Distributed power supply coordinated control method and system

Abstract

The present invention relates to the field of energy management and control technology, specifically to a method and system for coordinated control of distributed power sources, comprising the following steps: based on regional power consumption data, collecting and analyzing energy consumption in multiple regions, evaluating the periodic patterns and seasonal trends of energy consumption in multiple regions, and obtaining periodic energy demand patterns. In the present invention, by analyzing the periodic and seasonal changes in power consumption, and evaluating the impact of various factors such as population density and economic level on power demand, the accuracy of power demand forecasting is improved, by evaluating the impact of various environmental factors on the efficiency of renewable energy generation, the accuracy of energy output efficiency forecasting is improved, the flexibility of power network operation is enhanced, and by optimizing resource allocation and energy output parameters, the energy structure is optimized, resource waste is reduced, and energy supply chain management is optimized, the stability and continuity of distributed power system operation are ensured, and the economy and environmental protection of the power system are improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management and control technology, and in particular to a distributed power supply coordinated control method and system. Background Art

[0002] The field of energy management and control technology includes various methods and technologies for optimizing the generation, distribution and consumption of energy, aiming to improve the efficiency and reliability of energy use while reducing environmental impact. It includes smart grid technology, energy storage solutions, energy monitoring and management systems, and optimizes the flexibility of grid operations. Through real-time data monitoring and dynamic response mechanisms, it optimizes power supply and demand. In combination with energy storage technology, it balances supply and demand peaks and valleys and improves the stability of the energy system. It uses energy monitoring and management to monitor energy consumption data in real time to achieve efficient energy management and decision-making.

[0003] Among them, the coordinated control method of distributed power sources is a technology that aims to optimize the management of distributed energy resources, including solar photovoltaic, wind power, small hydropower, and biomass energy. It aims to improve the integration efficiency of distributed power sources, ensure the stable operation of the power grid, and optimize the utilization efficiency of various energy sources. Through coordinated control, effective coordination between distributed power sources can be achieved, energy waste can be reduced, the system's ability to absorb renewable energy can be enhanced, and the integration of renewable energy can be supported, thereby promoting the optimization of energy structure and the reduction of environmental load.

[0004] Traditional coordinated control methods for distributed power sources have shortcomings in dealing with high variability and multi-factor influences in power demand forecasting. In the current environment of rapid integration of renewable energy and diversified power consumption behaviors, it is difficult to accurately predict and effectively manage power demand and supply. It lacks flexibility in coordinating multiple energy types. When there are many distributed power sources, it leads to energy waste, unstable power supply and environmental pollution, which hinders the optimization and upgrading of the energy system and the realization of green development goals. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a distributed power supply coordinated control method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a distributed power supply coordinated control method, comprising the following steps:

[0007] S1: Based on regional electricity consumption data, collect and analyze energy consumption in multiple regions, evaluate the periodic patterns and seasonal trends of energy consumption in multiple regions, and obtain the periodic energy demand pattern;

[0008] S2: Based on the periodic energy demand pattern, analyze the relationship between multiple factors and regional power demand, quantify the weights of multiple influencing factors, and generate power demand forecast results;

[0009] S3: Based on the power demand forecast results, analyze the impact of various environmental factors on the power generation efficiency of renewable energy, evaluate the energy output efficiency of various renewable energy sources, build an energy output forecast model, and obtain energy efficiency evaluation results;

[0010] S4: using the energy efficiency evaluation results, analyzing the impact of various energy configurations on power network performance, adjusting the physical and logical connections of distributed resources, and generating a distributed energy layout;

[0011] S5: Based on the distributed energy layout, collect and analyze energy output data at multiple time points, calculate the output of the distributed energy network, and predict the output trend in combination with meteorological information to generate energy output prediction information;

[0012] S6: Combine the energy output prediction information with the real-time power demand data to evaluate the charging and discharging demand in the power grid, adjust the charging and discharging parameters and energy output parameters to optimize the energy supply and demand balance, and obtain energy coordination control parameters.

[0013] As a further solution of the present invention, the periodic energy demand pattern includes energy consumption, energy consumption peak and valley periods, and energy consumption trends; the electricity demand forecast results include regional electricity demand, forecast error evaluation results, and sensitivity analysis results of influencing factors; the energy efficiency evaluation results include renewable energy power generation efficiency, environmental adaptability score, and maintenance demand forecast information; the distributed energy layout includes geographical distribution information of energy access points, optimized configuration of energy types, and network connection topology; the energy output forecast information includes predicted time series output data, insufficient production capacity areas, and analysis of the impact of changes in meteorological conditions on output; the energy coordination control parameters include adjustment results of charging and discharging time windows, energy storage capacity allocation parameters, and demand response adjustment parameters.

[0014] As a further solution of the present invention, based on the regional power consumption data, the energy consumption of multiple regions is collected and analyzed, and the periodic patterns and seasonal trends of energy consumption in multiple regions are evaluated to obtain the periodic energy demand pattern. Specifically, the steps are as follows:

[0015] S101: Based on the regional power consumption data, collect and analyze the power consumption data of multiple regions, calculate the average energy consumption of multiple seasons and months in the target region, and generate regional seasonal energy consumption data;

[0016] S102: Based on the regional seasonal energy consumption data, identifying energy consumption peak and valley periods and consumption information of multiple regions, and obtaining energy consumption peak and valley periods;

[0017] S103: Based on the energy consumption peak and valley periods, combined with regional weather condition data, the impact of seasonal changes on energy consumption is analyzed to obtain a periodic energy demand pattern.

[0018] As a further solution of the present invention, based on the periodic energy demand pattern, the relationship between various factors and regional power demand is analyzed, the weights of various influencing factors are quantified, and the steps of generating power demand forecast results are specifically as follows:

[0019] S201: Based on the periodic energy demand pattern, collect and record population density, regional type, and economic activity data of multiple regions, evaluate the impact of multiple factors on electricity demand, and generate demand impact analysis data;

[0020] S202: Based on the demand impact analysis data, calculate the weights and interactions of multiple influencing factors, and analyze the contribution to power demand to obtain demand factor weight information;

[0021] S203: Based on the demand factor weight information and in combination with the energy demand pattern information, a regional power demand forecasting model is constructed to forecast the power demand of multiple regions and obtain a power demand forecasting result.

[0022] As a further solution of the present invention, based on the power demand forecast result, the influence of various environmental factors on the power generation efficiency of renewable energy is analyzed, the energy output efficiency of various renewable energy sources is evaluated, and an energy output forecast model is constructed. The steps of obtaining the energy efficiency evaluation result are specifically as follows:

[0023] S301: Based on the power demand forecast result, collect and record data of various environmental factors that affect the efficiency of renewable energy in the target area, including sunlight intensity, wind speed, and temperature, to obtain an environmental factor data set;

[0024] S302: Based on the environmental factor data set, analyzing the energy output data of solar energy, wind energy, and biomass energy in the distributed energy grid, evaluating the impact of target environmental conditions on the output efficiency of various energy sources, calculating the impact coefficient, and generating environmental impact analysis data;

[0025] S303: Based on the environmental impact analysis data, an energy output prediction model is constructed, and a gradient boosting tree algorithm is used to evaluate the output efficiency of the distributed energy grid under various environmental conditions to generate energy efficiency evaluation results.

[0026] As a further solution of the present invention, the gradient boosting tree algorithm is according to the formula:

[0027] ;

[0028] Calculate the energy output efficiency, where For the The model prediction value after iterations is For the The model prediction value after iterations is For the The learning rate of the iteration, is the index of the iteration number, A set of characteristic variables that are input to the model. The ambient humidity The influence coefficient of The duration of sunshine The influence coefficient of Air Quality Index The influence coefficient of The altitude of the area The influence coefficient of is the ambient humidity, is the sunshine duration, is the air quality index, is the altitude of the area.

[0029] As a further solution of the present invention, the steps of using the energy efficiency evaluation results to analyze the impact of various energy configurations on power network performance, adjusting the physical and logical connections of distributed resources, and generating a distributed energy layout are specifically as follows:

[0030] S401: Analyze the energy efficiency evaluation results, identify the connection efficiency and energy transmission paths between multiple energy sites, evaluate the efficiency of physical and logical connections, identify load bottleneck nodes, and generate connection path data;

[0031] S402: Based on the connection path data, perform energy configuration simulation, consider the geographical locations and connection status of multiple sites, analyze the performance of multiple power network configurations, including output stability and load fluctuation response efficiency, and obtain network performance simulation results;

[0032] S403: According to the network performance simulation result, the physical layout and logical connection of the distributed energy resources are adjusted to optimize the energy efficiency and response speed of the network to obtain the distributed energy layout.

[0033] As a further solution of the present invention, based on the distributed energy layout, the energy output data at multiple time points are collected and analyzed, the output of the distributed energy network is calculated, and the output trend is predicted in combination with meteorological information. The steps of generating energy output prediction information are specifically as follows:

[0034] S501: Based on the distributed energy layout, collect energy output data of the target area at multiple time points, record the real-time output of multiple energy sources, including wind energy and solar energy, and generate real-time energy output records;

[0035] S502: Based on the real-time energy output record and in combination with regional meteorological information, including wind speed and sunshine intensity, predict the change trend of energy output and generate an output trend prediction result;

[0036] S503: Based on the output trend prediction results, an energy output prediction model is constructed to predict the energy output of the distributed power network, evaluate the time and magnitude of energy supply fluctuations in the target area, and generate energy output prediction information.

[0037] As a further solution of the present invention, the steps of combining the energy output prediction information with the real-time power demand data, evaluating the charging and discharging demand in the power grid, adjusting the charging and discharging parameters and the energy output parameters to optimize the energy supply and demand balance, and obtaining the energy coordination control parameters are specifically as follows:

[0038] S601: Based on the energy output prediction information and in combination with real-time power demand data, the predicted energy output and actual demand are compared, the charging and discharging demand at multiple time points is evaluated, and a demand difference analysis result is generated;

[0039] S602: Based on the demand difference analysis result, adjusting the charging and discharging parameters of the energy storage device in the distributed power network to match the peak and valley periods of power demand, including charging and discharging rate and time, and generating charging and discharging adjustment parameters;

[0040] S603: Based on the charging and discharging adjustment parameters, combined with real-time power demand and predicted energy output, the energy output ratio and the operating parameters of the energy storage device are adjusted to optimize energy supply and demand and the stability of the power network, and generate energy coordination control parameters.

[0041] A distributed power supply coordinated control system, the distributed power supply coordinated control system is used to execute the above-mentioned distributed power supply coordinated control method, the system comprises:

[0042] The pattern analysis module collects power consumption data from multiple regions based on regional power consumption data, records energy usage and peak and valley times, evaluates the periodic patterns of energy consumption in multiple regions, and generates energy consumption data sets;

[0043] The demand assessment module analyzes the impact of population density, regional type and economic level on electricity demand based on the energy consumption data set, quantifies the weights of multiple influencing factors, and generates energy demand analysis results;

[0044] The efficiency evaluation module evaluates the impact of various environmental factors on the efficiency of renewable energy generation based on the energy demand analysis results, predicts the energy output efficiency under various conditions, and generates an energy output prediction model;

[0045] The network optimization module analyzes and adjusts the energy configuration in the power network based on the energy output prediction model, including energy type, geographical location and connection status, optimizes physical and logical connections, and generates power network layout information;

[0046] The coordination control module predicts the output of the energy network based on the power network layout information, combines the real-time power demand, monitors the power demand and energy supply status in real time, adjusts the charging and discharging and energy output parameters, and generates energy coordination control parameters.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by analyzing the cyclical and seasonal changes in electricity consumption and evaluating the impact of factors such as population density and economic level on electricity demand, the accuracy of electricity demand forecasting is improved; by evaluating the impact of various environmental factors on the efficiency of renewable energy power generation, the accuracy of energy output efficiency forecasting is improved, the flexibility of power network operation is enhanced, and by optimizing resource allocation and energy output parameters, the energy structure is optimized, resource waste is reduced, and energy supply chain management is optimized, the stability and continuity of distributed power system operation are ensured, and the economy and environmental protection of the power system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0059] See also Figure 1 The present invention provides a technical solution, a distributed power supply coordinated control method, comprising the following steps:

[0060] S1: Based on regional electricity consumption data, collect and analyze energy consumption in multiple regions, evaluate the periodic patterns and seasonal trends of energy consumption in multiple regions, and obtain the periodic energy demand pattern;

[0061] S2: Based on the periodic energy demand pattern, analyze the relationship between multiple factors and regional power demand, quantify the weights of multiple influencing factors, and generate power demand forecast results;

[0062] S3: Based on the power demand forecast results, analyze the impact of various environmental factors on the efficiency of renewable energy generation, evaluate the energy output efficiency of various renewable energy sources, build an energy output forecast model, and obtain energy efficiency evaluation results;

[0063] S4: Using the energy efficiency assessment results, analyze the impact of various energy configurations on the performance of the power network, adjust the physical and logical connections of distributed resources, and generate distributed energy layout;

[0064] S5: Based on the distributed energy layout, collect and analyze energy output data at multiple time points, calculate the output of the distributed energy network, and combine meteorological information to predict the output trend and generate energy output forecast information;

[0065] S6: Combine the energy output forecast information with the real-time power demand data to evaluate the charging and discharging demand in the power grid, adjust the charging and discharging parameters and energy output parameters to optimize the energy supply and demand balance, and obtain the energy coordination control parameters.

[0066] The periodic energy demand pattern includes energy consumption, energy consumption peak and valley periods, and energy consumption trends. The power demand forecast results include regional power demand, forecast error assessment results, and sensitivity analysis results of influencing factors. The energy efficiency assessment results include the power generation efficiency of renewable energy, environmental adaptability score, and maintenance demand forecast information. The distributed energy layout includes the geographical distribution information of energy access points, the optimal configuration of energy types, and the network connection topology. The energy output forecast information includes the predicted time series output data, insufficient production capacity areas, and analysis of the impact of changes in meteorological conditions on output. The energy coordination control parameters include the adjustment results of the charging and discharging time windows, energy storage capacity allocation parameters, and demand response adjustment parameters.

[0067] See also Figure 2 ,Based on the regional power consumption data, the energy consumption of multiple regions is collected and analyzed, and the periodic patterns and seasonal trends of energy consumption in multiple regions are evaluated. The specific steps to obtain the periodic energy demand pattern are as follows:

[0068] S101: Based on the regional power consumption data, the power consumption data of multiple regions are collected and analyzed, and the average energy consumption of multiple seasons and months in the target region is calculated. The specific process of generating regional seasonal energy consumption data is as follows;

[0069] In sub-step S101, based on the regional power consumption data, the power consumption data of multiple regions are collected and analyzed, and the monthly power usage details are collected through the regional smart meter system. The collected data are pre-processed, including cleaning outliers and missing data processing, and the total monthly energy consumption of each region is calculated using the cumulative statistical method. The energy consumption characteristics of each season are identified through the seasonal decomposition technology, and the monthly data are accumulated and averaged to obtain the average energy consumption of multiple seasons and months in the target area. The formula is: ,in, is the average energy consumption, is the number of months, For the Day of the month, For the Month Daily energy consumption data is used to generate regional seasonal energy consumption data.

[0070] S102: Based on the regional seasonal energy consumption data, identifying the energy consumption peak and valley periods and consumption information of multiple regions, and obtaining the energy consumption peak and valley periods is specifically as follows;

[0071] In sub-step S102, based on the regional seasonal energy consumption data, the energy consumption peak and valley time periods and consumption information of multiple regions are identified, and the seasonal energy consumption data are analyzed using the peak and valley analysis technology. By comparing the consumption in different months, the energy consumption peaks and valleys are identified. The moving average and standard deviation methods are used to select the time periods that exceed twice the average energy consumption as the peak period, and the time periods that are less than half of the average energy consumption as the valley. Regression analysis is applied to the data to determine the consumption peak and valley pattern. The formula is: ,in, is the average energy consumption, is the standard deviation of energy consumption, identifying consumption fluctuations and obtaining the peak and valley periods of energy consumption.

[0072] S103: Based on the peak and valley periods of energy consumption and combined with regional weather condition data, the impact of seasonal changes on energy consumption is analyzed to obtain a process of periodic energy demand pattern as follows;

[0073] In sub-step S103, based on the peak and valley periods of energy consumption and combined with regional weather condition data, the impact of seasonal changes on energy consumption is analyzed, the temperature and humidity data provided by the meteorological station and energy consumption records are integrated, and the impact of weather variables on energy consumption is considered using a multivariate linear regression model. Key weather parameters, including average temperature and sunshine hours, are extracted to predict energy demand. The formula is: ,in, For energy needs, is the average temperature, is the number of sunshine hours, , , is the regression coefficient, The error term is used to predict the periodic pattern of energy demand and obtain the periodic energy demand pattern.

[0074] See also Figure 3 ,Based on the periodic energy demand pattern, the relationship between multiple factors and regional power demand is analyzed, the weights of multiple influencing factors are quantified, and the steps to generate power demand forecast results are as follows:

[0075] S201: Based on the periodic energy demand pattern, the population density, regional type, and economic activity data of multiple regions are collected and recorded, and the impact of multiple factors on electricity demand is evaluated. The specific process of generating demand impact analysis data is as follows;

[0076] In sub-step S201, based on the periodic energy demand pattern, the population density, regional type, and economic activity data of multiple regions are collected and recorded. Related data, including census information and business activity information, are obtained through the Statistics Bureau and regional economic development departments. The data are standardized to eliminate dimension and scale differences. The impact intensity and correlation of various factors on energy demand are calculated using statistical analysis methods. The overall impact on electricity demand is evaluated by constructing a multivariate linear regression model. The formula is: ,in, The results of the analysis of the impact on electricity demand are as follows: is the population density, is the region type, For economic activities, , , , is the regression coefficient, The error term is used to analyze the impact of various factors on electricity demand and generate demand impact analysis data.

[0077] S202: Based on the demand impact analysis data, the weights and interactions of various influencing factors are calculated, and the contribution to the power demand is analyzed to obtain the demand factor weight information. The specific process is as follows;

[0078] In sub-step S202, based on the demand impact analysis data, the weights and interactions of various influencing factors are calculated, and the contribution to electricity demand is analyzed. The key factors are extracted using the principal component analysis method, and the weights and relationships between the factors are determined using the factor analysis method. The weights of the target factors are combined with the contribution to be ranked, and the overall impact intensity is calculated using the weighted average method. The formula is: ,in, represents the total impact weight, is the factor index, Is a factor The weight of Is a factor The contribution of demand factors is calculated to obtain the weight information of demand factors.

[0079] S203: Based on the demand factor weight information and combined with the energy demand pattern information, a regional power demand forecasting model is constructed to forecast the power demand of multiple regions. The specific process of obtaining the power demand forecasting result is as follows;

[0080] In sub-step S203, based on the demand factor weight information and combined with the energy demand pattern information, a regional power demand forecasting model is constructed. The energy demand pattern and demand factor weights are integrated, and a multivariate regression analysis model is used to predict the power demand of each region. Considering seasonal changes and cyclical fluctuations in economic activities, a time series analysis is performed. The formula is: ,in, is the electricity demand forecast result, Analyze data for demand impact, is the time variable, , , is the model coefficient, is the error term, predicts the power demand, and obtains the power demand forecast result.

[0081] See also Figure 4 Based on the power demand forecast results, the impact of various environmental factors on the efficiency of renewable energy generation is analyzed, the energy output efficiency of various renewable energy sources is evaluated, and an energy output prediction model is constructed. The specific steps to obtain the energy efficiency evaluation results are as follows:

[0082] S301: Based on the power demand forecast result, collect and record various environmental factor data that affect the efficiency of renewable energy in the target area, including sunlight intensity, wind speed, and temperature. The specific process of obtaining the environmental factor data set is as follows;

[0083] In sub-step S301, based on the power demand forecast results, data on various environmental factors that affect the efficiency of renewable energy in the target area are collected and recorded, including sunlight intensity, wind speed, and temperature. Environmental monitoring stations and satellite data are used to systematically collect key environmental parameters, normalize the data and perform time series analysis to ensure data quality and availability. A data set of multiple environmental variables is constructed, and the key environmental conditions that affect the efficiency of renewable energy are analyzed to obtain an environmental factor data set.

[0084] S302: Based on the environmental factor data set, the energy output data of solar energy, wind energy, and biomass energy in the distributed energy grid are analyzed, the impact of target environmental conditions on the output efficiency of various energy sources is evaluated, the impact coefficient is calculated, and the specific process of generating environmental impact analysis data is as follows;

[0085] In sub-step S302, based on the environmental factor data set, the energy output data of solar energy, wind energy, and biomass energy in the distributed energy grid are analyzed, the output data of each energy type is collected through the energy management system, and the multivariate analysis method is applied to evaluate the impact of the target environmental conditions on the energy output efficiency. The regression analysis model is used to calculate the impact coefficient of different environmental factors on energy efficiency. The formula is: ,in, represents the environmental impact coefficient, , , , is the regression coefficient, representing the impact weight of different environmental variables. It is used to analyze the impact of various environmental conditions on the efficiency of various types of renewable energy and generate environmental impact analysis data.

[0086] S303: Based on the environmental impact analysis data, an energy output prediction model is constructed, and a gradient boosting tree algorithm is used to evaluate the output efficiency of the distributed energy grid under various environmental conditions. The specific process of generating energy efficiency evaluation results is as follows;

[0087] In sub-step S303, an energy output prediction model is constructed based on the environmental impact analysis data, and a gradient boosting tree algorithm is used to optimize and predict energy output under different environmental conditions. Through feature importance scoring and model adjustment during the algorithm iteration process, the model parameters are optimized to match the complexity of environmental changes, and the output efficiency of the distributed energy grid under various environmental conditions is evaluated to generate energy efficiency evaluation results.

[0088] Gradient boosting tree algorithm, according to the formula:

[0089] ;

[0090] Calculate the energy output efficiency, where For the The model prediction value after the iteration is used to represent the energy efficiency prediction obtained in the current iteration. For the The model prediction value after the iteration is used to represent the energy efficiency prediction of the previous iteration. For the The learning rate of the iteration is used to adjust the step size of each model update. It is the index of the number of iterations, which is used to indicate the order of iterations performed by the model during the learning process. Each iteration aims to improve the prediction accuracy of the model. A set of characteristic variables that are input to the model, usually including a set of environmental and technical parameters for prediction, used as input to the model to predict energy output efficiency. The ambient humidity The influence coefficient is used to quantify the influence of ambient humidity on energy output efficiency. The duration of sunshine The influence coefficient is used to quantify the influence of sunshine duration on energy output efficiency. Air Quality Index The influence coefficient is used to quantify the impact of air quality on energy output efficiency. The altitude of the area The influence coefficient is used to quantify the impact of regional altitude on energy output efficiency. is the ambient humidity, which is used to indicate the humidity level in the environment. is the sunshine duration, which is used to indicate the length of sunshine time in the environment. The air quality index is used to indicate the air quality in the environment. It is the altitude of the region, used to indicate the altitude level of the region.

[0091] The specific execution process of the formula is as follows:

[0092] Obtain environmental humidity through the environmental monitoring system , sunshine duration , Air Quality Index , Regional altitude Parameters, based on historical data and current data, use the gradient boosting tree model to obtain the influence coefficient of each environmental factor , , , , substitute the parameters into the formula and calculate the Energy efficiency prediction for the iteration , used to improve the accuracy of energy output forecasts and the ability to match a variety of environmental changes.

[0093] See also Figure 5 ,Using the energy efficiency evaluation results, analyze the impact of various energy configurations on the performance of the power network, adjust the physical and logical connections of distributed resources, and generate the steps of distributed energy layout as follows:

[0094] S401: Analyze energy efficiency evaluation results, identify connection efficiency and energy transmission paths between multiple energy sites, evaluate the efficiency of physical and logical connections, identify load bottleneck nodes, and generate connection path data. The specific process is as follows;

[0095] In sub-step S401, the energy efficiency evaluation results are analyzed, the connection efficiency and energy transmission paths between multiple energy sites are identified, the efficiency of the physical and logical connections between sites is evaluated using system network analysis tools and data analysis software, the data transmission rate and energy transmission efficiency of each connection node, and the location of the load bottleneck node are recorded and evaluated, and the efficiency of each connection path in the network is calculated by building a network flow model. The formula is: ,in, is the connection path efficiency, is the path index, For the The efficiency of the path, For the total number of paths, identify energy efficiency issues in the network and generate connection path data.

[0096] S402: Based on the connection path data, energy configuration simulation is performed, the geographical locations and connection states of multiple sites are considered, and the performance of various power network configurations is analyzed, including output stability and load fluctuation response efficiency, and the specific process of obtaining network performance simulation results is as follows;

[0097] In sub-step S402, based on the connection path data, energy configuration simulation is performed, taking into account the geographical location and connection status of multiple sites, using geographic information systems and network simulation tools to analyze the performance of various power network configurations, with particular attention paid to output stability and load fluctuation response efficiency. By building a simulation model, the performance indicators under the network configuration are calculated, and the formula is: ,in, For network performance, and is the weight factor, Indicates the stability of the configuration, It represents the load response efficiency, realizes the analysis of the power network configuration, and obtains the network performance simulation results.

[0098] S403: According to the network performance simulation results, the physical layout and logical connection of the distributed energy resources are adjusted to optimize the energy efficiency and response speed of the network, and the specific process of obtaining the distributed energy layout is as follows;

[0099] In sub-step S403, according to the network performance simulation results, the physical layout and logical connection of distributed energy resources are adjusted to optimize the energy efficiency and response speed of the network. According to the simulation results, key nodes and connections in the network are identified and reconfigured to reduce energy consumption and improve efficiency. By applying the network optimization algorithm, the resource allocation and connection strategy are adjusted. The formula is: ,in, For the optimized network layout, is the node index, is the node weight, The node energy efficiency improvement is obtained by optimizing the network layout and obtaining the distributed energy layout.

[0100] See also Figure 6 ,Based on the distributed energy layout, the energy output data at multiple time points are collected and analyzed, the output of the distributed energy network is calculated, and the output trend is predicted in combination with meteorological information. The specific steps for generating energy output prediction information are as follows:

[0101] S501: Based on the distributed energy layout, energy output data of the target area at multiple time points are collected, and the real-time output of multiple energy sources, including wind energy and solar energy, is recorded. The specific process of generating real-time energy output records is as follows;

[0102] In sub-step S501, based on the distributed energy layout, energy output data of the target area at multiple time points is collected, and the real-time output of wind energy and solar energy is recorded using a remote monitoring system and a real-time data collection platform. The data collection includes hourly energy generation and cumulative daily output. The formula is: ,in, Represents real-time energy output records, is the wind energy output, For solar energy output, track the real-time performance of energy output and generate real-time energy output records.

[0103] S502: Based on the real-time energy output record, combined with regional meteorological information, including wind speed and sunshine intensity, predict the change trend of energy output, and generate the output trend prediction result. The specific process is as follows;

[0104] In sub-step S502, based on the real-time energy output records, combined with regional meteorological information, including wind speed and sunshine intensity, time series analysis and meteorological models are used to predict the changing trend of energy output. The impact of meteorological conditions on energy output is evaluated through correlation analysis and regression models. The formula is: ,in, To output trend prediction results, , , is the model coefficient, and The effects of wind speed and sunshine intensity on output are respectively expressed, providing an understanding of future energy output changes and generating output trend forecast results.

[0105] S503: Based on the output trend prediction results, an energy output prediction model is constructed to predict the energy output of the distributed power network, and the time and magnitude of energy supply fluctuations in the target area are evaluated. The specific process of generating energy output prediction information is as follows;

[0106] In sub-step S503, based on the output trend prediction results, an energy output prediction model is constructed, and the energy output of the distributed power network is predicted using machine learning technology. The historical output data, environmental factors and interactions are considered, and the prediction algorithm is optimized to evaluate the time and amplitude of energy supply fluctuations. The formula is: ,in, For energy output forecast information, , is the model coefficient, is the forecast trend obtained from the output trend forecast model, The error term is used to analyze and predict the energy supply status in multiple time periods and generate energy output forecast information.

[0107] See also Figure 7 , combined with energy output forecast information, combined with real-time power demand data, evaluate the charging and discharging demand in the power grid, adjust the charging and discharging parameters and energy output parameters to optimize the energy supply and demand balance, and obtain the energy coordination control parameters in the following steps:

[0108] S601: Based on the energy output forecast information, combined with the real-time power demand data, the forecasted energy output and the actual demand are compared, the charging and discharging demand at multiple time points is evaluated, and the process of generating the demand difference analysis result is specifically as follows;

[0109] In sub-step S601, based on the energy output forecast information, combined with the real-time power demand data, the predicted energy output and actual demand are compared, and the charging and discharging demand at multiple time points is evaluated using statistical analysis methods and demand forecasting models. By calculating the difference between the predicted output and the actual demand, the supply and demand imbalance is analyzed. The formula is: ,in, The results of demand difference analysis are: For actual demand data, To forecast energy output data, identify charging or discharging needs during critical periods and generate demand variance analysis results.

[0110] S602: Based on the demand difference analysis results, the charging and discharging parameters of the energy storage equipment in the distributed power network are adjusted to match the peak and valley periods of power demand, including the charging and discharging rate and time. The specific process of generating the charging and discharging adjustment parameters is as follows;

[0111] In sub-step S602, based on the demand difference analysis results, the charging and discharging parameters of the energy storage equipment in the distributed power network are adjusted to match the peak and valley periods of power demand. Considering the results of the demand difference analysis, the charging and discharging strategies are optimized, including the charging and discharging rate and time. By dynamically adjusting the model, a charging and discharging plan is formulated. The formula is: ,in, To adjust the parameters for charging and discharging, is the adjustment factor, To account for demand differences, ensure that energy storage equipment supplies power during peak demand periods and charges during valley periods, and generate charging and discharging adjustment parameters.

[0112] S603: Based on the charge and discharge adjustment parameters, combined with the real-time power demand and predicted energy output, the energy output ratio and the operating parameters of the energy storage equipment are adjusted to optimize the energy supply and demand and the stability of the power network, and the specific process of generating energy coordination control parameters is as follows;

[0113] In sub-step S603, based on the charge and discharge adjustment parameters, combined with the real-time power demand and predicted energy output, the energy output ratio and the operating parameters of the energy storage equipment are adjusted to optimize the energy supply and demand balance and the stability of the power network. The hybrid strategy model is applied to comprehensively consider the real-time demand and energy output data, and the energy storage strategy is adjusted in a timely manner. The formula is: ,in, is the energy coordination control parameter, is the adjustment factor, Adjust parameters for energy storage, To predict energy output, achieve efficient and stable energy management, and generate energy coordination control parameters.

[0114] See also Figure 8 , a distributed power supply coordinated control system, the distributed power supply coordinated control system is used to execute the above-mentioned distributed power supply coordinated control method, the system includes:

[0115] The pattern analysis module collects power consumption data from multiple regions based on regional power consumption data, records energy usage and peak and valley times, evaluates the periodic patterns of energy consumption in multiple regions, and generates energy consumption data sets;

[0116] The demand assessment module analyzes the impact of population density, regional type and economic level on electricity demand based on the energy consumption data set, quantifies the weights of multiple influencing factors, and generates energy demand analysis results;

[0117] The efficiency assessment module evaluates the impact of various environmental factors on the efficiency of renewable energy generation based on the results of energy demand analysis, predicts the energy output efficiency under various conditions, and generates an energy output prediction model;

[0118] The network optimization module analyzes and adjusts the energy configuration in the power network based on the energy output prediction model, including energy type, geographical location and connection status, optimizes physical and logical connections, and generates power network layout information;

[0119] The coordination control module predicts the output of the energy network based on the power network layout information, combines the real-time power demand, monitors the power demand and energy supply status in real time, adjusts the charging and discharging and energy output parameters, and generates energy coordination control parameters.

[0120] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A distributed power supply coordinated control method, characterized in that: The following steps are involved: Based on regional electricity consumption data, collect and analyze energy consumption in multiple regions, evaluate the periodic patterns and seasonal trends of energy consumption in multiple regions, and obtain periodic energy demand patterns; Based on the periodic energy demand pattern, the relationship between various factors and regional power demand is analyzed, the weights of various influencing factors are quantified, and power demand forecast results are generated; Based on the power demand forecast results, analyze the impact of various environmental factors on the efficiency of renewable energy power generation, evaluate the energy output efficiency of various renewable energy sources, build an energy output forecast model, and obtain energy efficiency evaluation results; Based on the power demand forecast results, the steps of analyzing the impact of various environmental factors on the power generation efficiency of renewable energy, evaluating the energy output efficiency of various renewable energy sources, and constructing an energy output forecast model to obtain the energy efficiency evaluation results are as follows: Based on the power demand forecast result, collecting and recording data of various environmental factors affecting the efficiency of renewable energy in the target area, including sunlight intensity, wind speed, and temperature, to obtain an environmental factor data set; Based on the environmental factor data set, the energy output data of solar energy, wind energy, and biomass energy in the distributed energy grid are analyzed, the impact of target environmental conditions on the output efficiency of various energy sources is evaluated, the impact coefficient is calculated, and environmental impact analysis data is generated; Based on the environmental impact analysis data, an energy output prediction model is constructed, and a gradient boosting tree algorithm is used to evaluate the output efficiency of the distributed energy grid under various environmental conditions to generate energy efficiency evaluation results; The gradient boosting tree algorithm is based on the formula: ； Calculate the energy output efficiency, where For the The model prediction value after iterations is For the The model prediction value after iterations is For the The learning rate of the iteration, is the index of the iteration number, A set of characteristic variables that are input to the model. The ambient humidity The influence coefficient of The duration of sunshine The influence coefficient of Air Quality Index The influence coefficient of The altitude of the area The influence coefficient of is the ambient humidity, is the sunshine duration, is the air quality index, is the altitude of the region; Using the energy efficiency evaluation results, analyzing the impact of various energy configurations on power network performance, adjusting the physical and logical connections of distributed resources, and generating a distributed energy layout; Based on the distributed energy layout, energy output data at multiple time points are collected and analyzed, the output of the distributed energy network is calculated, and the output trend is predicted in combination with meteorological information to generate energy output prediction information; Combined with the energy output prediction information and real-time power demand data, the charging and discharging demand in the power grid is evaluated, and the charging and discharging parameters and energy output parameters are adjusted to optimize the energy supply and demand balance, thereby obtaining energy coordination control parameters.

2. The coordinated control method for distributed power sources according to claim 1, characterized in that: The periodic energy demand pattern includes energy consumption, energy consumption peak and valley periods, and energy consumption trends. The power demand forecast results include regional power demand, forecast error assessment results, and sensitivity analysis results of influencing factors. The energy efficiency assessment results include the power generation efficiency of renewable energy, environmental adaptability score, and maintenance demand forecast information. The distributed energy layout includes the geographical distribution information of energy access points, the optimized configuration of energy types, and the network connection topology. The energy output forecast information includes predicted time series output data, insufficient production capacity areas, and analysis of the impact of changes in meteorological conditions on output. The energy coordination control parameters include the adjustment results of the charging and discharging time windows, energy storage capacity allocation parameters, and demand response adjustment parameters.

3. The coordinated control method for distributed power sources according to claim 1, characterized in that: Based on the regional power consumption data, the energy consumption of multiple regions is collected and analyzed, and the periodic patterns and seasonal trends of energy consumption in multiple regions are evaluated to obtain the periodic energy demand pattern. The specific steps are as follows: Based on regional power consumption data, collect and analyze power consumption data of multiple regions, calculate the average energy consumption of multiple seasons and months in the target region, and generate regional seasonal energy consumption data; Based on the regional seasonal energy consumption data, identifying energy consumption peak and valley periods and consumption information of multiple regions, and obtaining energy consumption peak and valley periods; Based on the energy consumption peak and valley periods, combined with regional weather condition data, the impact of seasonal changes on energy consumption is analyzed to obtain a periodic energy demand pattern.

4. The distributed power supply coordinated control method according to claim 1, characterized in that: Based on the periodic energy demand pattern, the relationship between various factors and regional power demand is analyzed, the weights of various influencing factors are quantified, and the steps of generating power demand forecast results are specifically as follows: Based on the periodic energy demand pattern, collect and record population density, regional type, and economic activity data of multiple regions, evaluate the impact of multiple factors on electricity demand, and generate demand impact analysis data; Based on the demand impact analysis data, weights and interactions of multiple influencing factors are calculated, and contributions to power demand are analyzed to obtain demand factor weight information; Based on the demand factor weight information and combined with the energy demand pattern information, a regional power demand forecasting model is constructed to forecast the power demand of multiple regions and obtain power demand forecasting results.

5. The coordinated control method for distributed power sources according to claim 1, characterized in that: The steps of using the energy efficiency evaluation results to analyze the impact of various energy configurations on the performance of the power network, adjusting the physical and logical connections of distributed resources, and generating a distributed energy layout are as follows: Analyze the energy efficiency evaluation results, identify the connection efficiency and energy transmission paths between multiple energy sites, evaluate the efficiency of physical and logical connections, identify load bottleneck nodes, and generate connection path data; Based on the connection path data, energy configuration simulation is performed, the geographical locations and connection status of multiple sites are considered, the performance of various power network configurations is analyzed, including output stability and load fluctuation response efficiency, and network performance simulation results are obtained; According to the network performance simulation results, the physical layout and logical connection of distributed energy resources are adjusted to optimize the energy efficiency and response speed of the network to obtain a distributed energy layout.

6. The coordinated control method for distributed power sources according to claim 1, characterized in that: Based on the distributed energy layout, the energy output data at multiple time points are collected and analyzed, the output of the distributed energy network is calculated, and the output trend is predicted in combination with meteorological information. The steps of generating energy output prediction information are specifically as follows: Based on the distributed energy layout, energy output data of the target area at multiple time points is collected, and the real-time output of multiple energy sources, including wind energy and solar energy, is recorded to generate real-time energy output records; Based on the real-time energy output record, combined with regional meteorological information, including wind speed and sunshine intensity, predict the change trend of energy output and generate output trend prediction results; Based on the output trend prediction results, an energy output prediction model is constructed to predict the energy output of the distributed power network, evaluate the time and magnitude of energy supply fluctuations in the target area, and generate energy output prediction information.

7. The coordinated control method for distributed power sources according to claim 1, characterized in that: Combined with the energy output forecast information and real-time power demand data, the charging and discharging demand in the power grid is evaluated, and the charging and discharging parameters and energy output parameters are adjusted to optimize the energy supply and demand balance, and the steps of obtaining energy coordination control parameters are specifically as follows: Based on the energy output forecast information, combined with real-time power demand data, the forecasted energy output and actual demand are compared, the charging and discharging demand at multiple time points is evaluated, and a demand difference analysis result is generated; Based on the demand difference analysis results, adjusting the charging and discharging parameters of the energy storage equipment in the distributed power network to match the peak and valley periods of power demand, including charging and discharging rates and times, and generating charging and discharging adjustment parameters; Based on the charging and discharging adjustment parameters, combined with real-time power demand and predicted energy output, the energy output ratio and the operating parameters of the energy storage equipment are adjusted to optimize energy supply and demand and the stability of the power network, and generate energy coordination control parameters.

8. Distributed power supply coordinated control system, characterized in that: Used to implement the distributed power supply coordinated control method according to any one of claims 1 to 7, the system comprises: The pattern analysis module collects power consumption data of multiple regions based on regional power consumption data, records energy usage and peak and valley times, evaluates the periodic patterns of energy consumption in multiple regions, and generates energy consumption data sets; A demand assessment module, based on the energy consumption data set, analyzes the impact of population density, regional type and economic level on electricity demand, quantifies the weights of multiple influencing factors, and generates energy demand analysis results; An efficiency evaluation module, based on the energy demand analysis results, evaluates the impact of various environmental factors on the efficiency of renewable energy generation, predicts the energy output efficiency under various conditions, and generates an energy output prediction model; A network optimization module, based on the energy output prediction model, analyzes and adjusts the energy configuration in the power network, including energy type, geographical location and connection status, optimizes physical and logical connections, and generates power network layout information; The coordination control module predicts the output of the energy network based on the power network layout information, combines the real-time power demand, monitors the power demand and energy supply status in real time, adjusts the charging and discharging and energy output parameters, and generates energy coordination control parameters.

Images