Design method of wind and light storage micro-grid system

Abstract

The invention relates to the technical field of micro-grid design, in particular to a design method of a wind and light storage micro-grid system, which comprises the following steps: setting the installed capacity of a distributed photovoltaic module and a wind driven generator and the capacity of a storage battery; wherein the maximum electricity demand of the target area is determined, and the installed capacity and the storage battery capacity are determined; minimizing the total cost of the system or maximizing the reliability of the system is used as a target function; setting constraint conditions; solving an optimal solution of the target function under the constraint condition based on an optimization algorithm, and adjusting the installed capacity and the storage battery capacity; and configuring a monitoring module, training to generate a deep neural network model so as to predict the generating capacity of the distributed photovoltaic module and the wind driven generator, and adjusting the charging and discharging strategy of the storage battery according to the predicted generating capacity and the real-time power demand. According to the method, the power demand of the target area is accurately predicted, so that the installed capacity of the distributed photovoltaic module and the wind driven generator is reasonably configured, and energy waste is reduced.

Description

Technical Field

[0001] The present application relates to the field of microgrid technology, and more specifically, to a design method for a wind, solar and energy storage microgrid system. Background Art

[0002] As global climate change intensifies and extreme weather events occur frequently, old transmission lines in many areas face severe challenges, especially in remote areas such as mountainous areas. The lines in these areas are seriously aged and prone to failures when encountering severe weather, resulting in frequent power outages, which seriously affects the quality of life and power safety of residents. In addition, due to the remote geographical location, repairing line failures is not only time-consuming but also costly, which puts tremendous pressure on the operation of power companies. These problems also often lead to a large number of repair reports, opinions and complaint work orders, increasing the service burden of power companies.

[0003] Traditionally, the renovation of these old lines often adopts the method of adding spare lines or strengthening existing lines, but this not only requires a large amount of capital investment, but is also difficult to implement in some areas with complex terrain or harsh natural conditions. In addition, even if the renovation is completed, the maintenance cost of these lines is still high and the return on investment is low.

[0004] The invention patent with the authorization announcement number CN112636334B discloses a solar-based microgrid system. It includes a solar power generation subsystem, a controlled power generation subsystem and a central control device, and the central control device includes N edge computing terminals. The solar power generation subsystem is composed of M solar photovoltaic conversion devices. Although this solution can improve the stability of power supply to a certain extent, it mainly relies on solar energy and cannot provide sufficient power support for areas with poor sunshine conditions (especially mountainous areas with frequent cloudy or rainy weather).

[0005] Therefore, there is an urgent need for a cost-effective, easy-to-deploy solution that can effectively deal with power outages under severe weather conditions. Especially for those "hollow villages" with sparse populations and scattered residences, there is an urgent need for a microgrid system that can operate independently and reduce dependence on external power grids to ensure that residents' basic living electricity needs are met. Summary of the invention

[0006] In view of this, the present application provides a design method for a wind, solar and energy storage microgrid system to provide a basis for setting up the wind, solar and energy storage microgrid system according to the predicted power generation and real-time power demand, thereby solving the above-mentioned technical problems.

[0007] This application provides the following technical solutions:

[0008] A design method for a wind-solar-storage microgrid system, comprising:

[0009] S1. Based on historical electricity consumption data, set the installed capacity and battery capacity of distributed photovoltaic modules and wind turbines; including collecting historical electricity consumption data and environmental change information in the target area within a preset time period, determining the maximum electricity demand in the target area, and determining the installed capacity and battery capacity; minimizing the total system cost or maximizing the system reliability as the objective function; taking the maximum discharge depth of the battery and the maximum output power of the distributed photovoltaic modules and wind turbines as constraints; solving the optimal solution of the objective function under the constraints based on the optimization algorithm, and adjusting the installed capacity and battery capacity;

[0010] S2. Configure the monitoring module, use historical meteorological data and electricity consumption data as training samples, generate a deep neural network model, which is used to predict the power generation of distributed photovoltaic components and wind turbines based on weather forecast information, and adjust the battery charging and discharging strategy based on real-time electricity demand.

[0011] In one possible implementation, determining the maximum power demand of the target area in S1 includes:

[0012] Based on the collected historical electricity consumption data, determine the peak and average electricity consumption in the target area within a preset time period;

[0013] The maximum power demand of the target area is determined according to the power peak value, average value and environmental change information.

[0014] In one possible implementation, in S1, the installed capacity of the distributed photovoltaic components, the micro wind turbine and the battery capacity are at least 1.5 to 2 times the maximum power demand.

[0015] In one possible implementation, in S1, the constraints of the optimization algorithm include:

[0016] The maximum discharge depth of the battery does not exceed the preset threshold;

[0017] The maximum output power of the distributed photovoltaic modules shall not exceed the rated power of the distributed photovoltaic modules;

[0018] The maximum output power of a wind turbine shall not exceed the rated power of the wind turbine.

[0019] In one possible implementation, in S1, solving the optimal solution of the objective function under the constraints based on the optimization algorithm includes:

[0020] Determine the initial installed capacity and battery capacity of the wind, solar and storage microgrid system;

[0021] Simulate system operation status under different installed capacity and battery capacity;

[0022] Evaluate system cost or reliability based on simulation results;

[0023] Adjust the installed capacity and battery capacity to optimize the objective function.

[0024] In one possible implementation, in S1, the optimization algorithm is any one of linear programming, dynamic programming, genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm.

[0025] In one possible implementation, in S2, adjusting the charging and discharging strategy of the battery includes:

[0026] Determine the timing and rate of battery charging and discharging based on the predicted power generation and real-time power demand;

[0027] When the power generation forecast is higher than the real-time power demand, the monitoring module stores the excess power in the battery;

[0028] When the power generation forecast is lower than the real-time power demand, the monitoring module releases power from the battery to meet the power demand;

[0029] In one possible implementation, the monitoring module further includes a feedback submodule for adjusting the prediction accuracy of the deep neural network model according to actual power generation and real-time power demand.

[0030] In one possible implementation, the wind, solar and energy storage microgrid system also includes a grid-connected / off-grid switching module, which is used to send the excess electric energy generated by the distributed photovoltaic components and the wind turbine into the grid when the grid is operating normally, and switch to off-grid mode when the grid fails, and power the load with a battery.

[0031] In one possible implementation, the grid-connected / off-grid switching module is further provided with a monitoring and protection mechanism to prevent the switching process from causing impact on the grid or the load.

[0032] Compared with the prior art, the technical solution of this application has the following beneficial effects:

[0033] This application determines the electricity consumption pattern and environmental influencing factors by collecting and analyzing the past electricity consumption data and environmental change information of the target area. Based on historical data, the electricity demand in the future is predicted to provide a basis for the setting of installed capacity and battery capacity. Build an optimization model with the goal of minimizing costs or maximizing reliability, and set corresponding constraints. Use the optimization algorithm to solve the optimal solution and determine the optimal installed capacity and battery capacity configuration. Use historical meteorological and electricity consumption data to train deep neural network models to improve the accuracy of power generation forecasts. According to the predicted power generation and real-time power demand, dynamically adjust the battery charging and discharging strategy to ensure efficient operation of the system.

[0034] By analyzing historical electricity consumption data and environmental change information, the electricity demand of the target area can be accurately predicted, so as to reasonably configure the installed capacity of distributed photovoltaic components and wind turbines and reduce energy waste. The application of optimization algorithms can ensure that the installed capacity and battery capacity are minimized while meeting the maximum electricity demand, thereby reducing initial investment and operating costs. By setting constraints, such as the maximum discharge depth of the battery and the maximum output power of the power generation equipment, the stable operation of the system under various environmental conditions can be guaranteed. The introduction of deep neural network models can be trained based on historical meteorological data and electricity consumption data to improve the accuracy of the prediction of photovoltaic components and wind turbine power generation, thereby optimizing the battery charging and discharging strategy. Through real-time monitoring and prediction, the system can automatically adjust the charging and discharging strategy, improve the utilization rate of renewable energy, and reduce dependence on traditional energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0036] Figure 1 A schematic diagram of the structure of a wind-solar-storage microgrid system provided in Example 1 of the present application.

[0037] Figure 2 A flow chart of a design method for a wind-solar-storage microgrid system provided in Example 2 of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] Embodiment 1:

[0040] See also Figure 1 , is a schematic diagram of the structure of a wind-solar-storage microgrid system provided in Example 1 of the present application. The wind-solar-storage microgrid system is a highly integrated energy solution that combines solar energy, wind energy and energy storage technology to provide a stable and reliable power supply for remote areas or independent power needs. The system is designed with environmental factors, energy efficiency and economy in mind, and can adapt to different geographical and climatic conditions. Figure 1 As shown in the figure, the wind-solar-storage microgrid system includes a distributed photovoltaic component 1, a micro wind turbine 2, a battery 3, a monitoring module 4, and a grid-connected / off-grid switching module 5.

[0041] Distributed photovoltaic module 1: Distributed photovoltaic module 1 is the core part of the wind, solar and storage microgrid system. It consists of multiple photovoltaic panels that can convert sunlight into direct current. These panels can be optimized according to the light intensity and duration of the target area to maximize power generation efficiency. The design of photovoltaic modules needs to consider weather resistance, conversion efficiency and long-term stability.

[0042] Micro wind turbines 2: Micro wind turbines 2 use wind energy to generate electricity. They are usually small and suitable for deployment in areas with moderate wind speeds. The design of these generators needs to consider wind speed changes, mechanical strength and maintenance costs. Through proper layout, micro wind turbines can complement photovoltaic modules and increase the energy output of the entire system.

[0043] Severe weather such as strong winds and thunderstorms often occurs in summer, when the sunlight is strong and the photovoltaic battery group can generate sufficient electricity to meet daily needs. The peak period for forest fire prevention is mainly in spring and winter every year. Strong winds are mainly concentrated in spring and winter, which coincides with the peak period for forest fire prevention. This can make up for the poor light intensity during this period and greatly extend the operation time of off-grid islands.

[0044] Solar energy and wind energy show complementary effects in different time periods and seasons. Generally, the sun is strong and the wind is weak during the day, while the sun is weak and the wind is strong during cloudy days and nights. In summer, the sun is strong and the wind is weak, while in winter, the sun is weak and the wind is strong. This wind-solar complementary power generation system makes the system more continuous, stable and reliable, thus achieving a continuous and uninterrupted power supply for 365 days.

[0045] Battery 3, Battery 3 is a key part of energy storage, which can store the electricity generated by photovoltaic panels and wind turbines. These batteries need to have high energy density, long cycle life and fast charge and discharge capabilities. The capacity and type of battery will be selected according to the power demand and budget of the system.

[0046] The monitoring module 4 is specifically used to monitor the operating status of each component in real time through sensors and communication technology. The monitoring module 4 can not only display the current power generation, energy storage status and load demand, but also predict energy output, optimize charging and discharging strategies, and ensure that the system operates in the best state.

[0047] In addition, the monitoring module 4 is also used to dynamically adjust the output power of the photovoltaic and wind power generation systems and the charging and discharging strategies of the batteries through real-time or short-term weather forecast data. The photovoltaic and wind power generation is predicted by obtaining weather forecast information. The battery charging and discharging strategies are adjusted according to the predicted power generation and real-time power demand to optimize the working state of the energy storage system and ensure that the power demand can be met even under adverse weather conditions.

[0048] The grid-connected / off-grid switching module 5 is specifically used to send the excess electric energy generated by the distributed photovoltaic components 1 and the micro wind turbine 2 into the grid when the grid is operating normally, and switch to the off-grid mode when the grid fails to supply power to the load through the battery 3.

[0049] In addition, the grid-connected / off-grid switching module 5 is also provided with a monitoring and protection mechanism to avoid the switching process from causing impact on the grid or the load, thereby ensuring that the power supply to the load is not interrupted.

[0050] The embodiment of the present application installs distributed photovoltaic components 1 and micro wind turbines 2 in the target area to be configured for the microgrid, and connects them to the battery 3 through cables to form a complete power generation and energy storage system. According to the geographical environment and meteorological conditions of the target area, the installation location of the distributed photovoltaic components and micro wind turbines is reasonably selected to ensure that solar energy and wind energy can be obtained to the maximum extent. In addition, the microgrid system is integrated with a monitoring and control module, which can ensure real-time monitoring of power generation and remaining battery power, and automatically control the charge and discharge status of the battery according to actual conditions. A grid-connected / off-grid switching device is set to ensure that excess electric energy can be fed into the grid when the grid is operating normally, and can automatically switch to off-grid mode when the grid fails, and power the load with batteries.

[0051] Embodiment 2

[0052] See also Figure 2 , is a design method for a wind-solar-storage microgrid system provided in Example 2 of the present application. This embodiment provides a method for determining the capacity of distributed photovoltaic components, micro wind turbines, and batteries in a wind-solar-storage microgrid system. The capacity of the microgrid system is adjusted based on historical electricity demand and renewable energy generation forecasts to ensure that basic electricity demand can still be met under extreme weather conditions.

[0053] like Figure 2 As shown in , the specific implementation steps of the above method include:

[0054] S10, obtaining historical electricity consumption data and environmental change information within a preset time period in the target area where the microgrid is to be constructed.

[0055] Optionally, the preset time period can be set according to actual conditions, and can be three months, six months or one year of historical electricity consumption data, which is not specifically limited in the present embodiment. The present embodiment provides an accurate data basis for subsequent electricity demand analysis by collecting historical electricity consumption data and environmental change information of the target area.

[0056] S11. Determine the peak and average power consumption values ​​of the target area within a preset time period based on the historical power consumption data.

[0057] By analyzing historical power consumption data, the peak and average power consumption of the target area within a preset time period can be accurately determined, which is crucial for subsequent capacity adjustment. The determination of peak and average power consumption helps to more accurately predict the peak power consumption that may occur under extreme weather conditions, thereby ensuring that the microgrid system can provide stable power supply under various circumstances.

[0058] S12. Analyze the maximum power demand of the target area based on the peak power consumption, average power consumption and environmental change information.

[0059] By comprehensively analyzing the peak and average power consumption and environmental change information, the maximum power demand in the target area can be predicted more scientifically. This prediction method helps to reasonably configure the capacity of distributed photovoltaic components, micro wind turbines and batteries, ensuring that the basic power demand of residents can be met even under extreme weather conditions, and improving the stability and reliability of the microgrid system.

[0060] For example, the highest electricity consumption in a certain region is during the Spring Festival of a certain year, with a monthly electricity consumption of 828.81kWh and a daily average electricity consumption of 25.11kWh. According to the daily average electricity consumption and historical data, 98% of the daily electricity consumption in the region is less than 18kWh. Alternatively, after comparing the loads of a certain region for several consecutive days and different seasons, it can be seen that the maximum power consumption in summer is generally less than 3kW, and the maximum load in winter is less than 2.5kW.

[0061] S13. Based on the above maximum electricity demand, preliminarily determine the installed capacity and battery capacity of the distributed photovoltaic components 1 and the wind turbine generator set 2.

[0062] It should be noted that, in order to ensure that the power demand of users is met, the microgrid system is set at 1.5 to 2 times the above maximum power demand. For example, the capacity of the microgrid system is selected as:

[0063] 1. Photovoltaic battery pack capacity: 540W*10 is 5.4kW;

[0064] 2. Wind turbine capacity: 5KW;

[0065] 3. Battery capacity: 150Ah, 12V battery 12 groups of lead-acid colloid batteries are 21.6KWh;

[0066] 4. Off-grid inverter: 10kW (considering that the maximum load is 7kW throughout the year, in order to ensure that under special circumstances, the photovoltaic inverter can still support user electricity consumption for a short time and meet power requirements, the inverter capacity is selected to be 10kW).

[0067] A 50Ah*12 lead-acid gel battery can fully discharge 21.6KWh to meet the daily demand of 18kWh under 98% electricity consumption throughout the year. The average daily power generation of photovoltaic and wind turbines is 50KWh. The excess power can be connected to the grid, and ideally, it can be used in an off-grid island state in the region.

[0068] S14. Minimize the total system cost or maximize the system reliability as the objective function. Minimize the total system cost or maximize the system reliability as the objective function; set constraints, including the maximum discharge depth of the battery, the maximum output power of the distributed photovoltaic components and wind turbines.

[0069] Among them, the above constraints include that the maximum discharge depth of the battery does not exceed a preset threshold, the maximum output power of the distributed photovoltaic module does not exceed the rated power of the distributed photovoltaic module, and the maximum output power of the wind generator does not exceed the rated power of the wind generator.

[0070] S15. Solve the optimal solution of the objective function under the constraints based on the optimization algorithm, and adjust the installed capacity and battery capacity.

[0071] Specifically, it includes determining the initial installed capacity and battery capacity of the wind, solar and battery storage microgrid system. Simulating the system operation status under different installed capacity and battery capacity. Based on the simulation results, the system cost or reliability is evaluated, and the installed capacity and battery capacity are adjusted to optimize the objective function.

[0072] Optionally, the above optimization algorithm can be any one of linear programming, dynamic programming, genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm. The present application embodiment does not make specific limitations.

[0073] By implementing this technical solution, the economic efficiency and reliability of the wind, solar and storage microgrid system can be effectively improved, while ensuring that the system operates within a safe range. In addition, through reasonable parameter configuration and application of optimization algorithms, the best system configuration solution can be obtained under the constraints, thereby achieving the goal of effective resource utilization and energy conservation and emission reduction.

[0074] S2. Configure monitoring module 4.

[0075] S20. Build a deep neural network, use historical meteorological data and electricity consumption data as training samples, and train and generate a deep neural network model.

[0076] By using a deep neural network model to learn historical meteorological data and electricity consumption data, this application can more accurately predict electricity demand in the future and the power generation of distributed photovoltaic components and wind turbines, thereby improving the accuracy of energy supply and demand matching.

[0077] S21. Obtain weather forecast information, including but not limited to environmental information such as light intensity and wind speed in the target area.

[0078] S22. Predict the power generation of the distributed photovoltaic assembly 1 and the wind turbine 2 according to the above weather forecast information.

[0079] Based on the predicted power generation and real-time electricity demand, the system can dynamically adjust the battery charging and discharging strategy, effectively reducing the unstable power supply caused by weather changes and ensuring the continuity and reliability of power supply.

[0080] S23. Adjust the battery charging and discharging strategy according to the predicted power generation and real-time power demand to optimize the working state of the energy storage system and ensure that the power demand can be met even under adverse weather conditions.

[0081] Among them, adjusting the charging and discharging strategy of the battery specifically includes:

[0082] Determine the timing and rate of battery charging and discharging based on predicted power generation and real-time power demand.

[0083] When the power generation forecast is higher than the real-time power demand, the monitoring module stores the excess power in the battery.

[0084] When the power generation forecast is lower than the real-time power demand, the monitoring module releases power from the battery to meet the power demand.

[0085] Compared with the prior art, the second embodiment of the present application has the following beneficial effects:

[0086] This application determines the electricity consumption pattern and environmental influencing factors by collecting and analyzing the past electricity consumption data and environmental change information of the target area. Based on historical data, the electricity demand in the future is predicted to provide a basis for the setting of installed capacity and battery capacity. Build an optimization model with the goal of minimizing costs or maximizing reliability, and set corresponding constraints. Use the optimization algorithm to solve the optimal solution and determine the optimal installed capacity and battery capacity configuration. Use historical meteorological and electricity consumption data to train deep neural network models to improve the accuracy of power generation forecasts. According to the predicted power generation and real-time power demand, dynamically adjust the battery charging and discharging strategy to ensure efficient operation of the system.

[0087] By analyzing historical electricity consumption data and environmental change information, the electricity demand of the target area can be accurately predicted, so as to reasonably configure the installed capacity of distributed photovoltaic components and wind turbines and reduce energy waste. The application of optimization algorithms can ensure that the installed capacity and battery capacity are minimized while meeting the maximum electricity demand, thereby reducing initial investment and operating costs. By setting constraints, such as the maximum discharge depth of the battery and the maximum output power of the power generation equipment, the stable operation of the system under various environmental conditions can be guaranteed. The introduction of deep neural network models can be trained based on historical meteorological data and electricity consumption data to improve the accuracy of the prediction of photovoltaic components and wind turbine power generation, thereby optimizing the battery charging and discharging strategy. Through real-time monitoring and prediction, the system can automatically adjust the charging and discharging strategy, improve the utilization rate of renewable energy, and reduce dependence on traditional energy.

[0088] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0089] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0090] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A design method for a wind-solar-storage microgrid system, characterized in that: include: S1. Based on historical electricity consumption data, set the installed capacity and battery capacity of distributed photovoltaic modules and wind turbines; in It includes collecting historical electricity consumption data and environmental change information within a preset time period in the target area, determining the maximum electricity demand in the target area, and determining the installed capacity and battery capacity; minimizing the total system cost or maximizing the system reliability as the objective function; using the maximum discharge depth of the battery, the maximum output power of the distributed photovoltaic components and the wind turbine as the constraints; solving the optimal solution of the objective function under the constraints based on the optimization algorithm, and adjusting the installed capacity and battery capacity; S2. Configure the monitoring module, use historical meteorological data and electricity consumption data as training samples, generate a deep neural network model, which is used to predict the power generation of distributed photovoltaic components and wind turbines based on weather forecast information, and adjust the battery charging and discharging strategy based on real-time electricity demand.

2. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S1, the maximum electricity demand of the target area is determined, including: Based on the collected historical electricity consumption data, determine the peak and average electricity consumption in the target area within a preset time period; The maximum power demand of the target area is determined according to the power peak value, average value and environmental change information.

3. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S1, the installed capacity of the distributed photovoltaic components, the micro wind turbine and the battery capacity are at least 1.5 to 2 times the maximum power demand.

4. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S1, the constraints of the optimization algorithm include: The maximum discharge depth of the battery does not exceed the preset threshold; The maximum output power of the distributed photovoltaic modules shall not exceed the rated power of the distributed photovoltaic modules; The maximum output power of a wind turbine shall not exceed the rated power of the wind turbine.

5. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S1, the optimal solution of the objective function under the constraints is solved based on the optimization algorithm, including: Determine the initial installed capacity and battery capacity of the wind, solar and storage microgrid system; Simulate system operation status under different installed capacity and battery capacity; Evaluate system cost or reliability based on simulation results; Adjust the installed capacity and battery capacity to optimize the objective function.

6. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S1, the optimization algorithm is any one of linear programming, dynamic programming, genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm.

7. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: In S2, the battery charging and discharging strategy is adjusted including: Determine the timing and rate of battery charging and discharging based on the predicted power generation and real-time power demand; When the power generation forecast is higher than the real-time power demand, the monitoring module stores the excess power in the battery; When the power generation forecast is lower than the real-time power demand, the monitoring module releases power from the battery to meet the power demand.

8. The design method of a wind-solar-storage microgrid system according to claim 7 is characterized in that: The monitoring module also includes a feedback submodule for adjusting the prediction accuracy of the deep neural network model according to actual power generation and real-time power demand.

9. The design method of a wind-solar-storage microgrid system according to claim 1 is characterized in that: The wind, solar and energy storage microgrid system also includes a grid-connected / off-grid switching module, which is used to send the excess electric energy generated by the distributed photovoltaic components and the wind turbine into the grid when the grid is operating normally, and switch to an off-grid mode when the grid fails to supply power to the load through a battery.

10. A design method for a wind-solar-storage microgrid system according to claim 9, characterized in that: The grid-connected / off-grid switching module is also provided with a monitoring and protection mechanism to prevent the switching process from causing impact on the grid or load.

Images