City-level new energy microgrid planning decision support system based on multi-objective optimization

Abstract

The invention relates to the technical field of energy planning, in particular to a city-level new energy microgrid planning decision support system based on multi-objective optimization, which comprises a data collection unit used for collecting local real-time new energy data and synchronous meteorological data, the new energy data comprising generating capacity data and supply quantity data; the analysis and prediction unit is used for analyzing and identifying a complementary mode of two kinds of new energy including wind energy and solar energy according to the preprocessed new energy data; and the multi-objective optimization unit is used for establishing an energy efficiency maximization objective function and an environmental influence minimization objective function, and searching an optimal solution between two conflicting objectives of energy efficiency maximization and environmental influence minimization based on the identified complementary mode of the wind energy and the solar energy. The system can reasonably distribute the use proportion of two energy sources, so that the overall system performance is optimized, renewable energy sources can be utilized to the maximum extent through complementary scheduling, and the overall reliability and stability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy planning, and more specifically, to an urban-level new energy microgrid planning decision support system based on multi-objective optimization. Background Art

[0002] With the continuous growth of global energy demand and the improvement of environmental protection awareness, the planning and construction of urban-level new energy microgrids have become increasingly important. The new energy microgrid integrates various renewable energy sources such as wind energy and solar energy, combined with energy storage systems, aiming to provide reliable, efficient, and environmentally friendly energy supply. However, traditional optimization methods face many challenges in dealing with such complex systems. The new energy microgrid needs to integrate multiple energy sources (such as wind energy, solar energy, energy storage, etc.) to achieve efficient collaborative work. This involves complex system integration and control problems. Traditional optimization methods may be difficult to handle this system complexity, especially when it comes to the coordination and optimization of multiple subsystems (such as power generation, energy storage, power distribution, etc.). At the same time, wind energy and solar energy have natural complementarity, but in traditional optimization methods, this complementarity is often not fully considered. The lack of effective utilization of complementarity will lead to the volatility and instability of energy supply, affecting the overall performance of the system. For example, in some periods, the wind is strong while the sunlight is weak, and in other periods, the situation may be reversed. Traditional optimization methods may not be able to fully utilize this complementarity, resulting in large fluctuations in energy supply. Therefore, an urban-level new energy microgrid planning decision support system based on multi-objective optimization is designed. Summary of the Invention

[0003] The purpose of the present invention is to provide an urban-level new energy microgrid planning decision support system based on multi-objective optimization to solve the problem that the complementarity is often not fully considered in the above background art, and the lack of effective utilization of complementarity will lead to the volatility and instability of energy supply, affecting the overall performance of the system.

[0004] To achieve the above object, the present invention aims to provide an urban-level new energy microgrid planning decision support system based on multi-objective optimization, including: A data collection unit, which is used to collect historical meteorological data and new energy data, and establish a real-time monitoring module to collect local real-time new energy data and synchronized meteorological data. The new energy data includes power generation data and supply data, and preprocesses the new energy data and the synchronized meteorological data, and displays the preprocessed new energy data in real time; wherein, the new energy includes wind energy and solar energy; An analysis and prediction unit, which is used to analyze and identify the complementary patterns of the two new energy sources of wind energy and solar energy according to the preprocessed new energy data, and predict the new energy power generation and supply based on the historical new energy data; A multi-objective optimization unit, which is used to establish an objective function for maximizing energy efficiency and an objective function for minimizing environmental impact, and to find an optimal solution between two conflicting objectives of maximizing energy efficiency and minimizing environmental impact based on the identified complementary pattern of wind energy and solar energy; A coordination and management unit, which is used to formulate a scheduling strategy according to the selected optimal solution, and determine the energy types to be preferentially used and the usage proportion of each energy type in different time periods.

[0005] As a further improvement of this technical solution, in the analysis and prediction unit (2), the specific steps for identifying the complementary pattern of wind energy and solar energy are as follows: S21. Obtain the time series data of the power generation data and supply data of wind energy and solar energy, and select the time lag value; S22. According to each time lag value, calculate the time lag cross-correlation between the wind energy and solar energy power generations, and introduce the geographical location for optimization in the process of calculating the time lag cross-correlation between the wind energy and solar energy power generations, find out the phase difference and correlation intensity between the wind energy and solar energy, and then identify the complementary pattern of the wind energy and solar energy; S23. Set labels for the identified complementary pattern, use an independent data set to verify the accuracy and stability of the identified complementary pattern, and conduct a sensitivity analysis to evaluate the influence of different factors on the complementary pattern.

[0006] As a further improvement of this technical solution, the specific content of S22 is as follows: ; Among them, is the time lag correlation between the wind energy and solar energy power generations; is the number of data points; is the time lag value; is the wind energy power generation at time point ; is the average value of the wind energy power generation; is the solar energy power generation at time point ; is the average value of the solar energy power generation; Find corresponding to the maximum value of , that is, , then the correlation intensity is .

[0007] As a further improvement of this technical solution, in S22, when calculating the time lag cross-correlation between the wind energy and solar energy power generations, the geographical location is introduced for optimization, and the specific content after optimization is: ; Among them, is the geographical weight factor; is the temperature-based weight factor; is the weight coefficient of the temperature-based weight factor; is the humidity-based weight factor; is the weight coefficient of the humidity-based weight factor; is the cloud cover-based weight factor; is the weight coefficient of the cloud cover-based weight factor; ; Among them, is the time-lag correlation between the optimized wind energy and solar energy power generation.

[0008] As a further improvement of this technical solution, in S23, tags are set for the identified complementary patterns, specifically as follows: According to and values, set the tags of the complementary patterns. If , it means that the wind energy reaches the peak before the solar energy; if , it means that the solar energy reaches the peak before the wind energy; if is close to 0, it means that there is no significant correlation between the two.

[0009] As a further improvement of this technical solution, in the analysis and prediction unit (2), predicting the new energy power generation and supply includes predicting the short-term power generation and supply, predicting the medium-term power generation and supply, and predicting the long-term power generation and supply.

[0010] As a further improvement of this technical solution, the specific steps of the multi-objective optimization unit (3) are as follows: S31. Define the objective function for maximizing energy efficiency and the objective function for minimizing environmental impact, generate a composite function, introduce a complementary factor for optimization in the composite function, set corresponding constraint conditions, and generate an adaptive weight according to the current system state and meteorological state, so as to adjust the weights of the two objective functions; S32. Randomly generate initial individuals, and each individual represents an energy configuration scheme; S33. Use the genetic algorithm to simulate the natural selection process, and at the same time use the particle swarm optimization to imitate the flight behavior of bird flocks. Individuals update their positions in the search space according to their own experience and the group experience, and combine the global search ability of the genetic algorithm and the local search efficiency of the particle swarm optimization to search for the optimal solution; S34. Calculate the energy efficiency and environmental impact corresponding to each individual, obtain the comprehensive score by combining the adaptive weights in S31, and then use the Pareto front to evaluate the non-dominated solution set; S35. Repeat the steps of S33 until the maximum number of iterations is reached and stop. Select the optimal solution from the final Pareto front.

[0011] As a further improvement of this technical solution, the constraint conditions in S31 include that the energy supply meets the demand, the maximum installed capacity of different energy types, the maximum storage and release capacity of the energy storage system, and physical and technical limitations.

[0012] As a further improvement of this technical solution, in S31, the generation of the composite function is specifically as follows: ; Among them, is the composite objective function; is the importance weight of energy efficiency; is the cost coefficient of wind power generation; is within the time period the predicted power generation of wind energy; is within the time period the proportion of wind energy used; is the cost coefficient of solar power generation; is within the time period the predicted power generation of solar energy; is within the time period the proportion of solar energy used; is the importance weight of environmental impact; is the environmental impact coefficient of wind power generation; is the environmental impact coefficient of solar power generation.

[0013] As a further improvement of this technical solution, in S31, a complementary factor is introduced into the composite function for optimization. After optimization, it is specifically: ; Among them, is the complementary factor; ; Among them, is the optimized composite objective function, is the weight of the complementary factor.

[0014] Compared with the prior art, the beneficial effects of the present invention: 1. In the urban - level new - energy micro - grid planning decision - making support system based on multi - objective optimization, identifying the complementary patterns of wind energy and solar energy helps to formulate more effective scheduling strategies. Complementary scheduling can maximize the utilization of renewable energy, reduce the dependence on traditional fossil - fuel power generation, improve the overall reliability and stability of the system. It not only smooths the power generation curve but also enhances the flexibility and response speed of the system, strengthening the stability and resilience of the power grid.

[0015] 2. In the urban - level new - energy micro - grid planning decision - making support system based on multi - objective optimization, introducing complementary factors into the objective function can better utilize the complementarity between wind energy and solar energy, improving the stability and reliability of the system. During the time periods when the power generation of wind energy and solar energy varies greatly, it can reasonably allocate the usage ratios of the two types of energy, thereby optimizing the overall system performance. Brief Description of the Drawings

[0016] Figure 1 is the overall flow chart of the present invention; The meanings of each label in the figure are as follows: 1. Data collection unit; 2. Analysis and prediction unit; 3. Multi - objective optimization unit; 4. Coordination and management unit. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0018] Please refer to Figure 1 As shown, a decision - making support system for urban - level new - energy micro - grid planning based on multi - objective optimization is provided, including a data collection unit 1, an analysis and prediction unit 2, a multi - objective optimization unit 3, and a coordination and management unit 4; Among them, the data collection unit 1 is used to collect historical meteorological data and new - energy data, and establish a real - time monitoring module to collect local real - time new - energy data and synchronized meteorological data. The new - energy data includes power generation data and supply data, and pre - processes the new - energy data and the synchronized meteorological data, and displays the pre - processed new - energy data in real time; among them, the new energy includes wind energy and solar energy; The analysis and prediction unit 2 is used to analyze and identify the complementary patterns of the two new - energy sources, wind energy and solar energy, based on the pre - processed new - energy data, and predict the new - energy power generation and supply based on historical new - energy data. In the analysis and prediction unit 2, the specific steps for identifying the complementary patterns of wind energy and solar energy are as follows: S21. Obtain the time series data of the power generation data and supply data of wind energy and solar energy, and select the time lag value; S22. According to each time lag value, calculate the time lag cross-correlation between the wind energy and solar energy power generations, and introduce the geographical location for optimization during the calculation of the time lag cross-correlation between the wind energy and solar energy power generations, find out the phase difference and correlation strength between the wind energy and solar energy, and then identify the complementary mode of the wind energy and solar energy; S22 is specifically as follows: ; Wherein, is the time lag correlation between the wind energy and solar energy power generations; is the number of data points, that is, the length of the time series; is the time lag value, indicating the time offset between the wind energy power generation and the solar energy power generation ; is the wind energy power generation at the time point ; is the average value of the wind energy power generation; is the solar energy power generation at the time point ; is the average value of the solar energy power generation; Find the corresponding to the maximum value of , that is , then the correlation strength is , and the range is between . Close to 1 indicates strong positive correlation, close to -1 indicates strong negative correlation, and close to 0 indicates no correlation; Since the wind energy and solar energy resources are distributed differently in different regions. For example, in some regions, the wind may be stronger at night, while in other regions, the wind may be stronger during the day. These geographical differences will affect the results of the time lag correlation. At the same time, the terrain (such as mountains, oceans, plains, etc.) will affect the wind and light conditions, and the complex terrain may lead to local changes in the wind and light, thus affecting the correlation calculation. Therefore, in S22, the geographical location is introduced for optimization during the calculation of the time lag cross-correlation between the wind energy and solar energy power generations. After optimization, it is specifically: ; Wherein, is the geographical weight factor, used to reflect the influence of different geographical locations; is the weight factor based on temperature; is the weight coefficient of the weight factor based on temperature; is the weight factor based on humidity; is the weight coefficient of the humidity-based weight factor; is the cloud cover-based weight factor; is the weight coefficient of the cloud cover-based weight factor; Among them, the impact of temperature on wind power generation is relatively small. However, in some cases, temperature changes can affect atmospheric pressure and wind speed. High temperatures may cause a decrease in air density, thereby slightly reducing the efficiency of wind power generation. However, both too high and too low temperatures can affect the efficiency of solar panels. Most solar panels experience a decrease in efficiency when the temperature rises because high temperatures increase the internal resistance of the panels, thereby reducing the output power; ; among them, is the temperature at time point ; is the optimum temperature (e.g., 25°C); is the standard deviation of temperature, controlling the width of the distribution; The impact of humidity on wind power generation is small. However, in a high-humidity environment, moisture in the air may increase the weight of the blades, affecting the performance of wind turbines; high humidity may cause water droplets to condense on the surface of solar panels, affecting the light transmittance and thus reducing the power generation efficiency. In addition, high humidity may also cause corrosion of the panels; ; among them, is the humidity at time point ; and are the minimum and maximum suitable values of humidity (e.g., 30% and 70%); The impact of cloud cover on wind power generation is small. However, changes in cloud cover may indirectly affect atmospheric pressure and wind speed; cloud cover directly affects the solar radiation intensity, and thus affects the solar power generation. The more clouds there are, the weaker the solar radiation and the lower the power generation efficiency.

[0019] ; among them, is the cloud cover at time point (e.g., 0 means no clouds, 1 means completely covered by clouds); is a small constant (e.g., 1e-6) used to avoid division by zero errors.

[0020] The formula comprehensively considers various climate factors such as temperature, humidity, and cloud cover, rather than a single factor. This makes the weight factor more comprehensive and accurate, and can more realistically reflect the changes in wind and solar power generation under different climate conditions. Since climate conditions are dynamically changing, by calculating the weight factor in real time, the identification of the complementary mode can be dynamically adjusted to improve the adaptability and accuracy of the system.

[0021] ; Among them, is the time-lag correlation between the optimized wind energy and solar energy generation; Identifying the complementary patterns of wind energy and solar energy helps to formulate more effective scheduling strategies. For example, at night when the wind is strong and solar radiation is weak, wind energy generation is preferentially used; during the day when sunlight is sufficient, solar energy generation is preferentially used. This complementary scheduling can maximize the utilization of renewable energy, reduce the dependence on traditional fossil fuel power generation, and improve the overall reliability and stability of the system; Identifying the complementary patterns helps to optimize the planning and management of energy storage systems. When wind energy and solar energy generation are in excess, the excess energy can be stored in the energy storage system; when generation is insufficient, the energy in the energy storage system is released to meet the demand. This not only smooths the generation curve, but also improves the flexibility and response speed of the system, enhancing the stability and resilience of the power grid; In multi-objective optimization, the identification results of complementary patterns can be used as one of the important constraint conditions to help the system simultaneously optimize multiple objectives such as environmental impact and energy efficiency. Through multi-objective optimization, the best solution that balances multiple objectives can be found, promoting the sustainable development of the city.

[0022] S23. Set labels for the identified complementary patterns, verify the accuracy and stability of the identified complementary patterns using an independent dataset, and conduct sensitivity analysis to evaluate the impact of different factors (such as weather conditions, seasonal changes) on the complementary patterns; In S23, set labels for the identified complementary patterns as follows: According to and values, set the labels of the complementary patterns. If , it means that wind energy reaches its peak before solar energy, and it is marked as "wind before sun". In this mode, wind energy reaches its peak at night or in the early morning, while solar energy reaches its peak during the day. Wind energy generation can be preferentially used at night, and solar energy generation can be used during the day; if , it means that solar energy reaches its peak before wind energy, and it is marked as "sun before wind". In this mode, solar energy reaches its peak during the day, while wind energy reaches its peak at night or in the evening. Solar energy generation can be preferentially used during the day, and wind energy generation can be used at night; if is close to 0, indicating that there is no significant correlation between the two, and it is marked as "no significant complementarity". In this mode, there is no significant correlation between wind energy and solar energy. The respective generation characteristics and scheduling strategies need to be considered separately, and more energy storage support may be required to smooth the generation curve; Clear complementary mode tags contribute to formulating more effective scheduling strategies, optimizing the utilization of wind energy and solar energy, improving the overall efficiency and stability of the system, enabling more reasonable planning of the use of energy storage systems, smoothing the power generation curve, and enhancing the flexibility and response speed of the system.

[0023] In the analysis and prediction unit 2, predicting the new energy power generation and supply includes predicting the short-term power generation and supply, predicting the medium-term power generation and supply, and predicting the long-term power generation and supply.

[0024] The multi-objective optimization unit 3 is used to establish the objective function of maximizing energy efficiency and the objective function of minimizing environmental impact, and based on the identified complementary mode of wind energy and solar energy, find the optimal solution between the two conflicting objectives of maximizing energy efficiency and minimizing environmental impact; The specific steps of the multi-objective optimization unit 3 are as follows: S31. Define the objective function of maximizing energy efficiency and the objective function of minimizing environmental impact, generate a composite function, introduce a complementary factor for optimization in the composite function, set the corresponding constraint conditions, and generate an adaptive weight according to the current system state and meteorological state, so as to adjust the weights of the two objective functions; The constraint conditions in S31 include that the energy supply meets the demand, the maximum installed capacity of different energy types, the maximum storage and release capacity of the energy storage system, and physical and technical limitations; Supply-demand balance ensures that the total power generation plus the charge and discharge of the energy storage system can meet the demand, avoiding energy shortage or surplus; the maximum installed capacity ensures that the wind energy and solar energy power generation do not exceed the maximum installed capacity, avoiding equipment overload; the maximum storage and release capacity of the energy storage system: ensures that the charge and discharge of the energy storage system are within the allowable range, avoiding damage to the energy storage equipment.

[0025] In S31, the generation of the composite function is specifically as follows: ; Among them, is the composite objective function; is the importance weight of energy efficiency; is the cost coefficient of wind power generation; is within the time period the predicted power generation of wind energy; is within the time period the proportion of wind energy used; is the cost coefficient of solar power generation; is within the time period the predicted power generation of solar energy; is within the time period the proportion of solar energy used; is the importance weight of environmental impact; is the environmental impact coefficient of wind power generation; is the environmental impact coefficient of solar power generation; In S31, a complementary factor is introduced into the composite function for optimization. After optimization, it is specifically: ; Among them, is the complementary factor; ; Among them, is the optimized composite objective function, is the weight of the complementary factor; By introducing the complementary factor , the complementarity between wind energy and solar energy can be better utilized, and the stability and reliability of the system can be improved; the complementary factor helps to more reasonably allocate the usage ratio of the two energy sources during the time period when the power generation of wind energy and solar energy varies greatly, thereby optimizing the overall system performance; through the weight , the importance of the complementary factor in the optimization process can be adjusted according to the actual situation.

[0026] S32. Randomly generate initial individuals, and each individual represents an energy configuration plan, including the quantity of each energy type, the configuration of the energy storage system, etc.; S33. Use the genetic algorithm to simulate the natural selection process, and at the same time use the particle swarm optimization to imitate the flight behavior of bird flocks. The individuals update their positions in the search space according to their own experience and the group experience, and search for the optimal solution by combining the global search ability of the genetic algorithm and the local search efficiency of the particle swarm optimization. First, use GA for rough search to find the potential area, and then apply PSO for refined search. First, determine the general energy distribution strategy at the macroscopic level, and then optimize the specific parameter settings of individual devices at the microscopic level; S34. Calculate the energy efficiency and environmental impact corresponding to each individual, obtain the comprehensive score by combining the adaptive weight in S31, and then use the Pareto front to evaluate the non-dominated solution set; Although the comprehensive score can help simplify the multi-objective problem and convert it into a single-objective problem, doing so may lose some information because there may be trade-offs between different objectives. The Pareto front method retains these trade-off relationships and provides a more comprehensive perspective. The comprehensive score can be used as an auxiliary means to help understand and compare the solutions on the Pareto front. The comprehensive score obtained by combining the adaptive weight can provide a simplified numerical reference for decision-makers, but the final decision often needs to consider the diverse options provided by the Pareto front. The Pareto front shows all feasible non-dominated solutions, and decision-makers can select the most suitable solution according to specific needs and preferences.

[0027] S35. Repeat the steps of S33 until the maximum number of iterations is reached and stop, and select the optimal solution from the final Pareto front; Finally, the coordination management unit 4 determines the energy types to be preferentially used and the proportion of each energy type used in different time periods according to the selected optimal solution braking scheduling strategy.

[0028] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A city-level new energy microgrid planning decision support system based on multi-objective optimization, characterized by: include: A data collection unit (1), the data collection unit (1) is used to collect historical meteorological data and new energy data, and establish a real-time monitoring module to collect local real-time new energy data and synchronized meteorological data, the new energy data including power generation data and supply data, and pre-process the new energy data and synchronized meteorological data, and display the pre-processed new energy data in real time; wherein the new energy includes wind energy and solar energy; An analysis and prediction unit (2), the analysis and prediction unit (2) being used to analyze and identify the complementary mode of wind energy and solar energy based on the pre-processed new energy data, and to predict the power generation and supply of new energy based on historical new energy data; A multi-objective optimization unit (3), wherein the multi-objective optimization unit (3) is used to establish an objective function of maximizing energy efficiency and an objective function of minimizing environmental impact, and to find an optimal solution between the two conflicting objectives of maximizing energy efficiency and minimizing environmental impact based on the identified complementary mode of wind energy and solar energy; A coordination management unit (4) is used to determine the energy types to be used preferentially in different time periods and the proportion of each energy type to be used according to the selected optimal solution and braking scheduling strategy.

2. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 1 is characterized by: In the analysis and prediction unit (2), the complementary mode of wind energy and solar energy is identified, and the specific steps are as follows: S21, obtaining time series data of wind power and solar power generation data and supply data, and selecting a time lag value; S22. Calculate the time lag cross correlation between wind power and solar power generation according to each time lag value, introduce the geographical location for optimization in the process of calculating the time lag cross correlation between wind power and solar power generation, find out the phase difference and correlation intensity between wind power and solar power, and then identify the complementary mode of wind power and solar power; S23. Set labels for the identified complementary patterns, use independent data sets to verify the accuracy and stability of the identified complementary patterns, and conduct sensitivity analysis to evaluate the impact of different factors on the complementary patterns.

3. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 2 is characterized in that: The S22 is specifically as follows: ; in, is the time-lagged correlation between wind and solar power generation; is the number of data points; is the time lag value; For at time point of wind power generation; is the mean value of wind power generation; For at time point of solar power generation; is the mean value of solar power generation; turn up The maximum value corresponding to ,Right now , then the correlation strength is .

4. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 3 is characterized by: In S22, the geographical location is introduced to optimize the process of calculating the time-lagged cross-correlation between wind power and solar power generation, and the optimization is as follows: ； in, is the geographic weight factor; is the weight factor based on temperature; is the weight coefficient of the temperature-based weight factor; is the weighting factor based on humidity; is the weight coefficient of the weight factor based on humidity; is the weight factor based on cloud cover; is the weight coefficient of the weight factor based on cloud cover; ; in, Time-lagged correlation between optimized wind and solar power generation.

5. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 4 is characterized by: In S23, a label is set for the identified complementary mode, specifically as follows: according to and The value of sets the complementary mode label. If , indicating that wind energy reaches its peak before solar energy; if , indicating that solar energy reaches its peak before wind energy; if A value close to 0 indicates that there is no significant correlation between the two.

6. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 5 is characterized by: In the analysis and prediction unit (2), predicting the amount of power generation and supply of new energy includes predicting short-term power generation and supply, predicting medium-term power generation and supply, and predicting long-term power generation and supply.

7. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 6 is characterized in that: The multi-objective optimization unit (3) has the following specific steps: S31. Define an objective function for maximizing energy efficiency and an objective function for minimizing environmental impact, generate a composite function, introduce complementary factors into the composite function for optimization, set corresponding constraints, and generate adaptive weights according to the current system state and meteorological state, so as to adjust the weights of the two objective functions; S32, randomly generate initial individuals, each individual represents an energy configuration scheme; S33, using genetic algorithm to simulate the natural selection process, and using particle swarm optimization to imitate the flight behavior of bird flocks. Individuals update their positions in the search space based on their own experience and group experience, and combine the global search capability of genetic algorithm and the local search efficiency of particle swarm optimization to search for the optimal solution; S34, calculate the energy efficiency and environmental impact corresponding to each individual, combine the adaptive weights in S31 to obtain a comprehensive score, and then use the Pareto frontier to evaluate the non-dominated solution set; S35. Repeat step S33 until the maximum number of iterations is reached and then select the optimal solution from the final Pareto frontier.

8. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 7 is characterized by: The constraints in S31 include energy supply meeting demand, maximum installed capacity of different energy types, maximum storage and release capacity of energy storage system, and physical and technical limitations.

9. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 8 is characterized by: In S31, the composite function is generated as follows: ； in, is the composite objective function; is the importance weight of energy efficiency; is the cost coefficient of wind power generation; For the time period The predicted electricity generation from internal wind energy; For the time period The proportion of internal wind energy used; is the cost coefficient of solar power generation; For the time period The predicted electricity generation from solar energy in the interior; For the time period The proportion of solar energy used in the interior; weighting of the importance of environmental impacts; is the environmental impact factor of wind power generation; is the environmental impact coefficient of solar power generation.

10. The city-level new energy microgrid planning decision support system based on multi-objective optimization according to claim 9 is characterized in that: In S31, a complementary factor is introduced into the composite function for optimization, and the optimization is as follows: ； in, is a complementary factor; ; in, is the optimized composite objective function, is the weight of the complementary factor.

Images