traditional energy power supply data to generate the fluctuation impact factors of the energy generation stage.

[0015] Through data preprocessing of the operation data of the regional power grid, including steps such as cleaning, filling of missing values, and standardization, a set of standardized operation data of the power grid can be obtained. These data have consistency and comparability, which is helpful for subsequent analysis and modeling. By classifying the power supply energy types of the operation data of the regional power grid, the data can be divided into two categories: traditional energy power supply data and new energy power supply data. This classification can help analyze and compare the usage and impacts of different types of energy. By performing a multi-level analysis on the new energy power supply data and the traditional energy power supply data, the fluctuation impact factors of the energy generation stage can be obtained. The factors can reflect the supply situation and volatility of different energy types at different time periods, which is helpful for understanding the stability and sustainability of energy supply.

[0016] Preferably, step S14 includes the following steps:

[0017] Step S141: Confirm the traditional energy power supply equipment sites for the traditional energy power supply data to obtain the analysis of the impact of extreme weather, and generate the data of the traditional energy power supply equipment sites; collect the meteorological sensor data through the data of the traditional energy power supply equipment sites to obtain the meteorological data of the traditional energy power supply equipment sites; perform an extreme weather analysis on the meteorological data of the traditional energy power supply equipment sites to generate the impact factors of traditional energy generation;

[0018] Step S142: Classify the new energy supply types for the new energy power supply data to generate the classified data of the new energy supply types, where the classified data of the new energy supply types includes wind power generation data and solar power generation data; confirm the power supply equipment sites based on the wind power generation data and the solar power generation data to obtain the data of the new energy power supply equipment sites;

[0019] Step S143: Collect meteorological sensor data through the data of new energy power supply equipment sites to obtain the meteorological data of new energy power supply equipment sites; conduct an analysis of the influence of sunlight transformation on the meteorological data of new energy power supply equipment sites based on solar power generation data to generate sunlight transformation influence data, where the sunlight transformation influence data includes cloud cover data and sunshine duration data; calculate the solar power generation efficiency based on the cloud cover data and sunshine duration data for the solar power generation data to obtain the solar power generation influence factor;

[0020] Step S144: Extract wind power characteristics from the meteorological data of new energy power supply equipment sites according to the wind power generation data to obtain wind power characteristic data, where the wind power characteristic data includes wind direction data and wind speed data; calculate the wind power generation efficiency based on the wind direction data and wind speed data for the wind power generation data to obtain the wind power generation influence factor; integrate the traditional energy power generation influence factor, the solar power generation influence factor and the wind power generation influence factor to generate the new energy power supply stage fluctuation influence factor.

[0021] The present invention helps to accurately locate the geographical distribution of traditional energy power supply equipment by identifying the sites of such equipment, improving the accuracy of data collection and analysis. By analyzing the impact of extreme weather on traditional energy power supply equipment, potential risks and challenges can be identified, providing a basis for subsequent preventive measures. By collecting data through meteorological sensors, real-time meteorological information can be obtained, timely reflecting environmental changes. The types of meteorological data collected are rich, providing comprehensive data support for subsequent climate analysis. By analyzing extreme weather, the impact of climate on traditional energy power generation can be predicted and evaluated, corresponding defensive measures can be formulated, the resilience of the power supply system can be improved, and the generated traditional energy power generation impact factors can be used as important reference data for the operation and management of power supply equipment, helping to optimize the energy supply strategy. Classifying new energy power supply data helps to classify and manage and analyze the characteristics and requirements of different types of new energy. By differentiating between wind power and solar power generation, resources can be allocated more effectively, improving the utilization efficiency of new energy. Identifying the sites of new energy power supply equipment helps to accurately locate and optimize the geographical distribution of the equipment, making full use of natural resources. The generated new energy power supply equipment site data provides an accurate basis for subsequent data collection and analysis. Through the real-time monitoring of meteorological sensors, meteorological data of new energy power supply equipment sites can be obtained in a timely manner, providing reliable data support for analyzing the power generation efficiency of solar and wind energy. The collected data covers a variety of meteorological elements, ensuring the comprehensiveness and accuracy of the data. Through the analysis of the impact of sunlight transformation, the impact of cloud cover and sunshine duration on solar power generation can be understood, and the utilization strategy of solar power generation can be optimized. The generated sunlight transformation impact data helps to evaluate and improve the efficiency of solar power generation, ensuring stable power supply. Based on the cloud cover and sunshine duration data, the calculation of solar power generation efficiency can accurately evaluate the actual effect of solar power generation. The obtained solar power generation impact factors can be used as an important reference for optimizing the configuration of solar power generation, improving the overall power generation efficiency. By extracting wind characteristics, understanding the changes in wind direction and wind speed helps to comprehensively grasp the distribution and changes of wind resources. The generated wind characteristic data provides reliable data support for the calculation of wind power generation efficiency. By calculating the wind power generation efficiency, the utilization of wind resources can be accurately evaluated, and the configuration and operation of wind power generation equipment can be optimized. The obtained wind power generation impact factors help to better utilize wind resources and improve the overall efficiency of wind power generation.

[0022] Preferably, step S2 includes the following steps:

[0023] Step S21: Conduct a grid transmission topology analysis on the standard regional power grid operation data to generate a grid transmission topology network; conduct a power transmission path analysis on the grid transmission topology network to generate power transmission path data; calculate the transmission distance for the power transmission path data to obtain power transmission distance data;

[0024] Step S22: Compare the power transmission distance data with a preset standard power transmission distance threshold. When the power transmission distance data is greater than or equal to the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as long-distance power transmission path data; when the power transmission distance data is less than the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as short-distance power transmission path data and eliminate it.

[0025] Step S23: Analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; perform power stroboscopic detection on the long-distance power transmission path data to obtain grid transmission power stroboscopic data.

[0026] Step S24: Calculate the power transmission loss of the grid transmission power stroboscopic data through the power transmission loss calculation formula to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate a fluctuation impact factor in the power transmission stage.

[0027] Through topology analysis and path analysis, the present invention can accurately identify power transmission paths, understand the structure and transmission conditions of the power grid. The calculation of transmission distance data helps manage and optimize power transmission paths, reduce losses and improve efficiency. By comparing the transmission distance data, long-distance and short-distance transmission paths can be classified and managed, and targeted optimization can be carried out. Eliminating short-distance transmission path data helps simplify the power grid structure, reduce redundant paths, and improve transmission efficiency. Through power flow stability performance analysis, unstable factors in power flow can be identified and solved, improving the overall stability of the power grid. Stroboscopic detection can help identify stroboscopic problems in power transmission, ensuring power quality and user experience. By calculating transmission losses, the losses of power during transmission can be quantified, and the optimization direction can be found. Integrating stability performance data and transmission loss data, the generated fluctuation impact factor can comprehensively evaluate the fluctuation of electric energy during transmission, providing a basis for power grid optimization. Through the above steps, the transmission paths and power flow of the power grid can be comprehensively analyzed and optimized, improving the stability and efficiency of power transmission. The generated fluctuation impact factor in the power transmission stage provides important data support and decision-making basis for power grid management and optimization.

[0028] Preferably, the power transmission loss calculation formula in Step S24 is specifically as follows:

[0029] ;

[0030] In the formula, represents the power transmission loss, represents the cable transmission length, represents the current loss coefficient.

[0031] Expressed as time The average current within Expressed as the resistance loss coefficient Expressed as time The average voltage within Expressed as the resistance on the Power transmission path Expressed as the instantaneous electric field change rate coefficient Expressed as the area of the power transmission region Expressed as described at The electric field strength at the point Expressed as the path The infinitesimal length of Expressed as the spatial abscissa point Expressed as the spatial ordinate point

[0032] The present invention analyzes and integrates a power transmission loss calculation formula. The current loss coefficient in the formula Represents the direct impact of current on transmission loss. As the current increases, the resistance inside the wire causes greater losses. By controlling the current loss coefficient , the circuit design and power transmission system can be optimized, energy losses caused by current can be reduced, and transmission efficiency can be improved. The resistance loss coefficient in the formula Reflects the contribution of resistance to energy losses during power transmission. The greater the resistance, the more obvious the losses. By optimizing the design of the power transmission path or selecting materials with lower impedance, the resistance loss coefficient Can be reduced, thereby reducing transmission losses. The instantaneous electric field change rate coefficient in the formula Describes the impact of the change in electric field strength on transmission loss. A rapid change in electric field strength may cause additional energy losses. By understanding and controlling the rate of change of electric field strength, the design of the power system can be optimized, transient losses can be reduced, and the stability and efficiency of power transmission can be improved. By integrating over the entire transmission path, the power loss can be comprehensively evaluated, providing accurate data support for system optimization. When using the conventional power transmission loss calculation formula in the art, the power transmission loss can be obtained. By applying the power transmission loss calculation formula provided by the present invention, the power transmission loss can be calculated more accurately. The combined effect of these parameters is that through quantitative analysis of key factors such as current, voltage, resistance, and electric field strength, the sources of energy losses during power transmission can be deeply understood and evaluated, thereby guiding design and operation decisions and achieving the efficient operation of the power transmission system and the maximization of energy utilization efficiency.

[0033] Preferably, the power stroboscopic detection of the long-distance power transmission path data includes:

[0034] Divide the long-distance power transmission path data based on a preset distance threshold to generate the position information data of the long-distance power transmission path division points; deploy power transmission detection nodes for the position information data of the long-distance power transmission path division points to obtain power transmission detection nodes, where the power transmission detection nodes are deployed with power sensors and signal sensors;

[0035] Discriminate the power transmission of the power transmission detection nodes through the power sensors. When the power sensors capture the current of the power transmission detection nodes, use the signal sensors to collect the passing current signals to obtain the power transmission signals; monitor the frequency and phase of the power transmission signals to obtain the power transmission signal frequency and the power transmission signal phase; calculate the power spectral density of the power transmission signal frequency and the power transmission signal phase to obtain the power frequency band power spectral density data;

[0036] Extract the energy peaks from the power frequency band power spectral density data to obtain the power grid transmission power stroboscopic data.

[0037] The present invention divides the path based on a preset distance threshold to ensure the precise management of the long-distance power transmission path, which helps to optimize the power grid structure. The generated position information data of the path division points provides an accurate position reference for the deployment of the detection nodes. Deploying the detection nodes at the key path points ensures the comprehensive monitoring of the key links of power transmission, improves the coverage rate and effectiveness of monitoring. The combination of the power sensors and the signal sensors can capture and collect the power transmission signals in real time to ensure the timeliness and accuracy of the data. By discriminating the current situation of the power transmission nodes through the power sensors, the accuracy of signal collection is ensured. When the power sensors capture the current, the signal sensors automatically collect the signals, improving the automation and efficiency of the data collection process. Monitoring the frequency and phase of the power transmission signals ensures the high-precision analysis of the power transmission signals. The frequency and phase monitoring provides comprehensive power transmission signal characteristic data, providing a solid foundation for subsequent analysis. By calculating the power spectral density, the frequency characteristics of the power transmission signals can be deeply analyzed to obtain detailed power frequency band power spectral density data. The power spectral density calculation helps to identify the frequency characteristics of the power transmission signals and provides important data support for stroboscopic detection. The energy peak extraction can accurately identify the energy changes in the power frequency band to obtain the power grid transmission power stroboscopic data. Through stroboscopic detection, the stroboscopic problems in the power grid transmission can be identified and solved to ensure the quality and stability of power transmission.

[0038] Preferably, step S3 includes the following steps:

[0039] Step S31: Obtain the capacity data of the distribution system; conduct regional population density analysis on the operation data of the standard regional power grid to obtain regional population density data; conduct regional electricity consumption pattern analysis on the operation data of the standard regional power grid through the regional population density data to generate regional electricity consumption pattern data;

[0040] Step S32: Calculate the maximum load capacity based on the regional electricity consumption pattern data for the capacity data of the distribution system to obtain the maximum load capacity of the regional distribution system; conduct load overload analysis on the maximum load capacity of the regional distribution system to generate regional distribution load overload data;

[0041] Step S33: Conduct time series analysis on the regional distribution load overload data to generate regional distribution load overload time series data; calculate the electricity demand based on the regional distribution load overload time series data for the regional electricity consumption pattern data to obtain the influencing factor of regional distribution stage fluctuation.

[0042] Through regional population density analysis and electricity consumption pattern analysis, the present invention can accurately evaluate the electricity demand, improve the scientific nature of power grid planning and management. The generated regional electricity consumption pattern data provides a basis for the optimization of the distribution system and the rational allocation of resources. By calculating the maximum load capacity and conducting load overload analysis, the risk of power grid overload can be identified and prevented in advance, ensuring the safe operation of the power grid. Understanding the maximum load capacity and overload situation of the distribution system helps to optimize the operation of the distribution system and improve the distribution efficiency. Through time series analysis, the change of load can be dynamically monitored, the time period of load overload can be identified, improving the real-time performance and flexibility of power grid management. The calculation of electricity demand provides accurate data support for the load prediction and scheduling of the power grid, ensuring the stability of power supply. Through the above steps, the capacity and load situation of the distribution system can be comprehensively analyzed and optimized. The generated influencing factor of regional distribution stage fluctuation provides an important decision-making basis for the planning and management of the power grid. Through the analysis of regional population density and electricity consumption pattern, the electricity demand can be accurately evaluated, the resource allocation can be optimized, the risk of power grid overload can be prevented, the change of load can be dynamically monitored, and the electricity demand can be accurately predicted, thereby improving the overall operation efficiency and stability of the power grid.

[0043] Preferably, the regional electricity consumption pattern analysis on the operation data of the standard regional power grid through the regional population density data includes:

[0044] Conduct electricity extreme value averaging on the operation data of the standard regional power grid according to the regional population density data to generate the overall electricity consumption level data of the regional population;

[0045] Conduct daily electricity consumption behavior characteristic analysis on the operation data of the standard regional power grid through the overall electricity consumption level data of the regional population to generate a daily electricity consumption load curve; extract the peak characteristic differences of the daily electricity consumption load curve to obtain electricity peak characteristic difference data;

[0046] Calculate the change curvature of the daily electricity load curve to obtain the electricity load change curvature data; perform regional electricity consumption pattern analysis based on the electricity load change curvature data and the difference data of electricity peak characteristics, and generate regional electricity consumption pattern data.

[0047] In the present invention, by equalizing the extreme values of electricity consumption, the influence of extreme values in the data is eliminated, making the data smoother and more standardized, generating the overall electricity consumption level data of the regional population, and providing basic data for subsequent electricity consumption pattern analysis. By analyzing the characteristics of daily electricity consumption behavior, the electricity consumption habits and behavior patterns of the population in different regions can be deeply understood, generating the daily electricity load curve, and providing a specific data basis for subsequent feature extraction and change curvature calculation. By extracting the difference data of electricity peak characteristics, the electricity peaks in different time periods can be accurately identified, which is helpful for power grid load management. The difference data of peak characteristics reveals the differences in electricity peak characteristics in different regions and time periods, providing key feature data for electricity consumption pattern analysis. By calculating the change curvature of the electricity load, the dynamic changes of the electricity load can be monitored, and the fluctuation trend of the electricity load can be identified. The change curvature data helps to analyze the change trend of the electricity load, providing an important reference basis for load forecasting and management. Based on the electricity load change curvature data and the difference data of electricity peak characteristics, comprehensive regional electricity consumption pattern analysis is carried out to generate comprehensive electricity consumption pattern data. The electricity consumption pattern data provides a scientific basis for the planning and management of the power grid, helps to optimize the allocation of power grid resources, and improves the operation efficiency of the power grid. Through the detailed analysis of the operation data of the standard regional power grid, comprehensive regional electricity consumption pattern data can be obtained. Steps such as equalizing the extreme values of electricity consumption, analyzing the characteristics of daily electricity consumption behavior, extracting the difference of peak characteristics, and calculating the change curvature make the analysis of power grid operation data more accurate and comprehensive. These data and analysis results provide important decision-making support for power grid planning and management, can effectively optimize the allocation of power grid resources, prevent the overload risk during the electricity peak period, improve the stability and efficiency of power grid operation, and ensure the reliability and sustainability of power supply.

[0048] Preferably, step S4 includes the following steps:

[0049] Step S41: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation impact factors in the energy generation stage, the fluctuation impact factors in the power transmission stage, and the fluctuation impact factors in the regional distribution stage, and generate a power grid fluctuation simulation data set;

[0050] Step S42: Divide the power grid fluctuation simulation data set to generate a model training set and a model test set; use the convolutional neural network algorithm to train the model training set to generate a real-time load forecasting training model; perform model test iteration on the real-time load forecasting training model through the model test set, so as to generate a real-time load forecasting model;

[0051] Step S43: Import the standard regional power grid operation data into the real-time load forecasting model for power grid load forecasting, so as to generate power grid load forecasting data.

[0052] Through stochastic power flow calculation and Monte Carlo simulation, the present invention can comprehensively analyze the influencing factors of fluctuations in each stage, generate a comprehensive power grid fluctuation simulation data set, and improve the accuracy and reliability of subsequent power grid load forecasting by comprehensively considering various fluctuation factors. Through reasonable data set division, the effectiveness of model training and testing is ensured, and the performance of the forecasting model is improved. The convolutional neural network algorithm is used for model training and testing, and its powerful feature extraction and learning capabilities are utilized to improve the accuracy and generalization ability of the real-time load forecasting model. Through model test iteration, the model parameters are continuously optimized to improve the stability and forecasting accuracy of the model. The generated real-time load forecasting model can perform real-time load forecasting based on the actual power grid operation data and provide dynamic load forecasting data. Through accurate power grid load forecasting, the risks of power grid overload and instability can be identified and prevented in advance, ensuring the safe operation of the power grid. The real-time load forecasting data provides an important reference basis for power grid dispatching and management, helps to optimize power grid resource allocation, and improves the operation efficiency of the power grid. Through the detailed analysis and processing in Step S4, the power grid fluctuations can be effectively simulated and the load can be forecasted. By using stochastic power flow calculation and Monte Carlo simulation, a comprehensive power grid fluctuation simulation data set is generated, and through the convolutional neural network algorithm, a high-precision real-time load forecasting model is generated. The finally generated power grid load forecasting data provides important decision-making support for the dispatching and management of the power grid, helps to optimize power grid resource allocation, improves the stability and efficiency of power grid operation, and ensures the reliability and continuity of power supply.

[0053] In this specification, a power grid load forecasting system based on stochastic power flow calculation is provided for implementing the above-mentioned power grid load forecasting method based on stochastic power flow calculation. The power grid load forecasting system based on stochastic power flow calculation includes:

[0054] A power generation stage influence module, configured to obtain the operation data of the regional power grid; perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; perform multi-level new power grid energy supply stage influence analysis on the operation data of the regional power grid to generate fluctuation influence factors in the energy power generation stage;

[0055] The transmission stage impact module is used to analyze the power transmission path of the standard regional power grid operation data to generate power transmission path data; calculate the transmission distance of the power transmission path data to obtain power transmission distance data; compare the power transmission distance data with the preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the fluctuation impact factor of the power transmission stage.

[0056] The power supply stage impact module is used to obtain the distribution system capacity data; analyze the regional power consumption pattern of the standard regional power grid operation data to generate regional power consumption pattern data; perform load overload analysis on the distribution system capacity data according to the regional power consumption pattern data to generate regional distribution load overload data; calculate the power consumption demand of the regional distribution load overload data to obtain the fluctuation impact factor of the regional distribution stage.

[0057] The power flow calculation simulation module is used to perform Monte Carlo simulation on the fluctuation impact factor of the energy generation stage, the fluctuation impact factor of the power transmission stage, and the fluctuation impact factor of the regional distribution stage by using the stochastic power flow calculation to generate a power grid fluctuation simulation data set; perform power grid load forecasting on the power grid fluctuation simulation data set to generate power grid load forecasting data.

[0058] The beneficial effects of the present invention are as follows. By preprocessing the regional power grid operation data, the data can be cleaned and standardized to generate standard regional power grid operation data, providing an accurate data basis for subsequent analysis. Through multi-level analysis of the regional power grid operation data, the impact factors of different power grid energy supply stages can be evaluated, helping to understand the energy supply situation of the power grid and related factors. By analyzing the power transmission path and calculating the distance of the standard regional power grid operation data, the power transmission path and distance can be determined, providing basic data for subsequent power flow stability and transmission loss analysis. By analyzing the power flow stability and calculating the power stroboscopic loss of the long-distance power transmission path data, the stability and loss of power transmission can be evaluated, providing a reference for power grid operation optimization. By analyzing the power consumption pattern and performing distribution load overload analysis on the standard regional power grid operation data, the distribution load situation of the region can be evaluated, and the power consumption demand can be calculated, providing a basis for power grid load management and planning. By performing Monte Carlo simulation on the fluctuation impact factor by using the stochastic power flow calculation to generate a power grid fluctuation simulation data set and performing power grid load forecasting, the load situation of the power grid can be predicted, providing a reference for power dispatching and energy planning. Therefore, the present invention improves the accuracy of power grid load forecasting through meticulous data integration and complex simulation. Description of the Drawings

[0059] Figure 1 It is a schematic diagram of the step flow of a power grid load forecasting method based on stochastic power flow calculation;

[0060] Figure 2 It is Figure 1 a detailed implementation step flow diagram of step S2 in

[0061] Figure 3 It is Figure 1 a detailed implementation step flow diagram of step S3 in

[0062] Figure 4 It is Figure 1 a detailed implementation step flow diagram of step S4 in

[0063] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0064] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work fall within the scope of protection of the present invention.

[0065] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the 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 in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0066] It should be understood that although terms such as "first", "second", etc. may be used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0067] To achieve the above object, please refer to Figures 1 to 4 , a power grid load forecasting method based on stochastic power flow calculation, the method includes the following steps:

[0068] Step S1: Obtain the operation data of the regional power grid; perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; perform multi-level impact analysis of the new power grid energy supply stage on the operation data of the regional power grid to generate the fluctuation impact factor of the energy generation stage.

[0069] Step S2: Analyze the power transmission path of the standard operation data of the regional power grid to generate power transmission path data; calculate the transmission distance of the power transmission path data to obtain the power transmission distance data; compare the power transmission distance data with the preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the stable performance of the power flow of the long-distance power transmission path data to generate the stable performance data of the power flow; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain the power transmission loss data; integrate the stable performance data of the power flow and the power transmission loss data to generate the fluctuation impact factor of the power transmission stage.

[0070] Step S3: Obtain the distribution system capacity data; analyze the regional electricity consumption pattern of the standard operation data of the regional power grid to generate the regional electricity consumption pattern data; perform load overload analysis on the distribution system capacity data according to the regional electricity consumption pattern data to generate the regional distribution load overload data; calculate the electricity demand of the regional distribution load overload data to obtain the fluctuation impact factor of the regional distribution stage.

[0071] Step S4: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation impact factor of the energy generation stage, the fluctuation impact factor of the power transmission stage, and the fluctuation impact factor of the regional distribution stage to generate a power grid fluctuation simulation dataset; perform power grid load forecasting on the power grid fluctuation simulation dataset to generate power grid load forecasting data.

[0072] Through preprocessing, the present invention can ensure the consistency of data in terms of structure and format, facilitating subsequent analysis and comparison. Noise and outliers in the data are removed to improve the accuracy and reliability of the data. By analyzing the impact of different energy supply stages on grid operation at multiple levels, it helps to understand the impact of fluctuations in the energy generation stage on grid stability. Analyzing the power transmission path, especially the long-distance transmission path, can optimize the efficiency and stability of power transmission. By analyzing the stability performance of power flow, the stroboscopic phenomenon in power transmission can be reduced, improving grid stability. Calculating the loss of the power transmission path helps to reduce energy loss during energy transmission and improve energy utilization efficiency. Analyzing the electricity consumption patterns and distribution load overload conditions in a region can optimize the capacity configuration of the distribution system and improve the stability and reliability of power supply. By accurately calculating the electricity demand, the risk of power supply interruption caused by load overload in the distribution system can be reduced, ensuring the continuity of power supply. By accurately calculating the electricity demand, the risk of power supply interruption caused by load overload in the distribution system can be reduced, ensuring the continuity of power supply. Based on the simulated dataset, grid load forecasting can be carried out to improve the forecasting accuracy, supporting grid operators to make more accurate decisions, such as power dispatch and equipment operation optimization. Therefore, through meticulous data integration and complex simulation, the present invention improves the accuracy of grid load forecasting.

[0073] In the embodiment of the present invention, with reference to Figure 1 as described, it is a schematic diagram of the step flow of a grid load forecasting method based on stochastic power flow calculation according to the present invention. In this example, the grid load forecasting method based on stochastic power flow calculation includes the following steps:

[0074] Step S1: Obtain the operation data of the regional power grid; perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; perform multi-level analysis on the impact of the new grid energy supply stage on the operation of the regional power grid to generate the influence factor of fluctuations in the energy generation stage;

[0075] In the embodiments of the present invention, by obtaining regional power grid operation data from a power grid operation management system or a relevant data provider, such data generally includes information such as power supply volume, load conditions, power transmission paths, power losses, etc. Clean the obtained regional power grid operation data, process the error values, missing values and abnormal data in the data to ensure the integrity and accuracy of the data. Standardize the cleaned power grid operation data to unify the dimension and range of the data for subsequent analysis and comparison. Based on the standard regional power grid operation data, analyze the power supply volume of different energy power generation facilities (such as thermal power plants, wind farms, solar cell arrays, etc.). Considering the operation modes and production capacities of various energy power generation facilities, calculate the contribution degree and volatility of each energy source in the total power supply. According to the obtained energy power generation stage data, calculate the fluctuation impact factors of the energy power generation stage, and these factors reflect the degree of fluctuation impact of different energy power generation methods on power supply. Statistical methods or model calculation methods, such as time series analysis, spectrum analysis or probability distribution analysis, can be used to quantify the volatility of each energy power generation method.

[0076] Step S2: Analyze the power transmission paths of the standard regional power grid operation data to generate power transmission path data; calculate the transmission distances of the power transmission path data to obtain power transmission distance data; compare the power transmission distance data with a preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the fluctuation impact factor of the power transmission stage;

[0077] In the embodiments of the present invention, by obtaining the power transmission path information in the operation data of the standard regional power grid, cleaning the data to process error values and abnormal data, ensuring the accuracy and integrity of the data. According to the power transmission path data, calculate the power transmission distance of each transmission path. The power transmission distance generally refers to the actual transmission distance from the power generation site to the load terminal. Set a preset standard power transmission distance threshold, such as a threshold determined according to factors such as the performance of power transmission equipment, the type of transmission line, and transmission loss. Compare the calculated power transmission distance data with the preset threshold. Mark the transmission path data that exceeds the preset distance threshold as long-distance power transmission path data. Conduct an analysis on the stable performance of power flow for the long-distance power transmission path data. Analyze the stability of current and voltage in the path, considering power fluctuations and power changes in the operation of the power grid. According to the stroboscopic situation in the power transmission path, calculate the impact of stroboscopy on power transmission. Use the power transmission loss calculation formula to quantify the stroboscopic loss into specific data indicators. Integrate the power flow stable performance data and the power transmission loss data. Appropriate methods such as weighted average can be used to combine the stability and loss data to generate the fluctuation impact factor in the power transmission stage.

[0078] Step S3: Obtain the distribution system capacity data; conduct an analysis on the regional power consumption pattern for the operation data of the standard regional power grid to generate regional power consumption pattern data; conduct a load overload analysis on the distribution system capacity data according to the regional power consumption pattern data to generate regional distribution load overload data; calculate the power consumption demand for the regional distribution load overload data to obtain the fluctuation impact factor in the regional distribution stage;

[0079] In the embodiments of the present invention, by obtaining the distribution system capacity data of the standard region, these data include the rated capacities of various power equipment, such as the rated load capacities of transformers, cables, switchgear, etc. Use the operation data of the standard regional power grid to conduct an analysis on the regional power consumption pattern. Analyze the power consumption behavior of the region, including daily load curves, peak-valley characteristics, and seasonal variations, etc. According to the regional power consumption pattern data, calculate the maximum load of the regional distribution system. The maximum load generally refers to the highest load level that the distribution system needs to support within a certain time period. Conduct a load overload analysis on the distribution system capacity data. Compare the actual load demand with the rated capacity of the distribution system to evaluate whether there is a load overload situation. According to the results of the load overload analysis, calculate the fluctuation impact factor in the regional distribution stage. Consider the impact of load overload on the stability of the power system, quantify the degree of load overload, and generate the fluctuation impact factor accordingly.

[0080] Step S4: Use probabilistic load flow calculation to perform Monte Carlo simulation on the fluctuation impact factors in the energy generation stage, power transmission stage, and regional power distribution stage, generating a power grid fluctuation simulation dataset; perform power grid load forecasting on the power grid fluctuation simulation dataset to generate power grid load forecasting data.

[0081] In the embodiment of the present invention, by using the probabilistic load flow calculation method, the volatility and uncertainty of energy generation are considered. Based on Monte Carlo simulation, multiple sets of data of the fluctuation impact factors in the energy generation stage are generated. Perform probabilistic load flow calculation on the power transmission path data, considering the uncertainty and volatility of power transmission. Use the Monte Carlo method to simulate multiple sets of data of the fluctuation impact factors in the power transmission stage. According to the data of the fluctuation impact factors in the regional power distribution stage generated in the aforementioned step S3. Also apply Monte Carlo simulation, considering the volatility and uncertainty under different load conditions. Integrate the data of the fluctuation impact factors in the energy generation stage, power transmission stage, and regional power distribution stage into a comprehensive power grid fluctuation simulation dataset. Ensure that the dataset contains combinations and diversities of different fluctuation factors to reflect the diversity and complexity in the actual operation of the power grid. Use the generated power grid fluctuation simulation dataset as input data for power grid load forecasting. Machine learning models (such as convolutional neural networks, recurrent neural networks, etc.) or traditional time series analysis methods can be used for power grid load forecasting. Divide the dataset into a model training set and a test set. Train the model, optimize the model parameters, and use the test set to evaluate and verify the model performance. According to the trained model, forecast the future power grid load. Generate timely and accurate power grid load forecasting data, reflecting the power grid load change trend under different fluctuation factors.

[0082] Preferably, step S1 includes the following steps:

[0083] Step S11: Obtain the operation data of the regional power grid;

[0084] Step S12: Perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid, where data preprocessing includes data cleaning, filling of missing data values, and data standardization;

[0085] Step S13: Classify the power supply energy types of the regional power grid for the operation data of the regional power grid to obtain the classified data of the power supply energy types of the regional power grid, where the classified data of the power supply energy types of the regional power grid includes traditional energy power supply data and new energy power supply data;

[0086] Step S14: Perform multi-level analysis on the impact of the new power grid energy supply stage on the new energy power supply data and traditional energy power supply data to generate the fluctuation impact factors in the energy generation stage.

[0087] In the embodiments of the present invention, detailed regional power grid operation data is obtained from the power grid operation department or the data monitoring system, including data in various links such as power generation, transmission, and distribution. Ensure the comprehensiveness and accuracy of the data, covering the power grid operation conditions in different periods and different regions. Remove the outliers and noise in the data to ensure the purity and effectiveness of the data. Fill in the missing values, which can be filled with the mean value, interpolation method, etc., to ensure the integrity of the data. Standardize the data so that the data can be compared and analyzed on a unified scale, and eliminate the dimension difference. According to the energy type information identified in the data, the power supply data is divided into traditional energy power supply data and new energy power supply data. The traditional energy power supply data includes thermal power, hydropower, etc., and the new energy power supply data includes wind energy, solar energy, etc. Record the division result in the power supply energy type division data. Confirm the traditional energy power supply equipment sites, analyze the impact of extreme climate, and generate traditional energy power supply equipment site data. Collect meteorological data through the site data, analyze the impact of extreme climate on traditional energy power generation, and generate impact factors. Confirm the new energy power supply equipment sites such as wind energy and solar energy, and generate new energy power supply equipment site data. Collect and analyze meteorological data such as wind power and sunshine hours, calculate the new energy power generation efficiency, and generate new energy power generation impact factors. Integrate the impact factors of traditional energy and new energy to generate a comprehensive energy power generation stage fluctuation impact factor.

[0088] Preferably, step S14 includes the following steps:

[0089] Step S141: Confirm the traditional energy power supply equipment sites for the traditional energy power supply data, obtain the extreme climate impact analysis, and generate traditional energy power supply equipment site data; collect meteorological sensor data through the traditional energy power supply equipment site data to obtain the traditional energy power supply equipment site meteorological data; conduct extreme climate analysis on the traditional energy power supply equipment site meteorological data to generate traditional energy power generation impact factors;

[0090] Step S142: Divide the new energy power supply data into new energy supply type division data, where the new energy supply type division data includes wind power generation data and solar power generation data; based on the wind power generation data and solar power generation data, confirm the power supply equipment sites to obtain new energy power supply equipment site data;

[0091] Step S143: Collect meteorological sensor data through the data of new energy power supply equipment sites to obtain the meteorological data of new energy power supply equipment sites; perform an analysis of the influence of sunlight transformation on the meteorological data of new energy power supply equipment sites based on solar power generation data to generate sunlight transformation influence data, where the sunlight transformation influence data includes cloud cover data and sunshine duration data; calculate the solar power generation efficiency based on the cloud cover data and sunshine duration data for the solar power generation data to obtain the solar power generation influence factor;

[0092] Step S144: Extract wind characteristics from the meteorological data of new energy power supply equipment sites based on wind power generation data to obtain wind characteristic data, where the wind characteristic data includes wind direction data and wind speed data; calculate the wind power generation efficiency based on the wind direction data and wind speed data for the wind power generation data to obtain the wind power generation influence factor; integrate the traditional energy power generation influence factor, the solar power generation influence factor, and the wind power generation influence factor to generate the fluctuation influence factor in the energy power supply stage.

[0093] In the embodiments of the present invention, the site locations and layouts of traditional energy power supply equipment are confirmed through geographic information data to ensure that the main energy supply points are covered. The historical meteorological data and local climate models are used to analyze the performance changes and stability of traditional energy power supply equipment sites under extreme climate conditions. Meteorological sensors are installed at traditional energy power supply equipment sites for data collection, including meteorological parameters such as temperature, humidity, wind speed, and precipitation. Based on the meteorological data and historical performance analysis, factors affecting the efficiency of traditional energy power generation are generated, such as the influence of temperature on the efficiency of power generation equipment. According to the regional resources and availability, new energy power supply types are divided, mainly including wind energy and solar energy. The sites suitable for installing new energy equipment are determined and confirmed, considering the richness of wind energy and solar energy resources and geographical conditions. Meteorological sensors are installed at new energy power supply equipment sites to collect meteorological data related to wind power generation and solar power generation, such as wind speed, wind direction, sunshine duration, and cloud cover. The performance of the solar power generation system under different weather conditions is analyzed, including the influence of sunny, cloudy, and overcast days on the power generation efficiency. According to the real-time and historical meteorological data, factors affecting the solar power generation efficiency are generated, such as cloud cover and sunshine duration. The expected efficiency of solar power generation is calculated using the cloud cover data and sunshine duration data for evaluating the system performance and stability. Key features such as wind speed and wind direction are extracted from the collected wind energy data to evaluate the distribution and potential of wind energy resources. Based on the wind speed and wind direction data, factors affecting the wind power generation efficiency are calculated, such as the influence of terrain on the wind field. The expected efficiency of the wind power generation system is calculated using the wind speed and wind direction data for evaluating the operation performance of the system under different conditions. The traditional energy power generation influence factor, the solar power generation influence factor, and the wind power generation influence factor are integrated to generate the comprehensive fluctuation influence factor in the new energy power supply stage.

[0094] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0095] Step S21: Conduct power grid transmission topology analysis on the operation data of the standard regional power grid to generate a power grid transmission topology network; conduct power transmission path analysis on the power grid transmission topology network to generate power transmission path data; calculate the transmission distance for the power transmission path data to obtain power transmission distance data;

[0096] Step S22: Compare the power transmission distance data with a preset standard power transmission distance threshold. When the power transmission distance data is greater than or equal to the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as long-distance power transmission path data; when the power transmission distance data is less than the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as short-distance power transmission path data and eliminate it;

[0097] Step S23: Conduct power flow stability performance analysis on the long-distance power transmission path data to generate power flow stability performance data; conduct power grid transmission power stroboscopic detection on the long-distance power transmission path data to obtain power grid transmission power stroboscopic data;

[0098] Step S24: Calculate the power transmission loss for the power grid transmission power stroboscopic data through the power transmission loss calculation formula to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate a fluctuation impact factor in the power transmission stage.

[0099] In the embodiments of the present invention, by obtaining the operation data of the standard regional power grid, including power grid nodes, line information, and power load data. Based on the power grid nodes and line information, a power grid transmission topology network is constructed, including determining the connection relationship of each node in the power grid and the transmission path of the power line. The power transmission path is analyzed using the power grid transmission topology network, including determining the power transmission path from the power generation station to each user or load node. According to the line length of the power transmission path or the algorithm of the economic transmission path, the transmission distance data of each power transmission path is calculated. A preset standard power transmission distance threshold is used to divide the short-distance and long-distance power transmission paths. The transmission distance data of each power transmission path is compared with the preset threshold. If the transmission distance is greater than or equal to the threshold, it is marked as long-distance power transmission path data; if the transmission distance is less than the threshold, it is marked as short-distance power transmission path data. The data marked as short-distance power transmission path data is excluded from the analysis and subsequent steps to ensure that the focus of the analysis is on the stability and efficiency issues of the long-distance power transmission path. The data marked as long-distance power transmission path data is collected for the stability performance data of the power flow, including indicators such as the stability of the power flow and load fluctuations. Using a mathematical model or simulation tool, the stability performance of the electric energy on the long-distance transmission path is analyzed, and the transmission efficiency and energy loss are evaluated. A power stroboscopic detection device is installed on the long-distance power transmission path to collect the power grid transmission power stroboscopic data. The collected stroboscopic data is analyzed to evaluate the impact degree of the stroboscopic on the power grid stability and power quality. Using an appropriate power transmission loss calculation formula, combined with the power transmission stroboscopic data, the loss situation of each power transmission path is calculated. The calculated power transmission loss data is integrated with the stability performance data of the power flow to comprehensively evaluate the efficiency and stability of the electric energy transmission. The stability performance data of the power flow and the power transmission loss data are integrated together to generate comprehensive fluctuation impact factors in the electric energy transmission stage, which reflect the energy loss and stability problems in the power transmission process and provide a basis and data support for optimizing the power transmission strategy.

[0100] Preferably, the power transmission loss calculation formula in step S24 is specifically as follows:

[0101] ;

[0102] In the formula, represents the power transmission loss, represents the cable transmission length, represents the current loss coefficient,

[0103] represents the time the average current within, represents the resistance loss coefficient, represents the time the average voltage within, Expressed as the power transmission path The resistance on Expressed as the coefficient of the instantaneous electric field change rate Expressed as the area of the power transmission region Expressed as described at The electric field strength at the point Expressed as the path The infinitesimal length of Expressed as the spatial abscissa point Expressed as the spatial ordinate point

[0104] The present invention analyzes and integrates a power transmission loss calculation formula. The current loss coefficient in the formula Represents the direct impact of current on transmission loss. As the current increases, the resistance inside the wire will cause greater loss. By controlling the current loss coefficient , the circuit design and power transmission system can be optimized, the energy loss caused by current can be reduced, and the transmission efficiency can be improved. The resistance loss coefficient in the formula Reflects the contribution of resistance to the energy loss during power transmission. The greater the resistance, the more obvious the loss. By optimizing the design of the power transmission path or selecting materials with lower impedance, the resistance loss coefficient Can be reduced, thereby reducing the transmission loss. The coefficient of the instantaneous electric field change rate in the formula Describes the impact of the change in electric field strength on transmission loss. The rapid change in electric field strength may cause additional energy loss. By understanding and controlling the change rate of electric field strength, the design of the power system can be optimized, transient loss can be reduced, and the stability and efficiency of power transmission can be improved. By integrating over the entire transmission path, the power loss can be comprehensively evaluated, providing accurate data support for system optimization. When using the conventional power transmission loss calculation formula in the art, the power transmission loss can be obtained. By applying the power transmission loss calculation formula provided by the present invention, the power transmission loss can be calculated more accurately. The combined effect of these parameters is that through the quantitative analysis of key factors such as current, voltage, resistance, and electric field strength, the sources of energy loss during power transmission can be deeply understood and evaluated, thereby guiding design and operation decisions and achieving the efficient operation of the power transmission system and the maximization of energy utilization efficiency.

[0105] Preferably, the power stroboscopic detection of the long-distance power transmission path data includes:

[0106] Divide the long-distance power transmission path data based on a preset distance threshold to generate the position information data of the division points of the long-distance power transmission path; deploy power transmission detection nodes for the position information data of the division points of the long-distance power transmission path to obtain power transmission detection nodes, where the power transmission detection nodes are equipped with power sensors and signal sensors;

[0107] Discriminate the transmitted power of the power transmission detection node through the power sensor. When the power sensor captures the current of the power transmission detection node, use the signal sensor to collect the passing current signal to obtain the transmission signal; monitor the frequency and phase of the transmission signal to obtain the transmission signal frequency and the transmission signal phase; calculate the power spectral density of the transmission signal frequency and the transmission signal phase to obtain the power frequency band power spectral density data; extract the energy peaks from the power frequency band power spectral density data to obtain the power grid transmission power stroboscopic data.

[0108] In the embodiment of the present invention, by dividing the long-distance power transmission path data according to a preset distance threshold, the position information data of the division points of the long-distance power transmission path is determined. Power transmission detection nodes are deployed at each division point position. These nodes include power sensors and signal sensors for power stroboscopic detection. The power sensor monitors the current flow of the power transmission detection node. When the power sensor captures the current signal, the signal sensor starts to collect the transmission signal. The signal sensor is used to monitor the frequency and phase of the collected transmission signal. Calculate the power spectral density of the frequency band of the transmission signal to evaluate the distribution and intensity of the signal in the frequency domain. Extract the main energy peaks from the power spectral density data. These energy peaks reflect the main frequency components of the power stroboscope. Integrate the frequency and phase information of the energy peaks to generate the power grid transmission power stroboscopic data, which describe the stroboscopic phenomenon and its characteristics existing in the power transmission process.

[0109] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0110] Step S31: Obtain the distribution system capacity data; analyze the regional population density of the standard regional power grid operation data to obtain the regional population density data; analyze the regional power consumption pattern of the standard regional power grid operation data through the regional population density data to generate the regional power consumption pattern data;

[0111] Step S32: Calculate the maximum load of the distribution system capacity data according to the regional power consumption pattern data to obtain the maximum load of the regional distribution system; analyze the load overload of the maximum load of the regional distribution system to generate the regional distribution load overload data;

[0112] Step S33: Perform time series analysis on the regional distribution load overload data to generate regional distribution load overload time series data; calculate the electricity demand based on the regional distribution load overload time series data for the regional electricity consumption pattern data, and obtain the regional distribution stage fluctuation impact factor.

[0113] In the embodiment of the present invention, by obtaining the capacity data of the distribution system from relevant power management departments or power companies, these data usually include the total capacity and distribution of each distribution area. Using the census data provided by the statistical bureau, perform population density analysis on the standard area, and these data can show the population density distribution of different areas. According to the regional population density data, combined with the standard area power grid operation data, perform regional electricity consumption pattern analysis, including understanding the electricity consumption patterns of different population density areas, such as the electricity consumption characteristics and consumption patterns of residential areas, commercial areas or industrial areas. Based on the regional electricity consumption pattern data, calculate the maximum load of the distribution system within a specific time period, which involves determining the load demand of the system during the peak load period according to historical data or model prediction. Compare the calculated maximum load of the regional distribution system with the actual capacity of the system. If the maximum load exceeds the design capacity or safe operating range of the system, load overload will occur. Perform time series analysis on the regional distribution load overload data to understand the occurrence frequency, duration and trend of load overload, which can help evaluate the severity and impact of load overload. Based on the regional distribution load overload time series data obtained from the time series analysis, calculate the actual electricity demand in different time periods, including the calculation of the peak and trough periods of electricity demand, and evaluate the stability and response ability of the distribution system according to the demand fluctuation.

[0114] Preferably, the regional electricity consumption pattern analysis of the standard area power grid operation data through the regional population density data includes:

[0115] Perform mean value normalization of the electricity consumption extreme values on the standard area power grid operation data according to the regional population density data to generate the overall regional population electricity consumption level data;

[0116] Perform daily electricity consumption behavior characteristic analysis on the standard area power grid operation data through the overall regional population electricity consumption level data to generate a daily electricity consumption load curve; extract the peak characteristic differences of the daily electricity consumption load curve to obtain the electricity consumption peak characteristic difference data;

[0117] Calculate the change curvature of the daily electricity consumption load curve to obtain the electricity consumption load change curvature data; perform regional electricity consumption pattern analysis based on the electricity consumption load change curvature data and the electricity consumption peak characteristic difference data to generate regional electricity consumption pattern data.

[0118] In the embodiments of the present invention, by correlating and integrating the regional population density data with the standard regional power grid operation data, for each region, the mean data of its overall power consumption level is calculated according to its population density, which can be achieved by statistically calculating the total power consumption of each region and dividing it by the population number of the region. According to the regional population's overall power consumption level data, the power consumption load of the standard regional power grid in different time periods is analyzed, including analyzing the power demand in different time periods of a day to form a daily power consumption load curve. Analyze the power consumption load curve of each region in different time periods, and extract the power consumption peak characteristics in different time periods, which can help determine the differences in power consumption behaviors of each region during high-load and low-load periods. Conduct mathematical and statistical analyses on the daily power consumption load curve, and calculate the change rate or curvature of the curve in different time periods. These data reflect the dynamic changes in the power consumption load. By comprehensively considering the change curvature of the power consumption load and the peak characteristic differences, analyze and classify the power demand patterns of each region, which can help understand the power consumption habits, peak and off-peak power consumption situations of different regions, so as to generate regional power consumption pattern data.

[0119] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0120] Step S41: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation impact factors in the energy generation stage, power transmission stage, and regional distribution stage, and generate a power grid fluctuation simulation data set;

[0121] Step S42: Divide the power grid fluctuation simulation data set to generate a model training set and a model test set; use the convolutional neural network algorithm to train the model training set to generate a real-time load prediction training model; perform model test iteration on the real-time load prediction training model through the model test set to generate a real-time load prediction model;

[0122] Step S43: Import the standard regional power grid operation data into the real-time load prediction model for power grid load prediction to generate power grid load prediction data.

[0123] In the embodiments of the present invention, by using the stochastic power flow calculation method, considering the volatility and uncertainty of energy supply, the power output data of different power generation facilities are generated. According to the power transmission path and power transmission distance data, stochastic power flow calculation is carried out, considering the fluctuations and losses during the power transmission process. Stochastic power flow calculation is performed on the regional distribution system, considering the fluctuations and changes that occur during the process of power supply to consumers. The stochastic power flow calculation results of the fluctuation impact factors in the energy generation stage, the power transmission stage, and the regional distribution stage are input into the Monte Carlo simulation. During the simulation process, input parameters are randomly generated through multiple iterations to simulate the grid operation conditions under different conditions. The results of each simulation are recorded, including data such as power supply quantity, load distribution, and power loss. The grid fluctuation simulation data set generated by the Monte Carlo simulation is divided into a model training set and a model test set. Ensure that the data distribution and fluctuation patterns of the training set and the test set can represent various situations of the actual grid operation. Use a convolutional neural network (CNN) or other suitable deep learning algorithms to train the model training set. CNN can effectively learn the dynamic characteristics and fluctuation patterns of the grid load from time series data. Use the model test set to test and iterate the trained real-time load prediction model. Analyze the prediction accuracy and accuracy of the model under different load conditions, and make necessary adjustments and optimizations. Input the real-time standard regional grid operation data into the trained real-time load prediction model. The model uses the input real-time data to predict the grid load. Output the prediction results, including the predicted power demand, peak load period, and power supply security assessment, etc.

[0124] In this specification, a grid load prediction system based on stochastic power flow calculation is provided for performing the above-mentioned grid load prediction method based on stochastic power flow calculation. The grid load prediction system based on stochastic power flow calculation includes:

[0125] The impact module in the power generation stage is used to obtain the regional grid operation data; perform data preprocessing on the regional grid operation data to generate standard regional grid operation data; perform multi-level new grid energy power supply stage impact analysis on the regional grid operation data to generate the fluctuation impact factor in the energy generation stage;

[0126] The transmission stage impact module is used to analyze the power transmission path of the standard regional power grid operation data to generate power transmission path data; calculate the transmission distance of the power transmission path data to obtain power transmission distance data; compare the power transmission distance data with a preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the fluctuation impact factor in the power transmission stage.

[0127] The power supply stage impact module is used to obtain the distribution system capacity data; analyze the regional power consumption pattern of the standard regional power grid operation data to generate regional power consumption pattern data; perform load overload analysis on the distribution system capacity data according to the regional power consumption pattern data to generate regional distribution load overload data; calculate the power consumption demand of the regional distribution load overload data to obtain the fluctuation impact factor in the regional distribution stage.

[0128] The power flow calculation simulation module is used to perform Monte Carlo simulation on the fluctuation impact factors in the energy generation stage, the power transmission stage, and the regional distribution stage by using stochastic power flow calculation to generate a power grid fluctuation simulation data set; perform power grid load forecasting on the power grid fluctuation simulation data set to generate power grid load forecasting data.

[0129] The beneficial effects of the present invention are as follows: By preprocessing the regional power grid operation data, the data can be cleaned and standardized to generate standard regional power grid operation data, providing an accurate data basis for subsequent analysis. Through multi-level analysis of the regional power grid operation data, the impact factors of different power grid energy supply stages can be evaluated, helping to understand the energy supply situation and related factors of the power grid. By analyzing the power transmission path and calculating the distance of the standard regional power grid operation data, the power transmission path and distance can be determined, providing basic data for subsequent power flow stability and transmission loss analysis. By analyzing the power flow stability and calculating the power stroboscopic loss of the long-distance power transmission path data, the stability and loss of power transmission can be evaluated, providing a reference for power grid operation optimization. By analyzing the power consumption pattern and performing distribution load overload analysis on the standard regional power grid operation data, the distribution load situation of the region can be evaluated, and the power consumption demand can be calculated, providing a basis for power grid load management and planning. By performing Monte Carlo simulation on the fluctuation impact factors using stochastic power flow calculation to generate a power grid fluctuation simulation data set and through power grid load forecasting, the load situation of the power grid can be predicted, providing a reference for power dispatching and energy planning. Therefore, the present invention improves the accuracy of power grid load forecasting through meticulous data integration and complex simulation.

[0130] Therefore, in view of any aspect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be embraced within the present invention.

[0131] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A power grid load forecasting method based on stochastic power flow calculation, characterized in that Including the following steps: Step S1: Obtain the operation data of the regional power grid; Perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid; Conduct a multi-level impact analysis of the new power grid energy supply stage on the operation data of the regional power grid to generate the fluctuation impact factor of the energy generation stage; Step S2: Conduct an analysis of the power transmission path on the standard operation data of the regional power grid to generate power transmission path data; Calculate the transmission distance for the power transmission path data to obtain the power transmission distance data; Compare the power transmission distance data with the preset standard power transmission distance threshold to generate long-distance power transmission path data; Conduct an analysis of the stable performance of the power flow on the long-distance power transmission path data to generate the stable performance data of the power flow; Calculate the power stroboscopic loss for the long-distance power transmission path data to obtain the power transmission loss data; Integrate the stable performance data of the power flow and the power transmission loss data to generate the fluctuation impact factor of the power transmission stage; Step S3: Obtain the distribution system capacity data; Conduct an analysis of the regional power consumption pattern on the standard operation data of the regional power grid to generate regional power consumption pattern data; Based on the regional power consumption pattern data, conduct a load overload analysis on the distribution system capacity data to generate regional distribution load overload data; Calculate the power consumption demand for the regional distribution load overload data to obtain the fluctuation impact factor of the regional distribution stage; Step S4: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation impact factor of the energy generation stage, the fluctuation impact factor of the power transmission stage, and the fluctuation impact factor of the regional distribution stage to generate a power grid fluctuation simulation data set; Conduct a power grid load prediction on the power grid fluctuation simulation data set to generate power grid load prediction data; Step S4 includes the following steps: Step S41: Use stochastic power flow calculation to perform Monte Carlo simulation on the fluctuation impact factor of the energy generation stage, the fluctuation impact factor of the power transmission stage, and the fluctuation impact factor of the regional distribution stage to generate a power grid fluctuation simulation data set; Step S42: Divide the power grid fluctuation simulation data set to generate a model training set and a model test set; Use the convolutional neural network algorithm to train the model on the model training set to generate a real-time load prediction training model; Conduct model test iteration on the real-time load prediction training model through the model test set to generate a real-time load prediction model; Step S43: Import the standard operation data of the regional power grid into the real-time load prediction model to conduct a power grid load prediction to generate power grid load prediction data.

2. The power grid load forecasting method based on probabilistic load flow calculation according to claim 1, wherein Step S1 includes the following steps: Step S11: Obtain the operation data of the regional power grid; Step S12: Perform data preprocessing on the operation data of the regional power grid to generate standard operation data of the regional power grid, where the data preprocessing includes data cleaning, filling of missing data values, and data standardization; Step S13: Conduct a division of the power grid power supply energy types on the operation data of the regional power grid to obtain the regional power grid power supply energy type division data, where the regional power grid power supply energy type division data includes traditional energy power supply data and new energy power supply data; Step S14: Conduct a multi-level impact analysis of the new energy power supply data and the traditional energy power supply data on the new power grid energy supply stage to generate the fluctuation impact factor of the energy generation stage.

3. The power grid load forecasting method based on stochastic power flow calculation according to claim 2, wherein Step S14 includes the following steps: Step S141: Confirm the traditional energy power supply equipment sites for the traditional energy power supply data to obtain the extreme climate impact analysis and generate the traditional energy power supply equipment site data; collect the meteorological sensor data through the traditional energy power supply equipment site data to obtain the traditional energy power supply equipment site meteorological data; conduct an extreme climate analysis on the traditional energy power supply equipment site meteorological data to generate the traditional energy generation impact factor; Step S142: Classify the new energy power supply data into new energy supply types to generate the new energy supply type classification data, where the new energy supply type classification data includes wind power generation data and solar power generation data; confirm the power supply equipment sites based on the wind power generation data and the solar power generation data to obtain the new energy power supply equipment site data; Step S143: Collect the meteorological sensor data through the new energy power supply equipment site data to obtain the new energy power supply equipment site meteorological data; conduct a sunlight transformation impact analysis on the new energy power supply equipment site meteorological data according to the solar power generation data to generate the sunlight transformation impact data, where the sunlight transformation impact data includes cloud cover data and sunshine duration data; calculate the solar power generation efficiency based on the cloud cover data and the sunshine duration data for the solar power generation data to obtain the solar power generation impact factor; Step S144: Extract the wind characteristics from the new energy power supply equipment site meteorological data according to the wind power generation data to obtain the wind characteristic data, where the wind characteristic data includes wind direction data and wind speed data; calculate the wind power generation efficiency based on the wind direction data and the wind speed data for the wind power generation data to obtain the wind power generation impact factor; integrate the traditional energy generation impact factor, the solar power generation impact factor, and the wind power generation impact factor to generate the fluctuation impact factor of the energy generation stage.

4. The power grid load forecasting method based on probabilistic load flow calculation according to claim 1, characterized in that Step S2 includes the following steps: Step S21: Conduct a grid transmission topology analysis on the standard regional grid operation data to generate a grid transmission topology network; conduct a power transmission path analysis on the grid transmission topology network to generate power transmission path data; calculate the transmission distance for the power transmission path data to obtain the power transmission distance data; Step S22: Compare the power transmission distance data with a preset standard power transmission distance threshold. When the power transmission distance data is greater than or equal to the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as long-distance power transmission path data; when the power transmission distance data is less than the preset standard power transmission distance threshold, mark the power transmission path data corresponding to the power transmission distance data as short-distance power transmission path data and eliminate it; Step S23: Analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; detect the power strobing of the long-distance power transmission path data to obtain the power grid transmission power strobing data; Step S24: Calculate the power transmission loss of the power grid transmission power strobing data through the power transmission loss calculation formula to obtain the power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the fluctuation influence factor in the power transmission stage.

5. The power grid load forecasting method based on stochastic power flow calculation according to claim 4, characterized in that The power transmission loss calculation formula in Step S24 is as follows: ； In the formula, represents the power transmission loss, represents the cable transmission length, represents the current loss coefficient, Expressed as the average current within a time, expressed as the resistance loss coefficient, expressed as the average voltage within a time, expressed as the resistance on the power transmission path expressed as the instantaneous electric field change rate coefficient, expressed as the area of the power transmission region, expressed as describing the electric field strength at a point, expressed as the infinitesimal length of a path, expressed as the spatial abscissa point, expressed as the spatial ordinate point.

6. The power grid load forecasting method based on stochastic power flow calculation according to claim 4, characterized in that, Detecting the power strobing of the long-distance power transmission path data includes: Based on a preset distance threshold, divide the long-distance power transmission path data to generate the position information data of the long-distance power transmission path division points; deploy power transmission detection nodes for the position information data of the long-distance power transmission path division points to obtain power transmission detection nodes, where the power transmission detection nodes are equipped with power sensors and signal sensors; Use the power sensor to discriminate the power transmission of the power transmission detection node. When the power sensor captures the current of the power transmission detection node, use the signal sensor to collect the passing current signal to obtain the power transmission signal; monitor the frequency and phase of the power transmission signal to obtain the power transmission signal frequency and the power transmission signal phase; calculate the power spectral density of the power transmission signal frequency and the power transmission signal phase to obtain the power frequency band power spectral density data; Extract the energy peaks from the power frequency band power spectral density data to obtain the power grid transmission power strobing data.

7. The power grid load forecasting method based on stochastic power flow calculation according to claim 1, characterized in that Step S3 includes the following steps: Step S31: Obtain the distribution system capacity data; analyze the regional population density of the standard regional power grid operation data to obtain the regional population density data; analyze the regional power consumption pattern of the standard regional power grid operation data through the regional population density data to generate the regional power consumption pattern data; Step S32: Calculate the maximum load of the distribution system capacity data according to the regional power consumption pattern data to obtain the maximum load of the regional distribution system; analyze the load overload of the maximum load of the regional distribution system to generate the regional distribution load overload data; Step S33: Perform time series analysis on the regional distribution load overload data to generate the regional distribution load overload time series data; calculate the power consumption demand of the regional power consumption pattern data based on the regional distribution load overload time series data to obtain the fluctuation influence factor in the regional distribution stage.

8. The power grid load forecasting method based on probabilistic load flow calculation according to claim 7, wherein Analyzing the regional power consumption pattern of the standard regional power grid operation data through the regional population density data includes: Equalize the power consumption extreme values of the standard regional power grid operation data according to the regional population density data to generate the overall regional population power consumption level data; Analyze the daily power consumption behavior characteristics of the standard regional power grid operation data through the overall regional population power consumption level data to generate the daily power consumption load curve; extract the peak feature differences of the daily power consumption load curve to obtain the power consumption peak feature difference data; Calculate the change curvature of the daily electricity load curve to obtain the electricity load change curvature data; analyze the regional electricity consumption pattern based on the electricity load change curvature data and the difference data of the electricity peak characteristics to generate the regional electricity consumption pattern data.

9. A power grid load forecasting system based on stochastic power flow calculation, characterized in that, For implementing the power grid load forecasting method based on stochastic power flow calculation as described in claim 1, the power grid load forecasting system based on stochastic power flow calculation includes: The power generation stage impact module is used to obtain the operation data of the regional power grid; perform data preprocessing on the operation data of the regional power grid to generate standard regional power grid operation data; perform multi-level new power grid energy supply stage impact analysis on the operation data of the regional power grid to generate the energy generation stage fluctuation impact factor. The transmission stage impact module is used to analyze the power transmission path of the standard regional power grid operation data to generate power transmission path data; calculate the transmission distance of the power transmission path data to obtain the power transmission distance data; compare the power transmission distance data with the preset standard power transmission distance threshold to generate long-distance power transmission path data; analyze the power flow stability performance of the long-distance power transmission path data to generate power flow stability performance data; calculate the power stroboscopic loss of the long-distance power transmission path data to obtain the power transmission loss data; integrate the power flow stability performance data and the power transmission loss data to generate the power transmission stage fluctuation impact factor. The power supply stage impact module is used to obtain the distribution system capacity data; analyze the regional electricity consumption pattern of the standard regional power grid operation data to generate regional electricity consumption pattern data; perform load overload analysis on the distribution system capacity data according to the regional electricity consumption pattern data to generate regional distribution load overload data; calculate the electricity demand of the regional distribution load overload data to obtain the regional power distribution stage fluctuation impact factor. The power flow calculation simulation module is used to perform Monte Carlo simulation on the energy generation stage fluctuation impact factor, the power transmission stage fluctuation impact factor, and the regional power distribution stage fluctuation impact factor by using stochastic power flow calculation to generate a power grid fluctuation simulation data set; perform power grid load forecasting on the power grid fluctuation simulation data set to generate power grid load forecasting data.

Images