Distributed photovoltaic aggregation optimization control method and system based on hydropower integration

Abstract

The present invention discloses a distributed photovoltaic aggregation optimization control method and system based on hydropower integration, which is used in the field of energy optimization control. The distributed photovoltaic aggregation optimization control method includes the following steps: collecting power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas; constructing a hydropower integration model that simulates the interaction between power and water resources in low-voltage areas; creating a multi-objective optimization model, and building an intelligent electricity-water collaborative control strategy suitable for real-time regulation; integrating the hydropower integration model and the intelligent electricity-water collaborative control strategy into the existing power management system and water resource management system; and regularly evaluating economic benefits and environmental impacts. The present invention realizes the organic integration of the power management system and the water resource management system by integrating the hydropower integration model and the intelligent electricity-water collaborative control strategy, breaking the information barriers between the original systems and improving the overall coordination and integration.

Description

Technical Field

[0001] The present invention relates to the field of energy optimization control, and in particular, to a distributed photovoltaic aggregation optimization control method and system based on hydropower integration. Background Art

[0002] With the high proportion of distributed photovoltaic power sources connected to rural low-voltage stations, the unstable output and randomness of photovoltaic systems have increased the complexity of the power grid, causing serious impacts on the power quality and power supply security of the power grid; traditional power grid management strategies and equipment are no longer sufficient to cope with this new challenge, especially in the context of growing demand for electricity and water resources; in addition, the particularities of rural areas, such as limitations on power and communication infrastructure, and specific electricity demands such as agricultural irrigation, have also put forward higher requirements for power grid management.

[0003] Therefore, researching and developing technologies and methods that can adapt to this new situation has become the key to improving power quality and ensuring the safe operation of the power grid.

[0004] Traditional power and water resource management systems often lack accurate data support, resulting in inefficient resource allocation and an inability to flexibly respond to changing environments or demands. Existing power and water resource management systems are usually designed only for specific environments or conditions and lack adaptability. When the environment or demands change, system efficiency decreases. Traditional models often cannot take into account both long-term planning and short-term operational needs, resulting in incomplete decision support functions and affecting the implementation of the overall strategy. Old power and water resource management systems often operate independently, lack effective coordination mechanisms, and have serious information island phenomena, which hinder the efficiency and effectiveness of resource management.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to overcome the above problems, the present invention aims to propose a distributed photovoltaic aggregation optimization control method and system based on hydropower integration, with the aim of solving the problem that existing power and water resource management systems are usually only designed for specific environments or conditions and lack adaptability. When the environment or demand changes, the system efficiency decreases. Traditional models often cannot take into account the needs of long-term planning and short-term operations at the same time, resulting in incomplete decision support functions and affecting the implementation effect of the overall strategy.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] According to one aspect of the present invention, a distributed photovoltaic aggregation optimization control method based on hydropower integration is provided, and the distributed photovoltaic aggregation optimization control method comprises the following steps:

[0009] S1. Collect the power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas;

[0010] S2. Based on the power consumption data and water resource consumption data of distributed photovoltaic systems, a hydropower integration model simulating the interaction between power and water resources in low-voltage areas is constructed to simulate the complementary behavior of power and water in rural low-voltage areas under various scenarios;

[0011] S3. Create a multi-objective optimization model, and build an intelligent electricity-water coordinated control strategy suitable for real-time regulation by minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources;

[0012] S4. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results.

[0013] Optionally, a hydropower integration model simulating the interaction between power and water resources in low-voltage areas is constructed based on the power consumption data and water resource consumption data of the distributed photovoltaic system to simulate the complementary behavior of power and water resources in rural low-voltage areas under various scenarios, including the following steps:

[0014] S21. Preprocessing the power consumption data and water resource consumption data of the distributed photovoltaic system in the rural low-voltage area;

[0015] S22. Perform exploratory data analysis to identify the characteristics and patterns of pre-processed electricity consumption data and water consumption data through descriptive statistics, correlation analysis and visualization, and define the framework of the water-power integration model;

[0016] S23. Use time series analysis techniques, combined with identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption, and capture seasonal and trend changes;

[0017] S24. Estimate the parameters of the hydropower integration model from actual data using the maximum likelihood estimation method;

[0018] S25. Verify and test the hydropower integration model using historical data, and adjust the parameters of the hydropower integration model according to the test results;

[0019] S26. Based on the hydropower integration model, simulate the electricity-water complementary behavior in rural low-voltage substations under various scenarios.

[0020] Optionally, perform exploratory data analysis to identify the characteristics and patterns of the pre-processed electricity consumption data and water consumption data through descriptive statistics, correlation analysis and visualization, and define the framework of the water-power integration model including the following steps:

[0021] S221. Arrange the pre-processed power consumption data and water resource consumption data, and calculate the mean, median and standard deviation of the power consumption data and water resource consumption data to obtain the distribution of the data;

[0022] S222. Based on the distribution of data, the Spearman method is used to analyze the correlation between electricity consumption data and water resource consumption data, and to identify the potential interaction pattern between electricity consumption data and water resource consumption data;

[0023] S223. Use scatter plots to display the changing trends and distribution characteristics of electricity consumption data and water resource consumption data;

[0024] S224. Integrate the descriptive statistics in step S221, the correlation analysis in step S222, and the visualization results in step S223 to identify the key characteristics and potential patterns of electricity consumption and water resource consumption data, and define the inputs, outputs, and key variables of the hydropower integration model.

[0025] Optionally, based on the distribution of the data, the Spearman method is used to analyze the correlation between the power consumption data and the water resource consumption data, and identifying the potential interaction pattern between the power consumption data and the water resource consumption data includes the following steps:

[0026] S2221. Obtain distribution of data points including power consumption data and water resource consumption data;

[0027] S2222, sorting the electricity consumption data and the water resource consumption data, and assigning ranks to the sorted data points according to the relative positions of the data points;

[0028] S2223. Calculate the rank correlation coefficient between the electricity consumption data and the water resource consumption data using the calculation formula of the Spearman rank correlation coefficient;

[0029] S2224, analyzing the calculation result of the Spearman rank correlation coefficient, if the absolute value of the rank correlation coefficient is close to 1, it means that the rank correlation between the power consumption data and the water resource consumption data is strong; if the absolute value of the rank correlation coefficient is close to 0, it means that the rank correlation between the power consumption data and the water resource consumption data is weak;

[0030] S2225. Based on the analysis results of Spearman's rank correlation coefficient, identify the potential interaction patterns between electricity consumption data and water resource consumption data.

[0031] Optionally, the expression for calculating the rank correlation coefficient between the electricity consumption data and the water resource consumption data is:

[0032]

[0033] r s represents the Spearman rank correlation coefficient between electricity consumption data and water consumption data;

[0034] n represents the number of data points in the electricity consumption data and water consumption data;

[0035] d represents the difference between the electricity consumption level and the water consumption level of each data point;

[0036] 6 represents the same as ∑d 2 The multiplication factor is used to adjust the influence of the sum of squared rank differences when calculating the correlation coefficient.

[0037] Optionally, using time series analysis techniques, combined with the identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption and capture seasonal and trend changes includes the following steps:

[0038] S231. Select a time series model for seasonal decomposition based on the key features and underlying patterns of electricity consumption data and water consumption data identified;

[0039] S232, identifying parameters of the time series model using the autocorrelation function and the partial autocorrelation function;

[0040] S233, checking whether the residual of the time series model presents a white noise distribution; if the residual is not white noise, indicating that the time series model does not fully capture all the information in the power consumption data and the water resource consumption data, then repeating steps S232 and S233 until the residual presents a white noise distribution; if the residual is white noise, executing step S234;

[0041] S234, comparing the prediction results of the model with the actual data, calculating and evaluating the prediction error and accuracy, so as to verify the prediction performance of the model;

[0042] S235. If the model prediction performance meets the preset requirements, the results of the time series model are integrated into the hydropower integration model to simulate and predict the electricity-water complementary behavior in rural low-voltage substations; if it does not meet the requirements, return to step S231 to reselect or adjust the model.

[0043] Optionally, according to the hydropower integration model, simulating the electricity-water complementary behavior of the rural low-voltage area under various scenarios includes the following steps:

[0044] S261. Define different scenarios including different seasons, different weather conditions and different electricity demand levels;

[0045] S262, obtaining power consumption data, water resource consumption data and photovoltaic power generation data corresponding to different seasons, different weather conditions and different power demand levels;

[0046] S263, inputting the acquired power consumption data, water resource consumption data and photovoltaic power generation data into the hydropower integration model, and running the hydropower integration model to simulate the electricity-water complementary behavior under various scenarios;

[0047] S264. Analyze the simulation results, evaluate the complementary effects of electricity consumption and water resource consumption and the contribution of photovoltaic power generation to electricity supply under various scenarios; and perform sensitivity analysis to explore the impact of photovoltaic power generation, electricity demand, and water resource availability on electricity-water complementary behavior.

[0048] Optionally, a multi-objective optimization model is created, and an intelligent electricity-water coordinated control strategy suitable for real-time regulation is constructed to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources, including the following steps:

[0049] S31. Set minimizing electricity costs and maximizing the efficiency of joint utilization of electricity and water resources as optimization goals, and define quantitative indicators and constraints of the optimization goals;

[0050] S32. Identify and determine the various variables that affect electricity costs and resource utilization efficiency;

[0051] S33. Treat the optimization goal as a game participant and use Nash game theory to assign each variable to the most relevant goal;

[0052] S34, setting the operating parameters of the genetic algorithm, and optimizing the current Pareto efficiency frontier solution using the Nash game equilibrium method after each generation of the genetic algorithm;

[0053] S35. Create a multi-objective optimization model and conduct simulation tests on the multi-objective optimization model to evaluate the performance under different operating conditions, analyze the preliminary optimization results, and identify the Pareto efficiency optimal solution in the solution set;

[0054] S36. Based on the test results of the multi-objective optimization model, an intelligent electricity-water coordinated control strategy suitable for real-time regulation is established to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources.

[0055] Optionally, the hydropower integration model and the intelligent power-water coordinated control strategy are integrated into the existing power management system and water resources management system; the economic benefits and environmental impacts are regularly evaluated, and the control strategy is adjusted and optimized based on the evaluation results, including the following steps:

[0056] S41. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system;

[0057] S42. After the integration is completed, the integrated existing power management system and water resources management system shall be subjected to functional testing, performance testing and stability testing;

[0058] S43, setting an evaluation time interval, and at the end of each evaluation period, collecting operation data of the power management system and the water resources management system, including power cost, power and water resources utilization efficiency, and environmental impact;

[0059] S44. Analyze the collected data and evaluate the economic benefits and environmental impact of the intelligent power-water coordinated control strategy;

[0060] S45. Based on the evaluation results, identify the problems and deficiencies in the intelligent power-water coordinated control strategy, make necessary adjustments and optimizations to the strategy, and reintegrate the adjusted strategy into the power and water resources management system for testing and verification.

[0061] According to another aspect of the present invention, a distributed photovoltaic aggregation optimization control system based on water-power integration is also provided, and the distributed photovoltaic aggregation optimization control system includes: a data acquisition module, a water-power integration model building module, an intelligent electricity-water coordinated control strategy creation module and a system integration and optimization module;

[0062] Data collection module, used to collect power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas;

[0063] The hydropower integration model building module is used to build a hydropower integration model that simulates the interaction between electricity and water resources in low-voltage areas based on the electricity consumption data and water resource consumption data of distributed photovoltaic systems, and is used to simulate the electricity-water complementary behavior of rural low-voltage areas under various scenarios;

[0064] Intelligent power-water coordinated control strategy creation module, which is used to create a multi-objective optimization model and build an intelligent power-water coordinated control strategy suitable for real-time regulation by minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources;

[0065] The system integration and optimization module is used to integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results.

[0066] Compared with the prior art, this application has the following beneficial effects:

[0067] 1. Based on actual data, the present invention provides accurate prediction and analysis tools, which helps to understand the interactive relationship between electricity and water resources, better allocate resources, and optimize the efficiency of energy and water resources. Multi-scenario simulation can take into account different seasons, weather conditions and electricity demand levels, and is widely applicable to various actual scenarios, so that the model can predict and respond to various situations that may arise in the future. Through time series analysis and parameter estimation, the model can capture seasonal and trend changes in the data, provide support for long-term planning and short-term adjustments, and the simulation of electricity-water complementary behavior can optimize the utilization of photovoltaic power generation and water resources and improve the overall sustainability of the system.

[0068] 2. The present invention identifies and takes into account various variables that affect electricity costs and resource utilization efficiency, such as electricity consumption, water resource consumption, etc., and defines corresponding constraints to ensure that the optimization process is carried out within a practical and feasible range. The Nash game theory is used to regard the optimization target as a game participant, and each variable is assigned to the most relevant target, so as to better handle the trade-off relationship between multiple targets and find a better solution. The operating parameters of the genetic algorithm are set, and the Nash game equilibrium method is used to optimize the current Pareto efficiency frontier solution after each generation. The method combining the genetic algorithm and the Nash game theory can more effectively search for the global optimal solution. A comprehensive simulation test of the multi-objective optimization model is carried out, the performance under different operating conditions is evaluated, and the preliminary optimization results are analyzed to identify the Pareto efficiency optimal solution in the solution set. Based on the test results of the multi-objective optimization model, an intelligent electricity-water coordinated control strategy suitable for real-time regulation is constructed. The strategy can dynamically adjust the use of electricity and water resources according to the actual operating conditions to achieve the optimization goal.

[0069] 3. The present invention realizes the organic integration of the power management system and the water resources management system by integrating the hydropower integration model and the intelligent power-water coordinated control strategy, breaks the information barriers between the original systems, and improves the overall coordination and integration. By regularly evaluating the economic benefits, it can timely discover and adjust the problems and deficiencies in the optimization control strategy, thereby further improving the utilization efficiency of electricity and water resources, reducing electricity costs, and bringing significant economic benefits to the region. Regularly evaluating the environmental impact enables managers to clearly understand the impact of the current strategy on the environment, and adjust and optimize the strategy based on the evaluation results to achieve a dual improvement in economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown:

[0071] Figure 1is a flow chart of a distributed photovoltaic aggregation optimization control method based on hydropower integration according to an embodiment of the present invention;

[0072] Figure 2 It is a principle block diagram of a distributed photovoltaic aggregation optimization control system based on hydropower integration according to an embodiment of the present invention.

[0073] In the figure:

[0074] 1. Data acquisition module; 2. Hydropower integration model building module; 3. Intelligent power-water coordinated control strategy creation module; 4. System integration and optimization module. DETAILED DESCRIPTION

[0075] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0076] According to an embodiment of the present invention, a distributed photovoltaic aggregation optimization control method and system based on hydropower integration are provided.

[0077] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a distributed photovoltaic aggregation optimization control method based on hydropower integration is provided, and the distributed photovoltaic aggregation optimization control method comprises the following steps:

[0078] S1. Collect electricity consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas.

[0079] What needs to be explained is that the goal of data collection should be clarified, that is, to understand the electricity consumption and water consumption of distributed photovoltaic systems in rural low-voltage areas; at the same time, the scope of data collection should be determined, including which areas, which time periods, etc., and appropriate data collection methods should be selected according to the goal and scope of data collection; for electricity consumption data, it should be obtained through smart meters or remote monitoring systems; for water consumption data, it is necessary to conduct on-site measurements or access relevant records, investigate existing data collection tools and resources, such as smart meters, remote monitoring systems, etc., and evaluate their accuracy and reliability.

[0080] Establish contact with substation managers or residents, explain the purpose and importance of data collection, and request their assistance; use the selected data collection tools and methods to collect data as planned. Communication is very important during the data collection process. Good communication with substation managers or residents can ensure that they understand the purpose of data collection and are willing to provide accurate and complete data. The collected data will be sorted and analyzed to extract useful information. This involves steps such as data cleaning, conversion, and visualization.

[0081] S2. Based on the electricity consumption data and water resource consumption data of distributed photovoltaic systems, a hydropower integration model simulating the interaction between electricity and water resources in low-voltage areas is constructed to simulate the electricity-water complementary behavior of rural low-voltage areas under various scenarios.

[0082] Preferably, a hydropower integration model simulating the interaction between power and water resources in low-voltage areas is constructed based on the power consumption data and water resource consumption data of the distributed photovoltaic system to simulate the complementary behavior of power and water in rural low-voltage areas under various scenarios, including the following steps:

[0083] S21. Preprocess the power consumption data and water resource consumption data of the distributed photovoltaic system in the rural low-voltage area.

[0084] It should be explained that data cleaning is the first step of preprocessing, which aims to identify and correct errors, anomalies or inconsistencies in the data; for electricity consumption data and water consumption data, it includes removing duplicate records, correcting incorrect values ​​or units, processing missing values, etc. Data conversion involves converting data from its original format to a format suitable for analysis and modeling; including data type conversion (such as converting text to numbers), data standardization or normalization, processing of time series data, etc. Data integration involves merging data from different sources or formats into a unified dataset; in the context of distributed photovoltaic systems in rural low-voltage areas, it includes integrating electricity consumption data and water consumption data with other relevant data (such as weather data, equipment operating status, etc.).

[0085] S22. Perform exploratory data analysis to identify the characteristics and patterns of the pre-processed electricity consumption data and water resource consumption data through descriptive statistics, correlation analysis and visualization, and define the framework of the water-power integration model.

[0086] Preferably, performing exploratory data analysis to identify the characteristics and patterns of the pre-processed electricity consumption data and water resource consumption data through descriptive statistics, correlation analysis and visualization, and defining the framework of the water-power integration model includes the following steps:

[0087] S221. Arrange the preprocessed electricity consumption data and water resource consumption data, and calculate the mean, median and standard deviation of the electricity consumption data and water resource consumption data to obtain the distribution of the data.

[0088] S222. Based on the distribution of data, the Spearman method is used to analyze the correlation between electricity consumption data and water resource consumption data, and to identify the potential interaction patterns between electricity consumption data and water resource consumption data.

[0089] S223. Use scatter plots to display the changing trends and distribution characteristics of electricity consumption data and water resource consumption data.

[0090] Preferably, based on the distribution of the data, the Spearman method is used to analyze the correlation between the power consumption data and the water resource consumption data, and identifying the potential interaction pattern between the power consumption data and the water resource consumption data includes the following steps:

[0091] S2221. Obtain distribution of data points including power consumption data and water resource consumption data;

[0092] S2222, sorting the electricity consumption data and the water resource consumption data, and assigning ranks to the sorted data points according to the relative positions of the data points;

[0093] S2223. Calculate the rank correlation coefficient between the electricity consumption data and the water resource consumption data using the calculation formula of the Spearman rank correlation coefficient;

[0094] S2224, analyzing the calculation result of the Spearman rank correlation coefficient, if the absolute value of the rank correlation coefficient is close to 1, it means that the rank correlation between the power consumption data and the water resource consumption data is strong; if the absolute value of the rank correlation coefficient is close to 0, it means that the rank correlation between the power consumption data and the water resource consumption data is weak;

[0095] S2225. Based on the analysis results of Spearman's rank correlation coefficient, identify the potential interaction patterns between electricity consumption data and water resource consumption data.

[0096] Preferably, the expression for calculating the rank correlation coefficient between the power consumption data and the water resource consumption data is:

[0097]

[0098] r s represents the Spearman rank correlation coefficient between electricity consumption data and water consumption data;

[0099] n represents the number of data points in the electricity consumption data and water consumption data;

[0100] d represents the difference between the electricity consumption level and the water consumption level of each data point;

[0101] 6 represents the same as ∑d 2 The multiplication factor is used to adjust the influence of the sum of squared rank differences when calculating the correlation coefficient.

[0102] It should be explained that the pre-processed electricity consumption data and water resource consumption data are sorted, and their means, medians and standard deviations are calculated to obtain the distribution of the data. The mean, median and standard deviation are the basic quantities of descriptive statistics, which provide measures of the center position, middle value and degree of dispersion of the data respectively.

[0103] Spearman's rank correlation coefficient is a nonparametric statistical method used to evaluate the rank correlation between two variables; it does not consider the specific numerical value of the data, but only focuses on the rank or order of the data.

[0104] It is necessary to obtain the distribution of data points including electricity consumption data and water resource consumption data, and use scatter plots or data visualization tools to intuitively display the distribution of data points. Scatter plots are commonly used data visualization tools that can show the relationship and distribution between two variables.

[0105] The power consumption data and the water resource consumption data are sorted, and ranks are assigned to the sorted data points according to the relative positions of the data points. The data are sorted using a sorting function in a data processing software or programming language, and ranks are assigned to the data points according to the sorted order (for example, the smallest data point is assigned rank 1, the second smallest is assigned rank 2, and so on). The rank assignment is based on the relative positions of the data points, which reflects the relative size of the data points in the entire data set. The rank correlation coefficient between the power consumption data and the water resource consumption data is calculated using the calculation formula of the Spearman rank correlation coefficient. The calculation results of the Spearman rank correlation coefficient are analyzed to determine the strength of the rank correlation between the power consumption data and the water resource consumption data. The absolute value of the rank correlation coefficient is compared to 1 and 0. The absolute value of the rank correlation coefficient close to 1 indicates a strong correlation, and close to 0 indicates a weak correlation. This is an important basis for determining the strength of the rank correlation between the two variables.

[0106] S224. Integrate the descriptive statistics in step S221, the correlation analysis in step S222, and the visualization results in step S223 to identify the key characteristics and potential patterns of electricity consumption and water resource consumption data, and define the inputs, outputs, and key variables of the hydropower integration model.

[0107] The pre-processed electricity consumption data and water resource consumption data were collated, including checking the completeness, accuracy and consistency of the data; then, the mean, median and standard deviation of these data were calculated.

[0108] Mean: The mean value of electricity consumption data is 100 kWh, and the mean value of water consumption data is 50 cubic meters;

[0109] Median: The median of electricity consumption data is 95 kWh, and the median of water consumption data is 48 cubic meters;

[0110] Standard deviation: The standard deviation of electricity consumption data is 15 kWh, and the standard deviation of water consumption data is 10 cubic meters;

[0111] Descriptive statistics obtain the central position, median and dispersion of the data; for example, the mean and median of the power consumption data are relatively high, and the standard deviation is also large, indicating that the power consumption data is generally high and has a certain degree of dispersion;

[0112] The Spearman method was used to analyze the correlation between electricity consumption data and water consumption data.

[0113] The distribution of data points containing these two variables is obtained; then the two variables are sorted, and the sorted data points are assigned ranks according to their relative positions; for example, the data point with the highest electricity consumption is assigned rank 1, the data point with the second highest is assigned rank 2, and so on; then, the rank correlation coefficient between the two variables is calculated using the Spearman rank correlation coefficient calculation formula, and the calculation result is 0.75, indicating that there is a strong rank correlation between the electricity consumption data and the water resource consumption data; finally, a scatter plot is used to display the changing trend and distribution characteristics of the electricity consumption data and the water resource consumption data; the scatter plot shows that with the increase in electricity consumption, water resource consumption also shows an increasing trend, which further verifies the correlation analysis results.

[0114] S23. Use time series analysis techniques, combined with identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption, and capture seasonal and trend changes.

[0115] Preferably, using time series analysis techniques, combined with the identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption, and to capture seasonal and trend changes, includes the following steps:

[0116] S231. Select a time series model for seasonal decomposition based on the key features and underlying patterns of electricity consumption data and water consumption data identified;

[0117] S232, identifying parameters of the time series model using the autocorrelation function and the partial autocorrelation function;

[0118] S233, checking whether the residual of the time series model presents a white noise distribution; if the residual is not white noise, indicating that the time series model does not fully capture all the information in the power consumption data and the water resource consumption data, then repeating steps S232 and S233 until the residual presents a white noise distribution; if the residual is white noise, executing step S234;

[0119] S234, comparing the prediction results of the model with the actual data, calculating and evaluating the prediction error and accuracy, so as to verify the prediction performance of the model;

[0120] S235. If the model prediction performance meets the preset requirements, the results of the time series model are integrated into the hydropower integration model to simulate and predict the electricity-water complementary behavior in rural low-voltage substations; if it does not meet the requirements, return to step S231 to reselect or adjust the model.

[0121] It should be explained that the seasonal, trend and random components of electricity consumption and water consumption data are analyzed. According to the characteristics of the data, the time series model of seasonal decomposition can capture the seasonal changes, long-term trends and random fluctuations in the data, so as to more accurately describe and predict the time series data;

[0122] Use the autocorrelation function (ACF) and partial autocorrelation function (PACF) to identify the parameters of the selected time series model, calculate the ACF and PACF of electricity consumption data and water consumption data, analyze the graphs of ACF and PACF, and determine the autoregressive order (p), moving average order (q) and seasonal parameters of the model. ACF and PACF are commonly used tools in time series analysis, which can help determine the parameters of the time series model; ACF describes the correlation between a time series and its own lagged version, while PACF describes the correlation between a time series and its own lagged version given an intermediate lag;

[0123] Check whether the residuals of the time series model show a white noise distribution; if the residuals are not white noise, it indicates that the model has not fully captured all the information in the data. It is necessary to repeat the parameter identification and model checking steps and perform a white noise test on the residuals of the model, such as using the Ljung-Box test. If the residuals are not white noise, return to step S232 to re-identify the parameters and check the residuals again. White noise is an ideal random process whose values ​​at each time point are independent and have the same variance. In time series analysis, if the residuals of the model show a white noise distribution, it means that the model has captured all the information in the data. Useful information, compare the prediction results of the model with the actual data, calculate and evaluate the prediction error and accuracy to verify the prediction performance of the model, and use the selected time series model for prediction; calculate the prediction error, such as mean square error (MSE) or mean absolute error (MAE); evaluate the accuracy of the model. If the prediction performance of the model meets the requirements, integrate it with other related models or data into the hydropower integration model, and use the integrated model for simulation and prediction to evaluate the potential impact of electricity-water complementary behavior. If the prediction performance of the model does not meet the requirements, return to step S231 to reselect or adjust the model.

[0124] S24. Use the maximum likelihood estimation method to estimate the parameters of the hydropower integration model from actual data.

[0125] S25. Use historical data to verify and test the hydropower integration model, and adjust the parameters of the hydropower integration model according to the test results.

[0126] S26. Based on the hydropower integration model, simulate the electricity-water complementary behavior in rural low-voltage substations under various scenarios.

[0127] Preferably, according to the hydropower integration model, simulating the electricity-water complementary behavior of rural low-voltage areas under various scenarios includes the following steps:

[0128] S261. Define different scenarios including different seasons, different weather conditions and different electricity demand levels;

[0129] S262, obtaining power consumption data, water resource consumption data and photovoltaic power generation data corresponding to different seasons, different weather conditions and different power demand levels;

[0130] S263, inputting the acquired power consumption data, water resource consumption data and photovoltaic power generation data into the hydropower integration model, and running the hydropower integration model to simulate the electricity-water complementary behavior under various scenarios;

[0131] S264. Analyze the simulation results, evaluate the complementary effects of electricity consumption and water resource consumption and the contribution of photovoltaic power generation to electricity supply under various scenarios; and perform sensitivity analysis to explore the impact of photovoltaic power generation, electricity demand, and water resource availability on electricity-water complementary behavior.

[0132] It should be explained that a hydropower integration model has been established taking the electricity-water complementarity behavior of a rural low-voltage substation in a certain city as an example; in order to have a more comprehensive understanding of the electricity-water complementarity situation in this substation, it is intended to simulate the behavior under a variety of different scenarios.

[0133] First, different scenarios were defined, including different seasons (such as spring, summer, autumn and winter), different weather conditions (such as sunny, cloudy and rainy days) and different electricity demand levels (such as peak, flat and valley). Different scenarios will help to more comprehensively understand the electricity-water complementary behavior of the substation under different conditions; the electricity consumption data, water resource consumption data and photovoltaic power generation data corresponding to these scenarios were collected; for example, for the summer sunny peak scenario, the electricity consumption, water resource consumption and photovoltaic power generation data of the substation during the summer sunny days and peak electricity demand periods were obtained.

[0134] Then, the data on electricity consumption, water resource consumption and photovoltaic power generation are input into the hydropower integration model, and the model is run to simulate the electricity-water complementary behavior under various scenarios; the model will consider the interaction between electricity consumption, water resource consumption and photovoltaic power generation, and output the simulation results.

[0135] The simulation results were analyzed, and the complementary effects of electricity consumption and water resource consumption and the contribution of photovoltaic power generation to electricity supply under various scenarios were evaluated. It was found that under the peak scenario of sunny days in summer, due to the high photovoltaic power generation, electricity consumption was effectively supplemented, while water resource consumption was also reduced.

[0136] In addition, a sensitivity analysis was performed to explore the impact of photovoltaic power generation, electricity demand, and water resource availability on electricity-water complementarity behavior; it was found that an increase in photovoltaic power generation will significantly improve the reliability of electricity supply and reduce water resource consumption; an increase in electricity demand will lead to a simultaneous increase in electricity consumption and water resource consumption; and a decrease in water resource availability will limit the effect of electricity-water complementarity.

[0137] S3. Create a multi-objective optimization model, and build an intelligent electricity-water coordinated control strategy suitable for real-time regulation in order to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources.

[0138] Preferably, a multi-objective optimization model is created, and an intelligent electricity-water coordinated control strategy suitable for real-time regulation is constructed to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources, including the following steps:

[0139] S31. Set minimizing electricity costs and maximizing the efficiency of joint utilization of electricity and water resources as optimization goals, and define quantitative indicators and constraints of the optimization goals;

[0140] S32. Identify and determine the various variables that affect electricity costs and resource utilization efficiency;

[0141] S33. Treat the optimization goal as a game participant and use Nash game theory to assign each variable to the most relevant goal;

[0142] S34, setting the operating parameters of the genetic algorithm, and optimizing the current Pareto efficiency frontier solution using the Nash game equilibrium method after each generation of the genetic algorithm;

[0143] S35. Create a multi-objective optimization model and conduct simulation tests on the multi-objective optimization model to evaluate the performance under different operating conditions, analyze the preliminary optimization results, and identify the Pareto efficiency optimal solution in the solution set;

[0144] S36. Based on the test results of the multi-objective optimization model, an intelligent electricity-water coordinated control strategy suitable for real-time regulation is established to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources.

[0145] It should be explained that the optimization objectives include: minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources;

[0146] Quantitative indicators include: electricity cost: calculated in monetary units (such as yuan), including electricity charges, equipment maintenance fees, etc. Resource utilization efficiency: measured by the comprehensive utilization rate of electricity and water resources, which can be calculated by comparing the ratio of actual consumption to the theoretical minimum consumption;

[0147] Constraints include: power supply must meet demand and must not fall below the minimum power demand, water consumption must not exceed available water resources, and equipment operating parameters must be within a safe range;

[0148] The variables include: electricity consumption, water consumption, photovoltaic power generation, electricity price, equipment efficiency, weather conditions (affecting photovoltaic power generation) and time of day (affecting electricity demand and water availability);

[0149] The game participants include: the goal of minimizing electricity costs and maximizing resource utilization efficiency;

[0150] The variable allocation includes: electricity consumption and water consumption: these two variables affect both electricity cost and resource utilization efficiency, so they are allocated to two goals and need to find an equilibrium point in the game;

[0151] Photovoltaic power generation: mainly affects the electricity cost, so more is allocated to the goal of minimizing electricity cost;

[0152] Equipment efficiency: mainly affects resource utilization efficiency, so more is allocated to the goal of maximizing resource utilization efficiency;

[0153] Other variables such as electricity prices, weather conditions and time of day serve as external environmental factors in the game;

[0154] The genetic algorithm operating parameters include: population size, crossover probability, mutation probability and number of iterations;

[0155] Nash game equilibrium optimization includes: after each generation, using Nash game theory to evaluate the individuals in the current population (i.e., possible solutions), and selecting those individuals that achieve equilibrium between the two goals as the parents of the next generation.

[0156] Combining genetic algorithms and Nash game theory, a multi-objective optimization model is created, which can simultaneously consider electricity costs and resource utilization efficiency. The model is simulated and tested under different operating conditions (such as different electricity demands, different weather conditions) to evaluate its performance; the preliminary optimization results are analyzed to identify the Pareto efficiency optimal solutions in the solution set, that is, those solutions that achieve the best trade-off between the two objectives. Based on the test results of the multi-objective optimization model, an intelligent electricity-water coordinated control strategy suitable for real-time regulation is built; the strategy can dynamically adjust the use of electricity and water resources according to actual operating conditions (such as real-time electricity demand, real-time weather conditions) to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources. The control strategy is applied to the actual system, and it is continuously monitored and evaluated to ensure its effectiveness and stability in actual operation; necessary adjustments and optimizations are made to the strategy based on the monitoring results.

[0157] Identifying and determining the various variables that affect electricity costs and resource utilization efficiency and treating the optimization objectives as game participants, using Nash game theory, and assigning each variable to the most relevant goal includes the following steps:

[0158] First, define the various objectives in the optimization problem and treat them as participants in the game. Determine the number of participants and assign a unique identifier to each participant.

[0159] For each participant, define its possible strategy set; in the context of optimization problems, strategies may represent different variable values ​​or decision plans. Make sure that each participant's strategy set is complete and mutually exclusive, that is, it covers all possible decision situations;

[0160] Define a utility function for each participant, which quantifies the participant's benefits or satisfaction under a given strategy combination. The utility function should be able to reflect the participant's preferences and constraints on the optimization goal;

[0161] Using the defined players, strategies, and utility functions, construct a Nash game model in which each player tries to choose a strategy that maximizes his or her own utility function.

[0162] Analyze the game model and find the strategy combination that meets the Nash game equilibrium conditions; at the Nash game equilibrium point, each participant cannot increase his or her own utility by changing the strategy alone. Use mathematical methods (such as linear programming, nonlinear programming or iterative algorithms) to solve the Nash game equilibrium point;

[0163] According to the strategy combination of the Nash game equilibrium point, each variable is assigned to the most relevant goal, the impact of the allocation results on the optimization goal is evaluated, and they are ensured to meet the expected optimization criteria;

[0164] The allocation results are verified to ensure that they are effective and feasible in practical applications. If necessary, the game model and allocation strategy are adjusted based on feedback and actual conditions.

[0165] The operating parameters of the genetic algorithm are set. After each generation of the genetic algorithm, the Nash game equilibrium method is used to optimize the current Pareto efficiency frontier solution, which includes the following steps:

[0166] Set the population size, that is, the number of individuals in each generation;

[0167] Set the crossover probability to control the frequency of crossover operations in the genetic algorithm;

[0168] Set the mutation probability to control the frequency of mutation operations in the genetic algorithm;

[0169] Set the number of iterations, i.e. the number of generations the genetic algorithm runs;

[0170] Starting from the initial population, the iterative process of the genetic algorithm is carried out;

[0171] In each generation, a new population is generated through selection, crossover, and mutation operations;

[0172] Evaluate each individual in the current population and calculate its corresponding electricity cost and the efficiency of the joint use of electricity and water resources;

[0173] Based on the evaluation results, determine the Pareto efficiency frontier solutions in the current population, that is, those solutions that achieve the best trade-off between the two objectives;

[0174] The current Pareto efficiency frontier solutions are considered as participants in the Nash game, and each solution represents a strategy;

[0175] A utility function is defined for each solution, which quantifies the performance of the solution in meeting the electricity cost and the efficiency of the joint use of electricity and water resources;

[0176] Find a solution that satisfies the Nash game equilibrium condition, that is, at this equilibrium point, no solution can increase its own utility by changing its strategy alone;

[0177] The Pareto efficiency frontier solution optimized by Nash game equilibrium is used as part of the new population;

[0178] If necessary, the population can be replenished by other means (such as randomly generating new individuals) to keep the population size constant;

[0179] Check whether the number of iterations or other termination conditions of the genetic algorithm have been reached;

[0180] If the termination condition is met, the final Pareto efficiency frontier solution is output; otherwise, return to step 2 to continue execution.

[0181] Creating a multi-objective optimization model and conducting simulation tests on the multi-objective optimization model, evaluating the performance under different operating conditions, analyzing the preliminary optimization results, and identifying the Pareto efficiency optimal solution in the solution set include the following steps:

[0182] According to the optimization problem, define the objective function, including minimizing the electricity cost and maximizing the efficiency of the joint utilization of electricity and water resources; determine the decision variables, such as electricity consumption, water resource consumption, etc., and the constraints, such as electricity supply demand, water resource availability, etc., and construct a mathematical model for the multi-objective optimization problem, integrating the objective function and the constraints;

[0183] Determine the environment and conditions for simulation testing, including different power demands, weather conditions, etc., design test cases to ensure that all possible operating conditions are covered, use simulation software or programming tools to simulate the multi-objective optimization model according to the designed test cases, and record the optimization results under each test case, including electricity cost, efficiency of joint utilization of electricity and water resources, and the values ​​of decision variables;

[0184] Analyze simulation test results, evaluate the performance of multi-objective optimization models under different operating conditions, compare optimization results with expected goals, calculate deviations or errors, and evaluate the accuracy and reliability of the model;

[0185] Conduct in-depth analysis of the optimization results obtained from simulation tests to understand the trade-offs between various objectives and identify which variables have the greatest impact on the optimization results under different operating conditions;

[0186] In the optimization results, identify those solutions that achieve the best trade-off between the two objectives, that is, the Pareto efficiency optimal solution. Use graphical methods (such as Pareto efficiency frontier diagrams) or mathematical methods (such as multi-objective decision analysis) to assist in identifying the Pareto efficiency optimal solution. Summarize the simulation test results and performance evaluation of the multi-objective optimization model. Based on the analysis results, make necessary adjustments and optimizations to the model to improve its performance and accuracy under different operating conditions.

[0187] S4. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results.

[0188] Preferably, the hydropower integration model and the intelligent power-water coordinated control strategy are integrated into the existing power management system and water resources management system; the economic benefits and environmental impacts are regularly evaluated, and the control strategy is adjusted and optimized based on the evaluation results, including the following steps:

[0189] S41. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system;

[0190] S42. After the integration is completed, the integrated existing power management system and water resources management system shall be subjected to functional testing, performance testing and stability testing;

[0191] S43, setting an evaluation time interval, and at the end of each evaluation period, collecting operation data of the power management system and the water resources management system, including power cost, power and water resources utilization efficiency, and environmental impact;

[0192] S44. Analyze the collected data and evaluate the economic benefits and environmental impact of the intelligent power-water coordinated control strategy;

[0193] S45. Based on the evaluation results, identify the problems and deficiencies in the intelligent power-water coordinated control strategy, make necessary adjustments and optimizations to the strategy, and reintegrate the adjusted strategy into the power and water resources management system for testing and verification.

[0194] It should be explained that, assuming that a region has an existing power management system and water resources management system, but the two systems have not yet been integrated and coordinated. In order to improve the efficiency of power and water resources utilization in the region, it is decided to integrate the hydropower integration model and the intelligent power-water coordinated control strategy into the two existing management systems.

[0195] The specific implementation steps are as follows:

[0196] Develop a hydropower integration model that comprehensively considers the supply and demand relationship, utilization efficiency and mutual impact of electricity and water resources;

[0197] Design an intelligent electricity-water coordinated control strategy that can dynamically adjust the use of electricity and water resources based on real-time data to minimize electricity costs and maximize the efficiency of the joint use of electricity and water resources;

[0198] Integrate the hydropower integration model and intelligent power-water collaborative control strategy into the existing power management system and water resources management system to ensure that the two systems can achieve data sharing and collaborative decision-making;

[0199] After the integration work is completed, the integrated system needs to be fully tested to ensure the correctness of its functions, superior performance and stable operation;

[0200] Conduct functional testing to verify whether the integrated system can achieve the expected functions, such as real-time data collection, collaborative decision-making, etc.;

[0201] Conduct performance testing to evaluate the response speed and stability of the integrated system when processing large amounts of data and performing complex calculations;

[0202] Conduct stability testing to ensure that the integrated system can maintain stable performance over a long period of time without crashing or losing data;

[0203] In order to evaluate the actual effect of the intelligent power-water coordinated control strategy, it is necessary to set a reasonable evaluation time interval and collect relevant operation data at the end of each evaluation cycle;

[0204] According to actual needs, the evaluation interval is set to once a quarter;

[0205] At the end of each assessment cycle, operational data including electricity costs, electricity and water efficiency, and environmental impacts are collected from the power management system and water resources management system;

[0206] Analyze the collected data to evaluate the performance of the smart electricity-water coordinated control strategy in terms of economic benefits and environmental impact;

[0207] Use data analysis tools to process and analyze the collected data to calculate indicators such as the reduction in electricity costs, the improvement in the efficiency of electricity and water resources, and environmental impact (such as the reduction in carbon emissions);

[0208] Based on the analysis results, the economic benefits and environmental impact of the intelligent power-water coordinated control strategy are evaluated to determine whether it achieves the expected goals;

[0209] Based on the evaluation results, identify the problems and deficiencies in the intelligent power-water coordinated control strategy and make necessary adjustments and optimizations;

[0210] Based on the evaluation results, problems in the smart power-water coordinated control strategy were identified, such as inaccurate decision-making in some cases and insufficient response to emergencies.

[0211] Make necessary adjustments and optimizations to strategies based on identified problems, such as improving algorithms and adding decision-making rules;

[0212] The adjusted strategies are reintegrated into the power and water management systems and fully tested and verified to ensure their correct functionality and superior performance.

[0213] According to another embodiment of the present invention, Figure 2 As shown, a distributed photovoltaic aggregation optimization control system based on hydropower integration is also provided, and the distributed photovoltaic aggregation optimization control system includes: a data acquisition module 1, a hydropower integration model construction module 2, an intelligent electricity-water coordinated control strategy creation module 3 and a system integration and optimization module 4;

[0214] Data collection module 1, used to collect power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas;

[0215] Hydropower integration model construction module 2 is used to construct a hydropower integration model that simulates the interaction between electricity and water resources in low-voltage areas based on the electricity consumption data and water resource consumption data of distributed photovoltaic systems, so as to simulate the electricity-water complementary behavior of rural low-voltage areas under various scenarios;

[0216] Intelligent power-water coordinated control strategy creation module 3 is used to create a multi-objective optimization model and build an intelligent power-water coordinated control strategy suitable for real-time regulation by minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources;

[0217] System integration and optimization module 4 is used to integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results.

[0218] In summary, with the help of the above technical solutions of the present invention, the present invention provides accurate prediction and analysis tools based on actual data, which is helpful to understand the interactive relationship between electricity and water resources, can better allocate resources, and optimize the efficiency of energy and water resources; multi-scenario simulation can take into account different seasons, weather conditions and electricity demand levels, and is widely applicable to various actual scenarios, so that the model can predict and respond to various situations that may occur in the future. Through time series analysis and parameter estimation, the model can capture seasonal and trend changes in the data, provide support for long-term planning and short-term adjustments, and the simulation of electricity-water complementary behavior can optimize the utilization of photovoltaic power generation and water resources, and improve the overall sustainability of the system; the present invention identifies and considers various variables that affect electricity costs and resource utilization efficiency, such as electricity consumption, water resource consumption, etc., and defines corresponding constraints to ensure that the optimization process is carried out within a practical and feasible range. The Nash game theory is used to regard the optimization target as a game participant, and each variable is assigned to the most relevant target, so as to better handle the trade-off relationship between multiple targets and find a better solution. The operating parameters of the genetic algorithm are set, and the Nash game equilibrium method is used to optimize after each generation. The current Pareto efficiency frontier solution is optimized. The method combining genetic algorithm and Nash game theory can more effectively search for the global optimal solution. A comprehensive simulation test is carried out on the multi-objective optimization model, the performance under different operating conditions is evaluated, and the preliminary optimization results are analyzed to identify the optimal Pareto efficiency solution in the solution set. Based on the test results of the multi-objective optimization model, an intelligent power-water coordinated control strategy suitable for real-time regulation is constructed. The strategy can dynamically adjust the use of electricity and water resources according to the actual operating conditions to achieve the optimization goal; the present invention realizes the organic integration of the power management system and the water resources management system by integrating the hydropower integration model and the intelligent power-water coordinated control strategy, breaks the information barriers between the original systems, and improves the overall coordination and integration. By regularly evaluating the economic benefits, problems and deficiencies in the optimization control strategy can be discovered and adjusted in time, thereby further improving the utilization efficiency of electricity and water resources, reducing electricity costs, and bringing significant economic benefits to the region. Regularly evaluating the environmental impact enables managers to clearly understand the impact of the current strategy on the environment, and adjust and optimize the strategy based on the evaluation results to achieve a dual improvement in economic and environmental benefits.

[0219] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A distributed photovoltaic aggregation optimization control method based on hydropower integration, characterized in that: The distributed photovoltaic aggregation optimization control method comprises the following steps: S1. Collect the power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas; S2. Based on the power consumption data and water resource consumption data of distributed photovoltaic systems, a hydropower integration model simulating the interaction between power and water resources in low-voltage areas is constructed to simulate the complementary behavior of power and water in rural low-voltage areas under various scenarios; S3. Create a multi-objective optimization model, and build an intelligent electricity-water coordinated control strategy suitable for real-time regulation by minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources; S4. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results; The S2 includes: S21. Preprocessing the power consumption data and water resource consumption data of the distributed photovoltaic system in the rural low-voltage area; S22. Perform exploratory data analysis to identify the characteristics and patterns of pre-processed electricity consumption data and water consumption data through descriptive statistics, correlation analysis and visualization, and define the framework of the water-power integration model; S23. Use time series analysis techniques, combined with identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption, and capture seasonal and trend changes; S24. Estimate the parameters of the hydropower integration model from actual data using the maximum likelihood estimation method; S25. Verify and test the hydropower integration model using historical data, and adjust the parameters of the hydropower integration model according to the test results; S26. Based on the hydropower integration model, simulate the electricity-water complementary behavior in rural low-voltage areas under various scenarios; The S22 includes: S221. Arrange the pre-processed power consumption data and water resource consumption data, and calculate the mean, median and standard deviation of the power consumption data and water resource consumption data to obtain the distribution of the data; S222. Based on the distribution of data, the Spearman method is used to analyze the correlation between electricity consumption data and water resource consumption data, and to identify the potential interaction pattern between electricity consumption data and water resource consumption data; S223. Use scatter plots to display the changing trends and distribution characteristics of electricity consumption data and water resource consumption data; S224. Integrate the descriptive statistics in step S221, the correlation analysis in step S222, and the visualization results in step S223 to identify the key characteristics and potential patterns of electricity consumption and water resource consumption data, and define the inputs, outputs, and key variables of the hydropower integration model; The S3 includes: S31. Set minimizing electricity costs and maximizing the efficiency of joint utilization of electricity and water resources as optimization goals, and define quantitative indicators and constraints of the optimization goals; S32. Identify and determine the various variables that affect electricity costs and resource utilization efficiency; S33. Treat the optimization goal as a game participant and use Nash game theory to assign each variable to the most relevant goal; S34, setting the operating parameters of the genetic algorithm, and optimizing the current Pareto efficiency frontier solution using the Nash game equilibrium method after each generation of the genetic algorithm; S35. Create a multi-objective optimization model and conduct simulation tests on the multi-objective optimization model to evaluate the performance under different operating conditions, analyze the preliminary optimization results, and identify the Pareto efficiency optimal solution in the solution set; S36. Based on the test results of the multi-objective optimization model, an intelligent electricity-water coordinated control strategy suitable for real-time regulation is established to minimize electricity costs and maximize the efficiency of the joint utilization of electricity and water resources; The S4 includes: S41. Integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; S42. After the integration is completed, the integrated existing power management system and water resources management system shall be subjected to functional testing, performance testing and stability testing; S43, setting an evaluation time interval, and at the end of each evaluation period, collecting operation data of the power management system and the water resources management system, including power cost, power and water resources utilization efficiency, and environmental impact; S44. Analyze the collected data and evaluate the economic benefits and environmental impact of the intelligent power-water coordinated control strategy; S45. Based on the evaluation results, identify the problems and deficiencies in the intelligent power-water coordinated control strategy, make necessary adjustments and optimizations to the strategy, and reintegrate the adjusted strategy into the power and water resources management system for testing and verification.

2. The distributed photovoltaic aggregation optimization control method based on hydropower integration according to claim 1 is characterized in that: The Spearman method is used to analyze the correlation between the power consumption data and the water resource consumption data based on the distribution of the data, and the potential interaction pattern between the power consumption data and the water resource consumption data is identified, which includes the following steps: S2221. Obtain distribution of data points including power consumption data and water resource consumption data; S2222, sorting the electricity consumption data and the water resource consumption data, and assigning ranks to the sorted data points according to the relative positions of the data points; S2223. Calculate the rank correlation coefficient between the electricity consumption data and the water resource consumption data using the calculation formula of the Spearman rank correlation coefficient; S2224, analyzing the calculation result of the Spearman rank correlation coefficient, if the absolute value of the rank correlation coefficient is close to 1, it means that the rank correlation between the power consumption data and the water resource consumption data is strong; if the absolute value of the rank correlation coefficient is close to 0, it means that the rank correlation between the power consumption data and the water resource consumption data is weak; S2225. Based on the analysis results of Spearman's rank correlation coefficient, identify the potential interaction patterns between electricity consumption data and water resource consumption data.

3. The distributed photovoltaic aggregation optimization control method based on hydropower integration according to claim 2 is characterized in that: The expression for calculating the rank correlation coefficient between the power consumption data and the water resource consumption data is: r s represents the Spearman rank correlation coefficient between electricity consumption data and water consumption data; n represents the number of data points in the electricity consumption data and water consumption data; d represents the difference between the electricity consumption level and the water consumption level of each data point; 6 represents the same as ∑d 2 The multiplication factor is used to adjust the influence of the sum of squared rank differences when calculating the correlation coefficient.

4. The distributed photovoltaic aggregation optimization control method based on water-power integration according to claim 3 is characterized in that: The method of using time series analysis techniques, combining the identified features and patterns, to establish a hydropower integration model between electricity consumption and water resource consumption, and to capture seasonal and trend changes includes the following steps: S231. Select a time series model for seasonal decomposition based on the key features and underlying patterns of electricity consumption data and water consumption data identified; S232, identifying parameters of the time series model using the autocorrelation function and the partial autocorrelation function; S233, checking whether the residual of the time series model presents a white noise distribution; if the residual is not white noise, indicating that the time series model does not fully capture all the information in the power consumption data and the water resource consumption data, then repeating steps S232 and S233 until the residual presents a white noise distribution; if the residual is white noise, executing step S234; S234, comparing the prediction results of the model with the actual data, calculating and evaluating the prediction error and accuracy, so as to verify the prediction performance of the model; S235. If the model prediction performance meets the preset requirements, the results of the time series model are integrated into the hydropower integration model to simulate and predict the electricity-water complementary behavior in rural low-voltage substations; if it does not meet the requirements, return to step S231 to reselect or adjust the model.

5. The distributed photovoltaic aggregation optimization control method based on hydropower integration according to claim 4 is characterized in that: According to the hydropower integration model, simulating the electricity-water complementary behavior of rural low-voltage areas under various scenarios includes the following steps: S261. Define different scenarios including different seasons, different weather conditions and different electricity demand levels; S262, obtaining power consumption data, water resource consumption data and photovoltaic power generation data corresponding to different seasons, different weather conditions and different power demand levels; S263, inputting the acquired power consumption data, water resource consumption data and photovoltaic power generation data into the hydropower integration model, and running the hydropower integration model to simulate the electricity-water complementary behavior under various scenarios; S264. Analyze the simulation results, evaluate the complementary effects of electricity consumption and water resource consumption and the contribution of photovoltaic power generation to electricity supply under various scenarios; and perform sensitivity analysis to explore the impact of photovoltaic power generation, electricity demand, and water resource availability on electricity-water complementary behavior.

6. A distributed photovoltaic aggregation optimization control system based on hydropower integration, used to implement the distributed photovoltaic aggregation optimization control method based on hydropower integration as described in any one of claims 1 to 5, characterized in that: The distributed photovoltaic aggregation optimization control system includes: data acquisition module, hydropower integration model building module, intelligent power-water coordinated control strategy creation module and system integration and optimization module; Data collection module, used to collect power consumption data and water resource consumption data of distributed photovoltaic systems in rural low-voltage areas; The hydropower integration model building module is used to build a hydropower integration model that simulates the interaction between electricity and water resources in low-voltage areas based on the electricity consumption data and water resource consumption data of distributed photovoltaic systems, and is used to simulate the electricity-water complementary behavior of rural low-voltage areas under various scenarios; Intelligent power-water coordinated control strategy creation module, which is used to create a multi-objective optimization model and build an intelligent power-water coordinated control strategy suitable for real-time regulation by minimizing electricity costs and maximizing the efficiency of the joint utilization of electricity and water resources; The system integration and optimization module is used to integrate the hydropower integration model and intelligent power-water coordinated control strategy into the existing power management system and water resources management system; regularly evaluate the economic benefits and environmental impacts, and adjust and optimize the control strategy based on the evaluation results.

Images