A distributed optimization method and system for a new energy power generation station and an energy storage station

Abstract

The application discloses a kind of new energy power station and the distributed optimization method and system of energy storage power station, method includes: according to predicted first power generation data of new energy power station, second power generation data of traditional power station and power consumption data, generate power size relationship curve;According to power size relationship curve, determine the optimization mode of new energy power station, if optimization mode is power station optimization, then output the prompt information of the distributed optimization of new energy power station;If optimization mode is energy storage power station optimization, then determine the capacity size of multiple energy storage power stations for energy storage, and according to each capacity size, the distributed optimization of energy storage power station is carried out.The capacity size of energy storage power station determined by the application can accurately match the remaining power except power consumption, to realize the accurate storage of surplus power energy;And energy storage power station can be set as pumped storage power station, to make full use of natural resources, to avoid affecting the environment.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a distributed optimization method and system for new energy power generation stations and energy storage power stations. Background Technology

[0002] In recent years, with the rapid development of new energy power generation technologies such as wind and solar power, the number of wind and solar power plants has increased significantly. However, the power output of wind and solar power is unstable due to environmental factors, making it difficult to connect to the power grid. This has led to increasingly prominent problems of energy curtailment, such as wind and solar power being abandoned. To fully and effectively utilize the electricity generated by new energy sources like wind and solar power and reduce carbon emissions, energy storage technology has emerged. As a key technology for promoting energy structure transformation, energy storage technology plays an indispensable role in the large-scale integration of renewable energy sources and in improving the efficiency, security, and economy of power systems and regional energy systems.

[0003] Currently, energy storage technologies can be categorized into mechanical energy storage, electrochemical energy storage, electrical energy storage, and thermal energy storage based on their storage methods. Among these, mechanical energy storage and electrochemical energy storage are the most commonly used. Mechanical energy storage converts electrical energy into mechanical energy such as potential energy or kinetic energy through specific devices or facilities, such as pumped hydro storage and flywheel energy storage. Electrochemical energy storage utilizes specific materials to achieve the interconversion of electrical energy and chemical energy, thus storing electrical energy, such as lithium-ion batteries and lead-acid batteries.

[0004] While the development of energy storage technology has alleviated the problem of energy curtailment from renewable energy generation to some extent, complex scenarios involving the combined generation of renewable and traditional energy sources still present challenges. These challenges include insufficient total power generation, excessive power generation leading to curtailment, or significant environmental impact due to inadequate planning of renewable energy power plants and energy storage stations. Therefore, how to optimize the distributed generation of renewable energy power plants and energy storage stations to meet electricity demand while storing renewable energy, thereby minimizing energy curtailment and environmental impact, is a pressing technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of this invention is to overcome the above-mentioned defects and problems in the prior art and provide a distributed optimization method and system for new energy power plants and energy storage power stations. This method is used to perform distributed optimization of new energy power plants and energy storage power stations, so as to meet the electricity demand while storing new energy power generation, thereby minimizing the curtailment of new energy and the impact on the environment.

[0006] To achieve the above objectives, the technical solution of the present invention is: a distributed optimization method for new energy power plants and energy storage power stations, comprising:

[0007] Predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period;

[0008] Predict the electricity consumption data of the area to be planned within a preset time period, and generate an electricity consumption relationship curve based on each of the first power generation data, each of the second power generation data, and the electricity consumption data;

[0009] Based on the power volume relationship curve, the optimization mode of the new energy power generation station is determined. If the optimization mode is power generation station optimization, a prompt message is output to perform distributed optimization of the new energy power generation stations in the area to be planned.

[0010] If the optimization mode is energy storage power station optimization, then the capacity of multiple energy storage power stations used for energy storage of each new energy power generation station in the area to be planned is determined, and distributed optimization of the energy storage power stations in the area to be planned is performed according to the capacity of each station.

[0011] The new energy power generation station is a wind power generation station, and the predicted power generation data of each new energy power generation station in the planned area within a preset time period includes:

[0012] For each wind power plant, acquire historical wind direction data, historical wind speed data, historical air density data, and historical wind power generation hours within multiple historical time periods corresponding to a preset time period;

[0013] Based on the historical wind direction data and the historical wind speed data, the average effective wind speed of the wind power station within the preset time period is predicted, as well as the effective duration corresponding to the average effective wind speed. Based on the effective duration and the historical wind power generation hours, the number of wind power generation hours is predicted.

[0014] The average air density of the wind power plant during the preset time period is predicted based on the historical air density data, and the wind turbine parameters, prediction correction coefficient, and first-year attenuation coefficient of the wind power plant are found.

[0015] Based on the first-year attenuation coefficient, average effective wind speed, average air density, wind power generation hours, prediction correction coefficient, and the wind turbine parameters including blade length, wind energy utilization coefficient, blade area, blade angle of attack, and generator angular velocity, the first power generation data of the wind power station in the preset period is calculated using the following formula:

[0016]

[0017] In the formula, Q1 represents the first power generation data; N represents the number of wind power generation hours; n1 represents the number of wind power generation stations; n2 represents the number of wind turbines in the wind power generation station; and r1 represents the first annual degradation coefficient. A represents the wind energy utilization factor of the j-th wind turbine in the i-th wind power station; ρ represents the average air density; A ij B represents the blade area of ​​the j-th wind turbine in the i-th wind power station; ij L represents the blade angle of attack of the j-th wind turbine in the i-th wind power station; ij V represents the blade length of the j-th wind turbine in the i-th wind power station; V represents the average effective wind speed; ω ij τ represents the generator angular velocity of the j-th wind turbine in the i-th wind power station; τ represents the prediction correction coefficient. Used to calculate the motor torque of the j-th wind turbine in the i-th wind power station.

[0018] The new energy power generation station is a photovoltaic power generation station, and the predicted power generation data of each new energy power generation station in the planned area within a preset time period includes:

[0019] The system acquires historical solar temperature data and historical solar intensity data of the photovoltaic power plant within multiple historical time periods corresponding to a preset time period, and predicts the solar temperature data and solar intensity data of the photovoltaic power plant during the preset time period based on each of the historical solar temperature data and historical solar intensity data.

[0020] The light temperature data and light intensity data are respectively fitted into a temperature time function and an intensity time function within a preset time period, and the light intensity data is generated as the average light intensity within the preset time period;

[0021] Find the second-year degradation coefficient, hourly reference output power, and temperature coefficient corresponding to the photovoltaic power generation station, as well as the hourly reference irradiance and hourly reference temperature corresponding to the hourly reference output power;

[0022] Based on the aforementioned second-year attenuation coefficient, hourly reference output power, temperature coefficient, hourly reference illuminance, hourly reference temperature, and the aforementioned average illuminance, temperature-time function, and intensity-time function, the first power generation data of the photovoltaic power station within a preset time period is calculated using the following formula:

[0023]

[0024] In the formula, Q2 represents the first power generation data; k represents the temperature coefficient; r2 represents the second annual decay coefficient; G represents the average solar intensity within the preset time period; G0 represents the hourly reference solar intensity; P0 represents the hourly reference output power; g(t) represents the intensity time function; θ(t) represents the temperature time function; θ0 represents the hourly reference temperature. Used to calculate the light intensity coefficient within a preset time period.

[0025] The prediction of electricity consumption data for the area to be planned within a preset time period includes:

[0026] Obtain historical electricity consumption data of the area to be planned in multiple historical time periods corresponding to the preset time period, as well as population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters for each historical time period;

[0027] Generate a historical array for each historical period from the historical electricity consumption data, population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters.

[0028] Based on a preset prediction model, the historical data for each historical period is analyzed and calculated to obtain the electricity consumption data of the area to be planned within the preset period. The formula used for analysis and calculation in the preset prediction model is as follows:

[0029]

[0030] In the formula, H represents electricity consumption data; W hb W represents the connection weights between the output layer and the b-th hidden layer in the preset prediction model; s represents the number of hidden layers in the preset prediction model; W cb d represents the connection weights between the input layer and the b-th hidden layer in the preset prediction model; c This represents the Cth history array; m represents the number of history arrays; α b δ represents the hidden layer model parameters of layer b; δ represents the output layer model parameters.

[0031] The determination of the capacity of multiple energy storage power stations used for energy storage at various new energy power plants within the planned area includes:

[0032] Identify the maximum difference in the power quantity relationship curve, and determine the total capacity of the multiple energy storage power stations based on the maximum difference;

[0033] Each of the first power generation data is generated as a power generation percentage, and the total capacity is divided into storage capacities corresponding to each of the new energy power generation stations based on the power generation percentages.

[0034] Based on the storage capacity to be stored, determine the energy storage capacity of the energy storage power station corresponding to each of the new energy power generation stations, and obtain the capacity loss value corresponding to each of the energy storage capacities to correct each of the energy storage capacities, thereby obtaining the capacity size of the energy storage power station corresponding to each of the new energy power generation stations.

[0035] The step of performing distributed optimization of energy storage power stations within the planned area based on the capacity of each station includes:

[0036] Determine whether the environmental parameters of the environment where each new energy power generation station is located include water source parameters. If water source parameters are included, then the energy storage power station corresponding to the new energy power generation station is identified as a pumped storage power station, and the location of the water source corresponding to the water source parameters is obtained as the location information of the pumped storage power station.

[0037] If the environmental parameters do not include water source parameters, then obtain the energy storage noise data corresponding to the capacity of the energy storage power station, and determine the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data.

[0038] The location information and the capacity size are used as optimization parameters for the energy storage power station, and the energy storage power station is optimized in a distributed manner based on the optimization parameters.

[0039] The step of determining the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data includes:

[0040] Obtain the power generation noise data corresponding to the energy storage noise data in each of the new energy power generation stations, and determine the initial location information of the energy storage power station;

[0041] Based on the initial location information, the energy storage noise data and the power generation noise data are superimposed to generate a superimposed value that varies with distance;

[0042] Determine the maximum value among the superimposed values ​​that change with distance, and determine whether the maximum value is less than or equal to a preset threshold. If it is less than or equal to the preset threshold, then determine the initial position information as the position information.

[0043] If the maximum value is greater than a preset threshold, the initial position information is adjusted, and based on the adjusted initial position information, the step of superimposing the volume of the energy storage noise data and the power generation noise data is performed.

[0044] The step of determining the optimization mode of the new energy power generation station based on the power volume relationship curve includes:

[0045] Based on the power generation curve, determine the total power generation and total power consumption of the area to be planned within a preset time period, and determine the relationship between the total power consumption and the total power generation.

[0046] If the relationship is that the total electricity consumption is greater than the total power generation, then it is determined whether the difference between the total electricity consumption and the total power generation is greater than a preset electricity consumption difference. If it is greater than the preset electricity consumption difference, then the optimization mode is determined to be power plant optimization.

[0047] If the total electricity consumption is less than the total power generation, then the optimization mode is determined as energy storage power station optimization.

[0048] A distributed optimization system for new energy power generation stations and energy storage power stations, the system being applied to the methods described above, the system comprising:

[0049] The power generation data acquisition module is used to predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period.

[0050] The power consumption curve generation module is used to predict the power consumption data of the area to be planned within a preset time period, and generate a power consumption curve based on the first power generation data, the second power generation data, and the power consumption data.

[0051] The distributed optimization mode determination module is used to determine the optimization mode of the new energy power generation station based on the power quantity relationship curve. If the optimization mode is power generation station optimization, it outputs a prompt message to perform distributed optimization on the new energy power generation station in the area to be planned. If the optimization mode is energy storage station optimization, it determines the capacity of multiple energy storage stations used for energy storage at each new energy power generation station in the area to be planned, and performs distributed optimization on the energy storage stations in the area to be planned based on the capacity of each station.

[0052] A distributed optimization device for new energy power generation stations and energy storage power stations includes a memory and a processor;

[0053] The memory is used to store computer program code and transmit the computer program code to the processor;

[0054] The processor is configured to execute the method described above according to instructions in the computer program code.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] This invention discloses a distributed optimization method and system for new energy power plants and energy storage power stations. The method predicts the first power generation data of new energy power plants within a planned area over a preset time period, and the second power generation data of traditional power plants within the same planned area over the same preset time period. It also predicts the electricity consumption data of the planned area within the preset time period. Based on the predicted first power generation data, second power generation data, and electricity consumption data, an electricity consumption relationship curve is generated. Then, the optimization mode for the new energy power plants is determined based on the electricity consumption relationship curve. If the determined optimization mode is power plant optimization, it indicates that the planning of new energy power plants within the planned area is unreasonable, and therefore, distributed optimization is performed on the new energy power plants. If the determined optimization mode is energy storage power station optimization, it indicates that the energy storage power stations within the planned area need to be optimized, thereby determining the capacity of multiple energy storage power stations used for energy storage at each new energy power plant within the planned area, and performing distributed optimization on the energy storage power stations within the planned area based on this capacity. The power generation curve illustrates the relationship between total power generation and power consumption, achieved through the combination of traditional and new energy sources. This allows for the identification of optimization models, including distributed optimization of new energy power plants and distributed optimization of energy storage stations used to store energy at these plants. Power plant optimization addresses the issue of insufficient total power generation. Energy storage station optimization determines the appropriate capacity to accurately match the remaining power beyond consumption, enabling precise storage of surplus energy and minimizing energy wastage. Furthermore, the location of energy storage stations is determined by considering the environmental impact of noise pollution, thus minimizing significant noise pollution. Attached Figure Description

[0057] Figure 1 This is a flowchart of the first embodiment of a distributed optimization method for new energy power generation stations and energy storage power stations according to the present invention.

[0058] Figure 2 This is a flowchart of the second embodiment of a distributed optimization method for new energy power generation stations and energy storage power stations according to the present invention.

[0059] Figure 3 This is a flowchart of the third embodiment of a distributed optimization method for new energy power generation stations and energy storage power stations according to the present invention.

[0060] Figure 4 This is a flowchart of the fourth embodiment of a distributed optimization method for new energy power generation stations and energy storage power stations according to the present invention.

[0061] Figure 5This is a structural block diagram of a distributed optimization system for a new energy power generation station and an energy storage power station according to the present invention.

[0062] Figure 6 This is a structural block diagram of a distributed optimization device for a new energy power generation station and an energy storage power station according to the present invention. Detailed Implementation

[0063] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0064] This invention provides a distributed optimization method for new energy power plants and energy storage power stations, see [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the distributed optimization method for new energy power plants and energy storage power stations of the present invention.

[0065] This invention provides an embodiment of a distributed optimization method for new energy power plants and energy storage power stations. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. Specifically, the distributed optimization method for new energy power plants and energy storage power stations in this embodiment includes:

[0066] S10. Predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period.

[0067] This embodiment applies the distributed optimization method for new energy power plants and energy storage power stations to the control center of the new energy power plant system. The control center performs distributed optimization on existing new energy power plants and on energy storage power stations used for storing energy from these plants. For the distributed optimization of new energy power plants, when the total power generation cannot meet the electricity demand, new new energy power plants are planned. The location of new power plants is determined by analyzing the noise generated by existing power plants, avoiding the cumulative noise impact from multiple power plants. For the distributed optimization of energy storage power stations, when the total power generation exceeds the electricity demand, energy storage power stations are planned to store the remaining electricity generated by the new energy power plants. The capacity of each energy storage station is determined by analyzing the remaining electricity at each power plant, ensuring accurate storage of the remaining electricity. Similarly, the location of energy storage power stations is determined by analyzing the noise generated by existing power plants, avoiding the cumulative noise impact from multiple power plants and energy storage power stations.

[0068] Specifically, new energy power plants utilize renewable natural resources such as wind and solar power to generate electricity, while traditional energy power plants utilize conventional coal-fired power generation. Energy storage power stations can be mechanical pumped-storage systems or electrochemical lithium-ion battery storage systems. Areas with both new and traditional energy power plants, where energy storage power stations are planned for energy storage, are designated as planned areas, such as areas divided by province. Furthermore, a pre-set time period should be established, which can be a quarter, half-year, or year, preferably a year, to reflect the impact of cyclical climate change on the power generation of new energy power plants.

[0069] Furthermore, the number of new energy power plants within the planned area is obtained, and historical power generation data for each new energy power plant is acquired for multiple past periods. These past periods correspond to preset periods; for example, if the preset period is one year, then the multiple past periods represent multiple previous years. The acquired historical power generation data includes, but is not limited to, historical wind speed and historical power generation. Based on this historical power generation data, the power generation data of each new energy power plant within the preset period is predicted to obtain the first power generation data for each new energy power plant within that preset period. This first power generation data is time-dependent; the corresponding power generation varies at different times within the preset period. For example, during a period of high sunlight intensity in summer, the power generation of new energy power plants in the planned area may be higher than at a certain time in winter.

[0070] Furthermore, the number of traditional power plants generating electricity using conventional energy sources within the planning area is obtained, as well as historical power generation data for each traditional power plant over multiple past periods. Based on this historical power generation data, the power generation data of each traditional power plant within a preset period is predicted, thereby obtaining the second power generation data of each traditional power plant within the preset period.

[0071] S20. Predict the electricity consumption data of the area to be planned within a preset time period, and generate an electricity consumption relationship curve based on the first power generation data, the second power generation data, and the electricity consumption data.

[0072] Understandably, the electricity consumption in the planned area is not static but dynamically changing. For example, although the climate changes little throughout the year (spring, summer, autumn, and winter), population movement and industrial shifts can lead to changes in electricity consumption. To determine the electricity consumption of the planned area within a preset time period, electricity consumption data from multiple past periods is acquired and combined with factors such as population changes and industrial shifts to predict the electricity consumption data for the planned area within the preset time period. Specifically, predicting the electricity consumption data of the planned area within the preset time period includes:

[0073] S21. Obtain historical electricity consumption data of the area to be planned in multiple historical time periods corresponding to the preset time period, as well as population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters for each historical time period.

[0074] S22. Generate a historical array for each historical period from the historical electricity consumption data, population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters.

[0075] S23. Based on the preset prediction model, analyze and calculate the historical arrays of each historical period to obtain the electricity consumption data of the area to be planned within the preset period.

[0076] Furthermore, historical electricity consumption data for the planned area within multiple historical time periods corresponding to the preset time period are acquired, i.e., electricity consumption data for multiple previous time periods. Simultaneously, population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters are acquired for each historical time period. Among these, the change parameters are used to reflect the magnitude of the change in data compared to the previous time period. For example, if there are three historical periods, including 2023, 2022, and 2021, then for the historical period corresponding to 2023, the population data is the population size in 2023, and the population change parameter is a parameter reflecting the magnitude of the population change in 2023 relative to 2022; the weather data includes at least the number of hot and cold days in 2023, and the corresponding weather change parameter is a parameter reflecting the magnitude of the change in the number of hot and cold days in 2023 relative to 2022; the primary industry data, secondary industry data, and tertiary industry data are the quantities of primary, secondary, and tertiary industries in 2023, and the primary industry change parameter, secondary industry change parameter, and tertiary industry change parameter are parameters reflecting the magnitude of the change in the quantities of primary, secondary, and tertiary industries in 2023 relative to 2022.

[0077] Furthermore, the acquired electricity consumption data, population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters are generated into historical arrays for each historical period. A pre-trained prediction model is then used to analyze and calculate the historical arrays for each historical period to obtain the total electricity consumption data for the area to be planned within the pre-trained period. This total electricity consumption data also has a time attribute; the corresponding electricity consumption varies at different times within the pre-trained period. For example, the electricity consumption in the area to be planned may be higher at a certain time during the high temperatures of summer than at a certain time in spring. The formula used for analysis and calculation in the pre-trained prediction model is as follows:

[0078]

[0079] In the formula, H represents electricity consumption data; W hb W represents the connection weights between the output layer and the b-th hidden layer in the preset prediction model; s represents the number of hidden layers in the preset prediction model; W cb d represents the connection weights between the input layer and the b-th hidden layer in the preset prediction model; c This represents the c-th history array; m represents the number of history arrays; α bδ represents the hidden layer model parameters of layer b; δ represents the output layer model parameters.

[0080] The pre-defined prediction model is trained using a large amount of electricity consumption data, population data, weather data, and industry data from different regions. The connection weights between the input layer and the hidden layer, as well as the connection weights between the output layer and the hidden layer, obtained through training, can accurately uncover the characteristic relationships between electricity consumption and population, weather, and industry, thereby achieving accurate prediction of electricity consumption data for the planned area within a preset time period.

[0081] Furthermore, the predicted primary power generation data, secondary power generation data, and power consumption data are combined to form a power generation relationship curve, which reflects the changes in power generation and power consumption in the planned area within a preset time period. This power generation relationship curve can include both a power generation curve and a power consumption curve, and can be formed on a two-dimensional coordinate system. The horizontal axis of the two-dimensional coordinate system represents each time point within the preset time period, and the vertical axis represents the power generation magnitude. From the primary and secondary power generation data, the primary and secondary power generation at the same time point within the preset time period are selected. The primary and secondary power generation at each same time point are summed to obtain the total power generation at each time point within the preset time period. This total power generation is then added to the two-dimensional coordinate system according to its chronological order, thus forming the power generation curve. Similarly, the power consumption data can be added to the two-dimensional coordinate system according to the chronological order reflected by its time attributes, thus forming the power consumption curve. The magnitudes of the vertical axes of the power generation and consumption curves in the coordinate system reflect the relationship between power generation and consumption, together forming a curve showing the relationship between power generation and consumption. It should be noted that the time period represented by each point on the horizontal axis can be set according to requirements, for example, one day. If the preset period is one year, then the horizontal axis corresponds to 365 time points, and the vertical axis correspondingly represents the total power generation formed by the sum of the first and second power generation data for each day.

[0082] S30. Based on the power quantity relationship curve, determine the optimization mode of the new energy power generation station. If the optimization mode is power generation station optimization, output a prompt message to perform distributed optimization of the new energy power generation station in the area to be planned.

[0083] Furthermore, for the electricity quantity relationship curves in a two-dimensional coordinate system, the vertical coordinates corresponding to the power generation curve and the power consumption curve may be the same or different on the same horizontal axis. If they are the same, it means that the power generation and power consumption are equal at that time. If they are different and the vertical coordinate corresponding to the power generation curve is greater than the vertical coordinate corresponding to the power consumption curve, it means that the power generation at that time is greater than the power consumption, indicating that the circuits generated by the new energy power plants and traditional power plants are sufficient to meet the usage demand. If they are different and the vertical coordinate corresponding to the power generation curve is less than the vertical coordinate corresponding to the power consumption curve, it means that the power generation at that time is less than the power consumption, indicating that the circuits generated by the new energy power plants and traditional power plants are insufficient to meet the usage demand. At the same time, the power generation curve and the power consumption curve in the electricity quantity relationship curve can also reflect the total power generation and total power consumption demand of the planned area within a preset time period. By observing the relationship between the total power generation and the total power consumption, it can be determined whether the total power generation within the preset time period can meet the total power consumption demand, thereby determining the optimization mode of the new energy power plants. This optimization mode includes a distributed optimization mode for new energy power generation stations and a distributed optimization mode for energy storage power stations, specifically determined based on the relationship between total power generation and total power consumption. If the optimization mode is determined to be power generation station optimization, a prompt message indicating that distributed optimization is being performed on the new energy power generation stations in the planned area is output. Specifically, determining the optimization mode of the new energy power generation station based on the power consumption relationship curve includes:

[0084] S31. Based on the power generation relationship curve, determine the total power generation and total power consumption of the area to be planned within a preset time period, and determine the relationship between the total power consumption and the total power generation.

[0085] S32. If the relationship is that the total electricity consumption is greater than the total power generation, then determine whether the difference between the total electricity consumption and the total power generation is greater than a preset electricity consumption difference. If it is greater than the preset electricity consumption difference, then the optimization mode is determined to be power generation station optimization. If the relationship is that the total electricity consumption is less than the total power generation, then the optimization mode is determined to be energy storage station optimization.

[0086] Furthermore, for the power generation curve within the power generation relationship curve, the area enclosed by the horizontal and vertical axes of the two-dimensional coordinate system represents the total power generation of the area to be planned within a preset time period, which can be obtained through integration. Similarly, for the power consumption curve within the power generation relationship curve, the total power consumption of the area to be planned within a preset time period can also be represented by the area enclosed by the horizontal and vertical axes of the two-dimensional coordinate system, and this total power consumption can also be obtained through integration.

[0087] Furthermore, after calculating the total electricity consumption and total power generation, the two are compared to determine their relative magnitudes. If the comparison shows that the total electricity consumption is greater than the total power generation, it indicates that the power generation in the planned area is insufficient within the preset time period, and power generation needs to be increased. This increase can be achieved through peak-shaving units at traditional power plants or by constructing new renewable energy power plants. Considering the higher cost of constructing new renewable energy power plants, when the required increase in power generation is small, priority is given to increasing power generation through peak-shaving units at traditional power plants.

[0088] Furthermore, a preset electricity consumption difference value is set to indicate a small increase in power generation. A difference calculation is performed between the total electricity consumption and the total power generation. The calculated difference is compared with the preset electricity consumption difference value to determine if the calculated difference is greater than the preset value. If it is greater, it indicates a significant increase in power generation is needed. In this case, increasing power generation through peak-shaving units in traditional power plants might have a substantial environmental impact, and the construction of new renewable energy power plants should be considered. The optimization mode is then set to power plant optimization, and the difference between total electricity consumption and total power generation is output as a prompt to add a new renewable energy power plant, indicating the need for distributed optimization of renewable energy power plants within the planned area. Conversely, if the calculated difference is less than or equal to the preset electricity consumption difference value, it indicates a small increase in power generation is needed, and power generation can be increased through peak-shaving units in traditional power plants. A prompt to add or activate peak-shaving units for power generation is then output.

[0089] Furthermore, if the comparison determines that the total electricity consumption is less than the total electricity generation, it indicates that there is a surplus of electricity generation in the planned area within the preset time period. In this case, the surplus electricity generation needs to be stored. Therefore, the optimization mode is determined to be energy storage power station optimization. Based on the electricity generation curve, the capacity of multiple energy storage power stations used for energy storage at various new energy power plants in the planned area is determined. By setting the capacity of the energy storage power stations to match the surplus electricity generation, the accurate storage of the surplus electricity generation is achieved, realizing the distributed optimization of energy storage power stations.

[0090] S40. If the optimization mode is energy storage power station optimization, then determine the capacity of multiple energy storage power stations used for energy storage of each new energy power generation station in the area to be planned, and perform distributed optimization of the energy storage power stations in the area to be planned according to the capacity of each station.

[0091] Furthermore, after determining the optimization mode as energy storage power station optimization, and needing to plan the capacity and geographical location of energy storage power stations, the remaining power generation in the planned area within a preset time period is determined through the power generation relationship curve. Based on the size of the remaining amount, the capacity of the energy storage power stations used for storing the remaining power from the new energy power generation plants is determined. Then, using the determined capacity sizes, each energy storage power station is planned to accurately store the remaining power, achieving distributed optimization of energy storage power stations within the planned area. Specifically, determining the capacity sizes of multiple energy storage power stations used for storing energy from each new energy power generation plant within the planned area includes:

[0092] S41. Identify the maximum value of the difference in the power quantity relationship curve, and determine the total capacity of the multiple energy storage power stations based on the maximum value of the difference;

[0093] S42. Generate a power generation percentage from each of the first power generation data, and divide the total capacity into storage capacity corresponding to each of the new energy power generation stations according to the power generation percentage.

[0094] S43. Based on the storage capacity to be stored, determine the energy storage capacity of the energy storage power station corresponding to each of the new energy power generation stations, and obtain the capacity loss value corresponding to each of the energy storage capacities to correct each of the energy storage capacities, thereby obtaining the capacity size of the energy storage power station corresponding to each of the new energy power generation stations.

[0095] Furthermore, multiple vertical axis differences are generated based on the horizontal axis coordinates of the power generation curve and the power consumption curve in the power quantity relationship curve. Each vertical axis difference reflects the difference between power generation and power consumption at a certain moment. Then, the differences are compared among the differences to determine the maximum difference. The maximum difference reflects the maximum remaining power that needs to be stored, so it can be used as the total storage capacity required by all energy storage power stations.

[0096] Furthermore, the total power generation originates from the sum of all new energy power generation stations, and the remaining power also originates from each new energy power generation station. To store the remaining power from each new energy power generation station nearby, this embodiment includes a mechanism for storage based on power generation ratio. Specifically, each first power generation data point is generated as a power generation ratio, that is, each first power generation data point is generated as its own total power generation. This can be achieved using the integration method described above, reflecting the individual power generation of each new energy power station. Then, the ratio of each individual power generation to the total power generation is used to obtain the proportion of each new energy power generation station's power generation in the total power generation, i.e., generating the power generation ratio. Then, according to the power generation ratio, the total capacity is divided accordingly, forming storage capacity for each new energy power generation station corresponding to its respective ratio. For example, among the five new energy power plants in the planned area, the power generation of each plant accounts for 30%, 20%, 10%, 25%, and 15% of the total power generation in the preset time period. Therefore, each new energy power plant can be equipped with its own energy storage station, and the storage capacity of each energy storage station accounts for 30%, 20%, 10%, 25%, and 15% of the total capacity, respectively.

[0097] Furthermore, after determining the storage capacity of each energy storage station, the storage capacity can be multiplied by the total capacity to obtain the storage capacity of each energy storage station corresponding to each new energy power generation station. Considering that energy losses may occur during the energy storage process, including but not limited to battery charging losses, energy storage and discharging losses, and power conversion system losses, and that these losses vary with different storage capacities, the energy loss corresponding to each storage capacity is obtained as a capacity loss value for each storage capacity. This capacity loss value is then used to correct each storage capacity, resulting in the appropriate capacity size for each new energy power generation station. This corrected capacity size, taking into account energy losses, is larger than the uncorrected capacity, allowing for matching with the remaining energy of the new energy power generation station and achieving effective storage of surplus energy.

[0098] This implementation of a distributed optimization method for new energy power plants and energy storage power stations involves predicting the first power generation data of new energy power plants within a pre-set time period in the planning area, and predicting the second power generation data of traditional power plants within the same pre-set time period. It also predicts the electricity consumption data of the planning area within the pre-set time period. Based on the predicted first power generation data, second power generation data, and electricity consumption data, an electricity consumption relationship curve is generated. Then, the optimization mode for the new energy power plants is determined based on the electricity consumption relationship curve. If the determined optimization mode is power plant optimization, it indicates that the planning of new energy power plants within the planning area is unreasonable, and therefore, distributed optimization is performed on these new energy power plants. If the determined optimization mode is energy storage power station optimization, it indicates that the energy storage power stations within the planning area need to be optimized. This determines the capacity of multiple energy storage power stations used for energy storage at each new energy power plant within the planning area, and based on this capacity, distributed optimization is performed on the energy storage power stations within the planning area. The power generation curve illustrates the relationship between total power generation and power consumption, achieved through the combination of traditional and new energy sources. This allows for the identification of optimization models, including distributed optimization of new energy power plants and distributed optimization of energy storage stations used to store energy at these plants. Power plant optimization addresses the issue of insufficient total power generation. Energy storage station optimization determines the appropriate capacity to accurately match the remaining power beyond consumption, enabling precise storage of surplus energy and minimizing energy wastage. Furthermore, the location of energy storage stations is determined by considering the environmental impact of noise pollution, thus minimizing significant noise pollution.

[0099] Further, see Figure 2 Based on the first embodiment of the distributed optimization method for new energy power generation stations and energy storage power stations of the present invention, a second embodiment of the distributed optimization method for new energy power generation stations and energy storage power stations of the present invention is proposed.

[0100] The second embodiment of the distributed optimization method for new energy power plants and energy storage power stations differs from the first embodiment in that the new energy power plants are wind power plants, and the predicted first power generation data of each new energy power plant in the planned area within a preset time period includes:

[0101] S11. Obtain historical wind direction data, historical wind speed data, historical air density data, and historical wind power generation hours for each wind power generation station within multiple historical time periods corresponding to a preset time period;

[0102] S12. Based on the historical wind direction data and the historical wind speed data, predict the average effective wind speed of the wind power station within the preset time period, and the effective duration corresponding to the average effective wind speed, and predict the number of wind power generation hours based on the effective duration and the historical wind power generation hours.

[0103] S13. Based on the historical air density data, predict the average air density of the wind power plant during the preset time period, and find the wind turbine parameters, prediction correction coefficient and first-year attenuation coefficient of the wind power plant.

[0104] S14. Based on the first annual attenuation coefficient, average effective wind speed, average air density, wind power generation hours, prediction correction coefficient, and the wind turbine parameters including blade length, wind energy utilization coefficient, blade area, blade angle of attack, and generator angular velocity, calculate the first power generation data of the wind power generation station during the preset period.

[0105] In this embodiment, the preferred new energy power generation station is a wind power generation station. For a wind power generation station, its power generation within a preset time period is mainly related to factors such as wind speed, wind direction, and the parameters of the wind turbines themselves. Specifically, the time periods corresponding to the preset time period are taken as historical time periods. For each wind power generation station, historical wind direction data, historical wind speed data, historical air density data, and historical wind power generation hours are acquired within multiple historical time periods. These historical wind direction data, historical wind speed data, historical air density data, and historical wind power generation hours from the same historical time period are then grouped into a data set. Based on the historical wind direction data and historical wind speed data in each data set, the average effective wind speed of the new energy power generation station within the preset time period is predicted. The average effective wind speed is the wind speed that can be used for wind turbine power generation. It can be predicted by analyzing the wind direction and wind speed change patterns reflected in historical wind direction and wind speed data from multiple historical periods. Then, based on the wind speed and wind direction at each time, the effective wind speed that can be used for power generation at each time can be predicted. Finally, the average effective wind speed within the preset time period can be obtained by averaging the effective wind speeds. At the same time, the durations corresponding to each effective wind speed are accumulated to obtain the effective duration corresponding to the average effective wind speed.

[0106] Furthermore, based on the historical wind power generation hours reflected in each data group, the number of power generation hours within a preset time period is predicted. This predicted number of power generation hours is then corrected using the effective duration to obtain the final number of wind power generation hours. During correction, it is determined whether the predicted number of power generation hours exceeds a reasonable range of the effective duration. If it does, it indicates that the power generation time based on the average effective wind speed is insufficient to reach the required number of power generation hours, and therefore the number of power generation hours is reduced. If it does not exceed a reasonable range, the number of power generation hours is taken as the actual number of wind power generation hours. The reasonable range can be preset through analysis and set to a value, and the amount of reduction in power generation hours can also be preset through analysis to correspond to the set value.

[0107] Furthermore, the power generation of wind power plants is also related to air density. The historical air density data in each data group is the average air density in each historical period. By observing the air density change patterns in each historical period as reflected in the historical air density data, the average air density for the preset period can be predicted.

[0108] Understandably, as wind power plants generate electricity, their performance degrades, leading to a decrease in power generation. This influencing factor can be determined in advance through testing and used as the first-year degradation coefficient. Simultaneously, the predicted wind power generation hours may differ from the actual average effective wind speed, affecting the accuracy of power generation predictions. To address this, a prediction correction coefficient can be generated based on the difference between predicted and actual data from previous years. For example, if the predicted average effective wind speed for 2023 is A based on historical wind direction and speed data, but the actual average effective wind speed is B, then the prediction correction coefficient can be B / A. Furthermore, another correction coefficient can be generated by combining the difference between the predicted and actual wind power generation hours. The two correction coefficients are then averaged to obtain the final prediction correction coefficient.

[0109] Furthermore, the power generation of a wind power plant is also related to the wind turbine parameters of the plant itself. These parameters include at least the blade length, wind energy utilization coefficient, blade area, and blade angle of attack. By finding these wind turbine parameters, prediction correction coefficients, and first-year attenuation coefficients for the new energy power plant, and then combining them with the predicted average effective wind speed, average air density, and wind power generation hours, the first power generation data of the new energy power plant within a preset time period can be calculated. The specific calculation formula is as follows:

[0110]

[0111] In the formula, Q1 represents the first power generation data; N represents the number of wind power generation hours; n1 represents the number of wind power generation stations; n2 represents the number of wind turbines in the wind power generation station; and r1 represents the first annual degradation coefficient. A represents the wind energy utilization factor of the j-th wind turbine in the i-th wind power station; ρ represents the average air density; A ij B represents the blade area of ​​the j-th wind turbine in the i-th wind power station; ij L represents the blade angle of attack of the j-th wind turbine in the i-th wind power station; ij V represents the blade length of the j-th wind turbine in the i-th wind power station; V represents the average effective wind speed; ω ij τ represents the generator angular velocity of the j-th wind turbine in the i-th wind power station; τ represents the prediction correction coefficient. Used to calculate the motor torque of the j-th wind turbine in the i-th wind power station.

[0112] This embodiment predicts the effective wind speed, air density, and power generation hours for a preset time period based on past wind speed, wind direction, air density, and power generation hours of a wind power plant. It also considers the prediction errors, combined with the parameters of the wind power plant itself, and the attenuation factors that occur as the wind power plant ages, to calculate the first power generation data of the wind power plant within the preset time period. This comprehensive consideration of the factors affecting the power generation of the wind generator makes the calculation of the first power generation data more accurate.

[0113] Further, see Figure 3 Based on the first and second embodiments of the distributed optimization method for new energy power plants and energy storage power stations of the present invention, a third embodiment of the distributed optimization method for new energy power plants and energy storage power stations of the present invention is proposed.

[0114] The third embodiment of the distributed optimization method for new energy power plants and energy storage power stations differs from the first and second embodiments in that the new energy power plants are photovoltaic power plants, and the predicted power generation data of each new energy power plant in the planned area within a preset time period includes:

[0115] S15. Obtain historical solar temperature data and historical solar intensity data of the photovoltaic power station in multiple historical time periods corresponding to the preset time period, and predict the solar temperature data and solar intensity data of the photovoltaic power station in the preset time period based on each of the historical solar temperature data and each of the historical solar intensity data.

[0116] S16. Fit the light temperature data and light intensity data to a temperature time function and an intensity time function within a preset time period, respectively, and generate the light intensity data as the average light intensity within the preset time period;

[0117] S17. Find the second annual attenuation coefficient, hourly reference output power, and temperature coefficient corresponding to the photovoltaic power generation station, as well as the hourly reference irradiance and hourly reference temperature corresponding to the hourly reference output power;

[0118] S18. Based on the second-year attenuation coefficient, hourly reference output power, temperature coefficient, hourly reference illuminance, hourly reference temperature, and the average illuminance, temperature-time function, and intensity-time function, calculate the first power generation data of the photovoltaic power station within a preset time period.

[0119] In this embodiment, the new energy power generation station is preferably a photovoltaic power generation station. For a photovoltaic power generation station, its power generation within a preset time period is mainly related to factors such as solar radiation temperature and solar radiation intensity. Specifically, the time periods corresponding to the preset time period in the past are taken as historical time periods corresponding to the preset time period. For each photovoltaic power generation station, historical solar radiation temperature data and historical solar radiation intensity data within multiple historical time periods are acquired, and historical solar radiation temperature data and historical solar radiation intensity data from the same historical time period are formed into a data group. Then, based on the solar radiation temperature change pattern reflected in the historical solar radiation temperature data in each data group within each historical time period, the solar radiation temperature data for the preset time period is predicted; and based on the solar radiation intensity change pattern reflected in the historical solar radiation intensity data in each data group within each historical time period, the solar radiation intensity data for the preset time period is predicted.

[0120] Furthermore, the predicted light temperature and light intensity data have a time attribute, representing the light temperature and intensity at a certain time within a preset time period. Preferably, the time is set to hours, representing the light temperature and light intensity per hour within each day of the preset time period. During prediction, historical light temperature data for each historical time period are generated into hourly average light temperatures according to their respective year, month, day, and hour. Then, based on the light temperature variation patterns reflected by the average light temperatures of the same hour on the same day across multiple historical years, the light temperature for that hour on that day within the preset time period is predicted. Similarly, historical light intensity data for each historical time period are generated into hourly average light intensities according to their respective year, month, day, and hour. And based on the light intensity variation patterns reflected by the average light intensities of the same hour on the same day across multiple historical years, the light intensity for that hour on that day within the preset time period is predicted. After obtaining the hourly light temperature and light intensity within each day of the preset time period, the light temperature and light intensity data for the preset time period are obtained.

[0121] Furthermore, a two-dimensional coordinate system is established, with the horizontal axis representing time in hours, and the vertical axis representing light temperature and light intensity. Light temperature data and light intensity data are added to the two-dimensional coordinate system in chronological order by day and hour. Then, the light temperature and light intensity data in the two-dimensional coordinate system are fitted to form temperature-time functions and intensity-time functions for a preset time period, reflecting the changes in light temperature and light intensity over time. Simultaneously, the light intensity data is averaged to generate the average light intensity for a preset time period, reflecting the average daily light intensity within that preset time period.

[0122] Furthermore, to accurately predict the power generation of photovoltaic power plants, a pre-set hourly reference output power for wind power plants is also included. This hourly reference output power is obtained through a one-hour test under specific light intensity and temperature conditions, representing the one-hour power output of the photovoltaic power plant at that specific light intensity and temperature. In addition, considering that different materials are used for the photovoltaic panels in the photovoltaic power plant, and that these materials have different physical properties resulting in different rates of temperature change, thus affecting power generation, this influencing factor is analyzed and determined in advance and used as a temperature coefficient. Moreover, considering that the performance of the photovoltaic power plant will degrade as it generates electricity, leading to a decrease in power generation, this influencing factor is determined in advance through testing and used as a second-year degradation coefficient.

[0123] Furthermore, the hourly reference output power, temperature coefficient, and second-year degradation coefficient are located, along with the illuminance and temperature that generated the hourly reference output power as the hourly reference illuminance and temperature. These are then combined with the average illuminance, temperature-time function, and intensity-time function to calculate the first power generation data of the photovoltaic power plant within a preset time period. The specific calculation formula is as follows:

[0124]

[0125] In the formula, Q2 represents the first power generation data; k represents the temperature coefficient; r2 represents the second annual decay coefficient; G represents the average solar intensity within the preset time period; G0 represents the hourly reference solar intensity; P0 represents the hourly reference output power; g(t) represents the intensity time function; θ(t) represents the temperature time function; θ0 represents the hourly reference temperature. Used to calculate the light intensity coefficient within a preset time period.

[0126] This embodiment aims to fit the predicted irradiance temperature and intensity within a preset time period of a photovoltaic power generation station into a temperature-time function and an intensity-time function in hourly units. It also sets an hourly reference output power, combines the hourly reference irradiance and hourly reference temperature to generate the hourly reference output power, and considers factors such as the degradation of the photovoltaic power generation station over the years and the temperature coefficient related to the physical properties of the photovoltaic panel materials. The embodiment calculates the first power generation data of the photovoltaic power generation station within the preset time period, comprehensively considering the factors affecting the power generation of the photovoltaic generator, and further subdividing the calculation into hourly units, making the calculation of the first power generation data more accurate.

[0127] Further, see Figure 4 Based on the first, second, and third embodiments of the distributed optimization method for new energy power plants and energy storage power stations of the present invention, a fourth embodiment of the distributed optimization method for new energy power plants and energy storage power stations of the present invention is proposed.

[0128] The fourth embodiment of the distributed optimization method for new energy power plants and energy storage power stations differs from the first, second, and third embodiments in that the distributed optimization of energy storage power stations within the planned area based on their respective capacities includes:

[0129] S44. Determine whether the environmental parameters of the environment where each new energy power generation station is located include water source parameters. If water source parameters are included, determine the energy storage power station corresponding to the new energy power generation station as a pumped storage power station, and obtain the water source location corresponding to the water source parameters as the location information of the pumped storage power station.

[0130] S45. If the environmental parameters do not include water source parameters, then obtain the energy storage noise data corresponding to the capacity of the energy storage power station, and determine the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data.

[0131] S46. Use the location information and the capacity as optimization parameters for the energy storage power station, and perform distributed optimization on the energy storage power station based on the optimization parameters.

[0132] Furthermore, in this embodiment, the energy storage power station used for energy storage at each new energy power plant within the planned area can be either pumped hydro storage or electrochemical energy storage. After determining the capacity of each energy storage power station, environmental parameters of the environment where each new energy power plant is located are acquired, including information on whether a water source is present. Then, the environmental parameters of each new energy power plant are identified one by one to determine whether a water source parameter is included. If a water source parameter is included, it indicates that a water source exists within a preset range around the new energy power plant, thus identifying the energy storage power station corresponding to that new energy power plant as a pumped hydro storage power station. In addition, the location of the water source is acquired as the location information of the energy storage power station, indicating that the energy storage power station used for energy storage at that new energy power plant can be built at that location.

[0133] Furthermore, if it is determined that the environmental parameters do not include water source parameters, it indicates that there is no water source within the preset range around the new energy power station. In this case, an electrochemical energy storage power station needs to be constructed to store energy for the new energy power generation station. To facilitate energy storage, the energy storage power station and the new energy power generation station are usually built in relatively close locations. However, both the energy storage power station and the new energy power station generate noise during operation. If they are close together, the combined noise may have a significant impact on the environment. Therefore, to avoid significant noise impact, the location of the energy storage power station needs to be determined based on noise levels.

[0134] Furthermore, considering the varying construction scales and noise levels of energy storage power stations with different capacities, simulation experiments are conducted beforehand to determine the noise levels generated by different capacity sizes, as well as the variation in noise levels based on distance from the noise source. This establishes a correspondence between capacity ranges, noise level ranges, and their variations. For new energy power plants that do not include water source parameters, the capacity of their corresponding energy storage power station is compared with this correspondence to determine the capacity range. Then, based on the corresponding noise level range within that capacity range, the noise level and its variation are determined. This noise level and its variation are combined to form energy storage noise data, which is used to determine the location information of the energy storage power station corresponding to the new energy power plant. The determined noise level can be either the median or the maximum value of the noise level range. The determined location information and capacity are then combined to form optimization parameters for the energy storage power station. These optimization parameters can be output as prompts to facilitate distributed optimization of the energy storage power station.

[0135] Specifically, determining the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data includes:

[0136] S451. Obtain the power generation noise data corresponding to the energy storage noise data in each of the new energy power generation stations, and determine the initial location information of the energy storage power station;

[0137] S452. Based on the initial location information, the energy storage noise data and the power generation noise data are superimposed to generate a superimposed value that varies with distance.

[0138] S453. Determine the maximum value among the superimposed values ​​that change with distance, and determine whether the maximum value is less than or equal to a preset threshold. If it is less than or equal to the preset threshold, then determine the initial position information as the position information.

[0139] If the maximum value is greater than a preset threshold, the initial position information is adjusted, and based on the adjusted initial position information, the step of superimposing the volume of the energy storage noise data and the power generation noise data is performed.

[0140] Furthermore, the energy storage noise data originates from energy storage power stations that store electrical energy from a specific renewable energy power plant, establishing a corresponding relationship between the energy storage noise data and that renewable energy power plant. The renewable energy power plant is located from among various renewable energy power plants, and its power generation noise data is obtained. This power generation noise data includes not only the magnitude of the noise generated by the renewable energy power plant's operation but also the relationship between the noise magnitude and the distance from the noise source, thus belonging to the power generation noise data corresponding to the energy storage noise data.

[0141] Furthermore, based on the noise levels in the energy storage noise data and the noise levels in the power generation noise data, the initial location information of the energy storage power station is determined. Specifically, a mapping relationship between noise levels and initial location distance is pre-established. The noise levels of the two are added together, and the sum is compared with the mapping relationship to determine the initial location distance corresponding to the sum. Then, based on the distance between the new energy power generation station and this initial location, the location area of ​​the energy storage power station is determined as the initial location information.

[0142] Furthermore, based on the distance between the location area indicated by the initial location information and the location area of ​​the new energy power generation station, the noise levels in the energy storage noise data and the power generation noise data are superimposed to obtain a superposition value that varies with distance. For example, if the distance determined by the initial location information is S, and there are two locations W1 and W2 at this distance, the noise level in the energy storage noise data varies with distance, and the magnitudes at locations W1 and W2 are p1 and p2, respectively. The noise level in the power generation noise data varies with distance, and the magnitudes at locations W1 and W2 are p3 and p4, respectively. Then, the superposition value superimposed on W1 is p1+p3, and the superposition value superimposed on W2 is p2+p4.

[0143] Furthermore, the various superimposed values ​​are compared to determine the maximum value, which represents the maximum noise level obtained by superimposing the energy storage noise data and the power generation noise data. A preset threshold representing the noise level is pre-set. The determined maximum value is compared with this preset threshold to determine if the maximum value is less than or equal to the preset threshold. If it is less than or equal to the preset threshold, it indicates that the noise generated by the superposition of the energy storage power station and the new energy power station is relatively small, and the energy storage power station can be set up at the initial location. Therefore, the initial location information is determined as the location information. Conversely, if the maximum value is determined to be greater than the preset threshold, it indicates that the noise generated by the superposition of the energy storage power station and the new energy power station is relatively large, and the environmental impact is significant. At this time, the initial location information is adjusted. After adjustment, the volume of the energy storage noise data and the power generation noise data is superimposed again, and the maximum value is compared with the preset threshold to determine if the maximum value is less than or equal to the preset threshold. If it is less than or equal to the preset threshold, it indicates that the adjusted initial location information meets the environmental requirements, and it is used as the location information. If the maximum value determined after adjustment is still greater than the preset threshold, the initial location information needs to be adjusted again until the maximum value determined after adjustment is less than or equal to the preset threshold to ensure that the environmental impact is minimal.

[0144] This embodiment targets energy storage power stations. When there is a water source around the new energy power generation station, the energy storage power station is set up as a pumped storage power station. When there is no water source around the new energy power station, the location of the energy storage power station is determined by combining the environmental impact of the noise generated by the energy storage power station and the environmental impact of the noise generated by the new energy power generation station, so as to ensure that the set-up energy storage power station will not increase the environmental burden.

[0145] See Figure 5 The present invention also provides a distributed optimization system for new energy power plants and energy storage power stations. This system is applied to the aforementioned distributed optimization method for new energy power plants and energy storage power stations. The system includes:

[0146] The power generation data acquisition module is used to predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period.

[0147] The power consumption curve generation module is used to predict the power consumption data of the area to be planned within a preset time period, and generate a power consumption curve based on the first power generation data, the second power generation data, and the power consumption data.

[0148] The distributed optimization mode determination module is used to determine the optimization mode of the new energy power generation station based on the power quantity relationship curve. If the optimization mode is power generation station optimization, it outputs a prompt message to perform distributed optimization on the new energy power generation station in the area to be planned. If the optimization mode is energy storage station optimization, it determines the capacity of multiple energy storage stations used for energy storage at each new energy power generation station in the area to be planned, and performs distributed optimization on the energy storage stations in the area to be planned based on the capacity of each station.

[0149] The specific implementation of the distributed optimization system for new energy power plants and energy storage power stations of the present invention is basically the same as the embodiments of the distributed optimization method for new energy power plants and energy storage power stations described above, and will not be repeated here.

[0150] See Figure 6 The present invention also provides a distributed optimization device for new energy power generation stations and energy storage power stations, including a memory and a processor;

[0151] The memory is used to store computer program code and transmit the computer program code to the processor;

[0152] The processor is used to execute the aforementioned distributed optimization method for new energy power generation stations and energy storage power stations according to the instructions in the computer program code.

[0153] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned distributed optimization method for new energy power generation stations and energy storage power stations.

[0154] Generally, the computer instructions for implementing the method of the present invention can be carried on any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable medium except for the signal itself, which is temporarily propagating.

[0155] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EKROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0156] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. In particular, Python, suitable for neural network computation, and platform frameworks such as TensorFlow and PyTorch can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer or to an external computer (e.g., via the Internet using an Internet service provider) through any type of network, including a local area network (LAN) or a wide area network (WAN).

[0157] For details regarding the aforementioned equipment and non-transitory computer-readable storage media, please refer to the specific description of a distributed optimization method for a new energy power generation station and an energy storage power station and its beneficial effects, which will not be repeated here.

[0158] Although embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A distributed optimization method for new energy power plants and energy storage power stations, characterized in that, include: Predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period; Predict the electricity consumption data of the area to be planned within a preset time period, and generate an electricity consumption relationship curve based on each of the first power generation data, each of the second power generation data, and the electricity consumption data; Based on the power generation curve, the optimization mode of the new energy power generation station is determined. If the optimization mode is power generation station optimization, a prompt message is output to perform distributed optimization of the new energy power generation stations in the area to be planned. The prompt message is information used to prompt the construction of new energy power generation stations, which is formed by the difference between the total power generation and the total power consumption determined by the power generation curve. If the optimization mode is energy storage power station optimization, then the capacity of multiple energy storage power stations used for energy storage of each new energy power generation station in the area to be planned is determined, and distributed optimization of the energy storage power stations in the area to be planned is carried out according to the capacity of each one. The step of performing distributed optimization of energy storage power stations within the planned area based on the capacity of each station includes: Determine whether the environmental parameters of the environment where each new energy power generation station is located include water source parameters. If water source parameters are included, then the energy storage power station corresponding to the new energy power generation station is determined as a pumped storage power station, and the location of the water source corresponding to the water source parameters is obtained as the location information for constructing the pumped storage power station. The location information and the capacity size are used as optimization parameters for the energy storage power station, and the optimization parameters are output as prompt information to perform distributed optimization of the energy storage power station based on the optimization parameters.

2. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The new energy power generation station is a wind power generation station, and the predicted power generation data of each new energy power generation station in the planned area within a preset time period includes: For each wind power plant, acquire historical wind direction data, historical wind speed data, historical air density data, and historical wind power generation hours within multiple historical time periods corresponding to a preset time period; Based on the historical wind direction data and the historical wind speed data, the average effective wind speed of the wind power station within the preset time period is predicted, as well as the effective duration corresponding to the average effective wind speed. Based on the effective duration and the historical wind power generation hours, the number of wind power generation hours is predicted. The average air density of the wind power plant during the preset time period is predicted based on the historical air density data, and the wind turbine parameters, prediction correction coefficient, and first-year attenuation coefficient of the wind power plant are found. Based on the first-year attenuation coefficient, average effective wind speed, average air density, wind power generation hours, prediction correction coefficient, and the wind turbine parameters including blade length, wind energy utilization coefficient, blade area, blade angle of attack, and generator angular velocity, the first power generation data of the wind power station in the preset period is calculated using the following formula: ； In the formula, This indicates the first power generation data; Indicates the number of hours of wind power generation; Indicates the number of wind power generation stations; This indicates the number of wind turbines in a wind power plant. This represents the decay coefficient for the first year; Indicates the first The first of the wind power generation stations The wind energy utilization coefficient of each wind turbine; Indicates average air density; Indicates the first The first of the wind power generation stations The blade area of ​​a single wind turbine; Indicates the first The first of the wind power generation stations The angle of attack of the blades of a wind turbine; Indicates the first The first of the wind power generation stations The blade length of each fan; Indicates the average effective wind speed; Indicates the first The first of the wind power generation stations The angular velocity of the generator in the wind turbine; This represents the prediction correction factor; Used to calculate the The first of the wind power generation stations The motor torque of each fan.

3. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The new energy power generation station is a photovoltaic power generation station, and the predicted power generation data of each new energy power generation station in the planned area within a preset time period includes: The system acquires historical solar temperature data and historical solar intensity data of the photovoltaic power plant within multiple historical time periods corresponding to a preset time period, and predicts the solar temperature data and solar intensity data of the photovoltaic power plant during the preset time period based on each of the historical solar temperature data and historical solar intensity data. The light temperature data and light intensity data are respectively fitted into a temperature time function and an intensity time function within a preset time period, and the light intensity data is generated as the average light intensity within the preset time period; Find the second-year degradation coefficient, hourly reference output power, and temperature coefficient corresponding to the photovoltaic power generation station, as well as the hourly reference irradiance and hourly reference temperature corresponding to the hourly reference output power; Based on the aforementioned second-year attenuation coefficient, hourly reference output power, temperature coefficient, hourly reference illuminance, hourly reference temperature, and the aforementioned average illuminance, temperature-time function, and intensity-time function, the first power generation data of the photovoltaic power station within a preset time period is calculated using the following formula: ； In the formula, This indicates the first power generation data; Indicates the temperature coefficient; This indicates the decay coefficient for the second year; This represents the average light intensity within a preset time period; Indicates the hourly reference illuminance; Indicates the hourly reference output power; Indicates the intensity-time function; Represents a temperature-time function; Indicates the hourly reference temperature; Used to calculate the light intensity coefficient within a preset time period.

4. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The prediction of electricity consumption data for the area to be planned within a preset time period includes: Obtain historical electricity consumption data of the area to be planned in multiple historical time periods corresponding to the preset time period, as well as population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters for each historical time period; Generate a historical array for each historical period from the historical electricity consumption data, population data, population change parameters, weather data, weather change parameters, primary industry data, primary industry change parameters, secondary industry data, secondary industry change parameters, tertiary industry data, and tertiary industry change parameters. Based on a preset prediction model, historical data for each historical period are analyzed and calculated to obtain electricity consumption data for the area to be planned within the preset period. The formula used for analysis and calculation in the preset prediction model is as follows: ； In the formula, This represents electricity consumption data; This indicates that the output layer in the preset prediction model is related to the first... Connection weights between hidden layers; This indicates the number of hidden layers in the preset prediction model; This indicates that the input layer and the first layer in the preset prediction model are related. Connection weights between hidden layers; Indicates the first A historical array; Indicates the number of historical arrays; Indicates the first Hidden layer model parameters; This represents the output layer model parameters.

5. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The determination of the capacity of multiple energy storage power stations used for energy storage at various new energy power plants within the planned area includes: Identify the maximum difference in the power quantity relationship curve, and determine the total capacity of the multiple energy storage power stations based on the maximum difference; Each of the first power generation data is generated as a power generation percentage, and the total capacity is divided into storage capacities corresponding to each of the new energy power generation stations based on the power generation percentages. Based on the storage capacity to be stored, determine the energy storage capacity of the energy storage power station corresponding to each of the new energy power generation stations, and obtain the capacity loss value corresponding to each of the energy storage capacities to correct each of the energy storage capacities, thereby obtaining the capacity size of the energy storage power station corresponding to each of the new energy power generation stations.

6. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The step of determining whether the environmental parameters of the environment where each of the new energy power generation stations is located include water source parameters is followed by: If the environmental parameters do not include water source parameters, then obtain the energy storage noise data corresponding to the capacity of the energy storage power station, and determine the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data. The location information and the capacity size are used as optimization parameters for the energy storage power station, and the optimization parameters are output as prompt information to perform distributed optimization of the energy storage power station based on the optimization parameters.

7. The distributed optimization method for new energy power plants and energy storage power stations according to claim 6, characterized in that, The step of determining the location information of the energy storage power station corresponding to the new energy power generation station based on the energy storage noise data includes: Obtain the power generation noise data corresponding to the energy storage noise data in each of the new energy power generation stations, and determine the initial location information of the energy storage power station; Based on the initial location information, the energy storage noise data and the power generation noise data are superimposed to generate a superimposed value that varies with distance; Determine the maximum value among the superimposed values ​​that change with distance, and determine whether the maximum value is less than or equal to a preset threshold. If it is less than or equal to the preset threshold, then determine the initial position information as the position information. If the maximum value is greater than a preset threshold, the initial position information is adjusted, and based on the adjusted initial position information, the step of superimposing the volume of the energy storage noise data and the power generation noise data is performed.

8. The distributed optimization method for new energy power plants and energy storage power stations according to claim 1, characterized in that, The step of determining the optimization mode of the new energy power generation station based on the power volume relationship curve includes: Based on the power generation curve, determine the total power generation and total power consumption of the area to be planned within a preset time period, and determine the relationship between the total power consumption and the total power generation. If the relationship is that the total electricity consumption is greater than the total power generation, then it is determined whether the difference between the total electricity consumption and the total power generation is greater than a preset electricity consumption difference. If it is greater than the preset electricity consumption difference, then the optimization mode is determined to be power plant optimization. If the total electricity consumption is less than the total power generation, then the optimization mode is determined as energy storage power station optimization.

9. A distributed optimization system for new energy power generation stations and energy storage power stations, characterized in that, The system is applied to the method according to any one of claims 1-8, the system comprising: The power generation data acquisition module is used to predict the first power generation data of each new energy power plant in the planned area within a preset time period, and the second power generation data of each traditional power plant in the planned area within a preset time period. The power consumption curve generation module is used to predict the power consumption data of the area to be planned within a preset time period, and generate a power consumption curve based on the first power generation data, the second power generation data, and the power consumption data. The distributed optimization mode determination module is used to determine the optimization mode of the new energy power generation station based on the power quantity relationship curve. If the optimization mode is power generation station optimization, it outputs a prompt message to perform distributed optimization on the new energy power generation station in the area to be planned. If the optimization mode is energy storage station optimization, it determines the capacity of multiple energy storage stations used for energy storage at each new energy power generation station in the area to be planned, and performs distributed optimization on the energy storage stations in the area to be planned based on the capacity of each station.

10. A distributed optimization device for new energy power generation stations and energy storage power stations, characterized in that, Including memory and processor; The memory is used to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method as described in any one of claims 1 to 8 according to instructions in the computer program code.

Images