A wind-solar-water multi-objective optimal scheduling method and device, a storage medium and a computer device

Abstract

The application discloses a wind-solar-water multi-objective optimization scheduling method and device, a storage medium and computer equipment, belongs to the field of renewable energy power system operation scheduling, and acquires wind-solar power prediction data, load demand prediction data, reservoir parameter data, basin hydrology and meteorology data and market electricity price data. A multi-objective function is constructed according to the wind-solar power prediction data, the load demand prediction data, the reservoir parameter data, the basin hydrology and meteorology data and the market electricity price data. A multi-objective optimization scheduling model is established based on the multi-objective function and a preset constraint condition set. The multi-objective optimization scheduling model is solved according to a non-dominated sorting genetic algorithm, and a Pareto front solution set is acquired. A compromise solution is selected from the Pareto front solution set based on a fitness function, and the compromise solution is used for wind-solar-water multi-objective optimization scheduling. The application effectively considers system operation in multiple aspects and effectively balances system economy and hydropower output stability.

Description

Technical Field

[0001] This application relates to the field of renewable energy power system operation and dispatch technology, specifically to a multi-objective optimization dispatch method, device, storage medium and computer equipment for wind, solar and hydropower. Background Technology

[0002] As the proportion of intermittent renewable energy sources such as wind and solar power in the power system continues to increase, the randomness and volatility of their output pose a severe challenge to the safe and stable operation of the power grid. Hydropower, with its flexible regulation and rapid response, can serve as an important means of regulating fluctuations in wind and solar power output. Therefore, constructing a multi-energy complementary system of wind, solar, and hydropower and achieving its optimized scheduling is crucial for improving the absorption capacity of new energy sources and ensuring the stable operation of the power grid.

[0003] Existing research on optimal scheduling of wind, solar, and hydropower mainly focuses on single economic objectives or deterministic models, making it difficult to simultaneously consider both system economics and the stability of hydropower operation. Furthermore, traditional multi-objective optimization algorithms suffer from slow convergence speed and uneven solution set distribution when solving high-dimensional, nonlinear, and multi-constraint scheduling models. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, storage medium, and computer equipment for multi-objective optimization scheduling of wind, solar, and water resources, so as to overcome the defects caused by the prior art.

[0005] To achieve the above objectives, this application employs the following technical solution:

[0006] In a first aspect, this application discloses a multi-objective optimization scheduling method for wind, solar, and water resources, characterized by comprising:

[0007] Acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data;

[0008] A multi-objective function is constructed based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data.

[0009] Based on the multi-objective function and a preset set of constraints, a multi-objective optimization scheduling model is established.

[0010] The multi-objective optimization scheduling model is solved using a non-dominated sorting genetic algorithm to obtain the Pareto front solution set;

[0011] A compromise solution is selected from the Pareto front solution set based on the fitness function, and the compromise solution is used for multi-objective optimization scheduling of wind, solar and water resources.

[0012] In a further embodiment of this application, the multi-objective function includes a first objective function, used to calculate the minimum comprehensive operating cost within the system scheduling cycle; the minimum comprehensive operating cost within the system scheduling cycle is calculated using the following formula;

[0013] ;

[0014] ;

[0015] in, This is a function for calculating the lowest overall operating cost within the system scheduling cycle. The lowest overall operating cost within the system scheduling cycle; The cost of generating hydropower; Cost of purchasing electricity from the grid; It is the cost of penalties for abandoning electricity; The penalty cost when wind power is wasted; It is the penalty cost when light generates wasted electricity; It is the maximum output of wind power during time period i; It is the maximum output of photovoltaic power during time period i; This is the actual output value of wind power during time period i; It is the actual output value of photovoltaic power during time period i.

[0016] In a further embodiment of this application, the multi-objective function includes a second objective function, used to calculate the minimum total output fluctuation of the cascade hydropower stations; the total output fluctuation of the cascade hydropower stations is calculated using the following formula;

[0017] ;

[0018] in, This is a function for calculating the minimum total output fluctuation of a cascade hydropower station; This represents the minimum total output fluctuation of the cascade hydropower stations; It refers to the number of hydroelectric power stations; Let i be the output of the nth hydropower station at time i. This represents the power output of the nth hydropower station at the previous moment.

[0019] A further aspect of this application involves selecting a compromise solution from the Pareto front solution set based on a fitness function. This compromise solution is used for multi-objective optimization scheduling of wind, solar, and water resources, including:

[0020] The fitness value of the Pareto optimal solution is calculated using the fitness function, and the minimum objective fitness among the Pareto optimal solutions is selected as the compromise solution for multi-objective optimization scheduling of wind, solar and water resources.

[0021] The fitness function formula is as follows;

[0022] ;

[0023] in This represents the j-th objective function value of the i-th Pareto optimal solution; The maximum value of the j-th objective function; and Let be the minimum value of the j-th objective function;

[0024] The optimal formula for calculating the fitness value of the objective function is as follows:

[0025] ;

[0026] Where N is the number of objective functions that need to be optimized.

[0027] A further aspect of this application, wherein solving the multi-objective optimization scheduling model using a non-dominated sorting genetic algorithm to obtain the Pareto front solution set includes:

[0028] Randomly generate a parent population P of size N. t The first generation of offspring populations of the same size are generated through rapid non-dominated sorting and genetic operations.

[0029] The parent and offspring generations are merged according to the elite strategy to form a mixed population of size 2N; the population is then subjected to rapid non-dominated sorting and divided into Pareto fronts of different levels according to the non-dominated relationship.

[0030] From low to high, add complete non-dominated layers to the new parent population P. t+1 Until a certain layer can no longer accommodate all individuals, the crowding distance comparison mechanism is used to select the best individuals to ensure that the population size is restored to N.

[0031] Genetic operations are performed on the new parent population to generate the next generation of offspring. The above sorting and selection process is repeated until the termination condition is met, at which point a Pareto front solution set is generated.

[0032] A further aspect of this application is that, based on the multi-objective function, the constraints are subject to a preset set of constraints, including...

[0033] Based on the system power balance constraints, the output power constraints of photovoltaic power plants and wind farms, the water balance constraints of hydropower stations, the reservoir capacity constraints of hydropower stations, the water level constraints of hydropower stations, and the discharge flow constraints of hydropower stations, the multi-objective function is constrained to construct and establish a multi-objective optimization scheduling model.

[0034] Secondly, this application discloses a multi-objective optimization scheduling device for wind, solar, and water resources, which includes...

[0035] The acquisition module is configured to acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data.

[0036] The first construction module is configured to construct a multi-objective function based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data;

[0037] The second construction module is configured to establish a multi-objective optimization scheduling model based on the multi-objective function and a preset set of constraints.

[0038] The computation module is configured to solve the multi-objective optimization scheduling model using a non-dominated sorting genetic algorithm to obtain a Pareto front solution set.

[0039] The confirmation module is configured to select a compromise solution from the Pareto front solution set based on the fitness function, the compromise solution being used for multi-objective optimization scheduling of wind, solar and water resources.

[0040] Thirdly, this application also discloses a computer-readable storage medium that stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method described in any one of claims 1 to 5.

[0041] Fourthly, this application also discloses a computer device comprising:

[0042] One or more processors and one or more memories, one or more programs stored in one or more memories and configured to be executed by one or more processors, the one or more programs including instructions for performing the methods described above.

[0043] The beneficial effects of this application are as follows:

[0044] This application constructs a multi-objective function based on survey data to provide a more comprehensive scheduling scheme from the perspective of system operation. By utilizing the NSGA-II algorithm and combining it with parallel computing technology, it can obtain a Pareto optimal solution set with uniform distribution and good convergence in a short time. This improves the convergence of the algorithm and the quality of the solution set, enabling rapid generation and rolling optimization of the scheduling plan, and effectively balancing system economy and the stability of hydropower output. Attached Figure Description

[0045] Figure 1 This is a flowchart of the multi-objective optimization scheduling method for wind, solar and water resources in the embodiments of this application;

[0046] Figure 2 This is a flowchart illustrating the execution of the NSGA-II algorithm in an embodiment of this application.

[0047] Figure 3 This is a diagram showing the Pareto optimal frontier solution results in the embodiments of this application;

[0048] Figure 4 This is a diagram showing the scheduling results for typical days in all four seasons in this application embodiment. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this application or its application or use.

[0050] Example 1

[0051] like Figure 1 As shown, this application discloses an embodiment of a multi-objective optimization scheduling method for wind, solar, and water resources based on the NSGA-II algorithm, which includes the following steps:

[0052] Acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data;

[0053] A multi-objective function is constructed based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data.

[0054] Based on a multi-objective function and a pre-set set of constraints, a multi-objective optimization scheduling model is established.

[0055] The Pareto front solution set is obtained by solving the multi-objective optimization scheduling model using a non-dominated sorting genetic algorithm.

[0056] A compromise solution is selected from the Pareto front solution set based on the fitness function, and the compromise solution is used for multi-objective optimization scheduling of wind, solar and water resources.

[0057] In some embodiments, a multi-objective optimization scheduling method for wind, solar and hydropower based on the NSGA-II algorithm is designed as follows;

[0058] Taking a wind-solar-hydro complementary system in a certain river basin, which includes four cascade hydropower stations, one wind farm, and one photovoltaic power station, as the object, we carried out optimized scheduling of 96 points (15-minute intervals) the next day.

[0059] Step S1: Data preparation and model parameter input.

[0060] The system obtains predicted data on wind speed and solar intensity for the next 24 hours through the data input module and converts them into power prediction curves for wind and solar power; it also obtains system load prediction curves; it reads parameters such as reservoir capacity curves, tailrace water level curves, unit efficiency characteristics, maximum / minimum output, and ramp rate for each cascade hydropower station; and it sets hydropower generation cost coefficients, grid connection price, purchased electricity price, and wind and solar curtailment penalty coefficients.

[0061] Step S2: Construct the day-ahead.

[0062] Based on the above data, the mathematical expressions for the biobjective function and all constraints are generated in the model building module.

[0063] Current multi-objective optimization models include:

[0064] First objective: To minimize the overall operating cost within the system scheduling cycle;

[0065] ;

[0066] ;

[0067] in, This is a function for calculating the lowest overall operating cost within the system scheduling cycle. The lowest overall operating cost within the system scheduling cycle; C Hydro The cost of generating hydropower; C grid Cost of purchasing electricity from the grid; C w It is the cost of penalties for abandoning electricity; The penalty cost when wind power is wasted; It is the penalty cost when light generates wasted electricity; It is the maximum output of wind power during time period i; It is the maximum output of photovoltaic power during time period i; This is the actual output value of wind power during time period i; is the actual power output of the photovoltaic system during time period i, and T is the length of the sequence.

[0068] Second objective: To minimize the total power output fluctuation of the cascade hydropower stations;

[0069] ;

[0070] in, This is a function for calculating the minimum total output fluctuation of a cascade hydropower station; This represents the minimum total output fluctuation of the cascade hydropower stations; num is the number of hydropower stations. Let i be the output of the nth hydropower station at time i. This represents the power output of the nth hydropower station at the previous moment.

[0071] The constraints include:

[0072] 1. System power balance constraints:

[0073] ;

[0074] Where: N h It represents the number of cascade hydropower stations, y n It refers to the number of generating units within the hydroelectric power station. This represents the power generation of the nth generating unit during time period i. This is the load value for time period i. This refers to the planned power generation of the photovoltaic power station during time period i. It represents the scheduled power generation of the wind farm during time period i.

[0075] 2. The output power constraints for photovoltaic power plants and wind farms are as follows:

[0076] ;

[0077] ;

[0078] In the formula: It is the maximum power generation of the wind farm during time period i; It is the maximum power generation of the photovoltaic power station during time period i; It is the output power of the wind farm at time i; It is the output power of the wind farm at time i.

[0079] 3. The theoretical output of a hydropower station is related to the amount of natural water energy per unit time. Energy loss occurs during the process of the turbine converting water energy into electrical energy; therefore, the actual output of a hydropower station is lower than its theoretical output. Its model can be expressed as:

[0080] ;

[0081] In the formula: g is a constant, which is taken as 9.81 in this paper; η h q represents the efficiency coefficient of the water turbine. ht The power generation flow rate at time t (m 3 / s); H ht Let t be the reservoir head at time t; It is the theoretical output of the hydropower station at time t.

[0082] 4. Water balance constraints of hydropower stations

[0083] ;

[0084] Where: Ca h,t It is the reservoir capacity (m³) of the hydropower station during time period t. 3 ); Ca h,t-1It is the reservoir capacity of the hydropower station in the previous time period of time t; I h,t Inbound flow (m) 3 / s); Q h,t The discharge flow rate at time t (m 3 / s).

[0085] 5. Reservoir capacity constraints of hydropower stations

[0086] ;

[0087] Where: Ca hmin Minimum reservoir capacity (m³) for hydropower stations 3 ); , Ca hmax This is the maximum reservoir capacity of the hydropower station; Let t be the reservoir capacity of the hydropower station at time t.

[0088] 6. Water level constraints at hydropower stations;

[0089] ;

[0090] In the formula: Z h min Z represents the minimum water level limit (m) for hydropower stations. h max This refers to the maximum water level limit for the hydropower station. Let t be the water level at the hydroelectric power station at time t.

[0091] 7. Constraints on downstream flow of hydropower stations

[0092] ;

[0093] In the formula: Q h min Minimum discharge flow rate (m 3 / s); Q h min This is the maximum discharge flow rate; Let t be the discharge flow of the hydropower station at time t.

[0094] Step S3: Use the non-dominated sorting genetic algorithm (NSGA-II).

[0095] Set the algorithm parameters: population size N=200, maximum number of iterations G=300.

[0096] 1. Initialization: Randomly generate an initial population of 200 individuals within the feasible region, with each individual representing a complete 96-point scheduling scheme chromosome.

[0097] 2. Parallel Fitness Calculation: The current population data is copied to the GPU memory. The GPU launches a large number of threads, each responsible for calculating the objective function value (including cost calculation and volatility calculation) for one or more individuals, achieving completion in milliseconds.

[0098] 3. Non-dominated sorting and crowding calculation: Under CPU control, the GPU parallel kernel is invoked to perform fast non-dominated sorting of the population and calculate the crowding distance for individuals at the same frontier.

[0099] 4. Selection, Crossover, and Mutation: Parents are selected using a tournament selection method based on the non-dominant level and crowding degree of individuals. Under CPU control, the GPU performs SBX crossover and polynomial mutation operations in parallel to generate the offspring population. The crossover and mutation probabilities adaptively decrease with the number of iterations.

[0100] 5. Merging and Elite Selection: Merge the parent and offspring populations. Again, utilize GPUs in parallel for fast non-dominated sorting and crowding calculation. Based on the sorting and crowding comparison results, select the top 200 individuals from the merged population as the next generation.

[0101] 6. Constraint Correction: In each generation, the FPGA constraint verification module quickly checks whether the new individuals generated through genetic operations violate complex constraints such as reservoir water balance. If a violation is found, the embedded correction logic (such as adjusting the power generation flow sequence) is invoked to correct the violation and ensure the individual's feasibility.

[0102] 7. Iteration: Repeat steps 2-6 until the maximum number of iterations G=300 is reached.

[0103] Step S4: Extract the compromise solution and generate a scheduling plan.

[0104] After the algorithm terminates, the final frontier solution set is stored in the Pareto optimal memory. For each solution in the solution set, the normalized values ​​of its two objective function values ​​relative to the range of the solution set are calculated, and the normalized objective fitness value of each solution is also calculated. The solution with the smallest fitness value is selected as the final day-ahead scheduling scheme.

[0105] The expression for the optimization objective fitness function of the Pareto optimal front solution is as follows:

[0106] ;

[0107] Where f i,j f is the j-th objective function value of the i-th Pareto optimal solution; max,j Let f be the maximum value of the j-th objective function; and f min,j Let be the minimum value of the j-th objective function; fitness function

[0108] The fitness values ​​of the objective function for any Pareto optimal solution are shown below:

[0109] ;

[0110] Where N is the number of objective functions that need to be optimized.

[0111] Optimized scheduling based on the NSGA-II algorithm can better coordinate the competitive relationship between two multi-objectives, reducing the system's operating costs while ensuring that the total output fluctuation of the hydropower system is small.

[0112] Example 2

[0113] This application also discloses an embodiment of a multi-objective optimization scheduling device for wind, solar, and water resources based on the NSGA-II algorithm, which includes...

[0114] The acquisition module is configured to acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data.

[0115] The first construction module is configured to construct a multi-objective function based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data;

[0116] The second construction module is configured to establish a multi-objective optimization scheduling model based on the multi-objective function and a preset set of constraints.

[0117] The computation module is configured to solve the multi-objective optimization scheduling model using a non-dominated sorting genetic algorithm to obtain a Pareto front solution set.

[0118] The confirmation module is configured to select a compromise solution from the Pareto front solution set based on the fitness function, the compromise solution being used for multi-objective optimization scheduling of wind, solar and water resources.

[0119] Example 3

[0120] This application also discloses an embodiment of a computer-readable storage medium that stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method in embodiment 1.

[0121] Example 4

[0122] This application also discloses an embodiment in which a computer device includes one or more processors and one or more memories, one or more programs are stored in one or more memories and configured to be executed by one or more processors, and the one or more programs include instructions for performing the method described in Embodiment 1.

[0123] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0124] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

Claims

1. A multi-objective optimization scheduling method for wind, solar, and water resources, characterized in that, include: Acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data; A multi-objective function is constructed based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data. Based on the multi-objective function, and constrained by a preset set of constraints, a multi-objective optimization scheduling model is established. The multi-objective optimization scheduling model is solved using a non-dominated sorting genetic algorithm to obtain the Pareto front solution set; A compromise solution is selected from the Pareto front solution set based on the fitness function, and the compromise solution is used for multi-objective optimization scheduling of wind, solar and water resources.

2. The multi-objective optimization scheduling method for wind, solar, and water resources according to claim 1, characterized in that, The multi-objective function includes a first objective function, which is used to calculate the minimum comprehensive operating cost within the system scheduling cycle; the calculation of the minimum comprehensive operating cost within the system scheduling cycle is performed by the following formula; ； ； in, This is a function for calculating the lowest overall operating cost within the system scheduling cycle. The lowest overall operating cost within the system scheduling cycle; C Hydro The cost of generating hydropower; C grid Cost of purchasing electricity from the grid; C w It is the cost of penalties for abandoning electricity; The penalty cost when wind power is wasted; It is the penalty cost when light generates wasted electricity; It is the maximum output of wind power during time period i; It is the maximum output of photovoltaic power during time period i; This is the actual output value of wind power during time period i; It is the actual output value of photovoltaic power in time period i, and T is the sequence length.

3. The multi-objective optimization scheduling method for wind, solar, and water resources according to claim 1, characterized in that, The multi-objective function includes a second objective function, which is used to calculate the minimum total output fluctuation of the cascade hydropower stations; the total output fluctuation of the cascade hydropower stations is calculated by the following formula; ； in, This is a function for calculating the minimum total output fluctuation of a cascade hydropower station; This represents the minimum total output fluctuation of the cascade hydropower stations; It refers to the number of hydroelectric power stations; Let i be the output of the nth hydropower station at time i. The output of the nth hydropower station at the previous moment is T; the sequence length is T.

4. The multi-objective optimization scheduling method for wind, solar, and water resources according to claim 1, characterized in that, Based on the fitness function, a compromise solution is selected from the Pareto front solution set. This compromise solution is used for multi-objective optimization scheduling of wind, solar, and water resources, including: The fitness value of the Pareto optimal solution is calculated using the fitness function, and the minimum objective fitness among the Pareto optimal solutions is selected as the compromise solution for multi-objective optimization scheduling of wind, solar and water resources. The fitness function formula is as follows; ； in This represents the j-th objective function value of the i-th Pareto optimal solution; The maximum value of the j-th objective function; and Let be the minimum value of the j-th objective function; The fitness function; The optimal formula for calculating the fitness value of the objective function is as follows: ； Where N is the number of objective functions that need to be optimized; The fitness of the objective function is optimal.

5. The multi-objective optimization scheduling method for wind, solar, and water resources according to claim 1, characterized in that, The step of solving the multi-objective optimization scheduling model using a non-dominated sorting genetic algorithm to obtain the Pareto front solution set includes: Randomly generate a parent population P of size N. t The first generation of offspring populations of the same size are generated through rapid non-dominated sorting and genetic operations. The parent and offspring generations are merged according to the elite strategy to form a mixed population of size 2N; the population is then subjected to rapid non-dominated sorting and divided into Pareto fronts of different levels according to the non-dominated relationship. From low to high, add complete non-dominated layers to the new parent population P. t+1 When the first layer can no longer accommodate all individuals, the crowding distance comparison mechanism is used to select the best individuals to ensure that the population size is restored to N. Genetic operations are performed on the new parent population to generate the next generation of offspring. The above sorting and selection process is repeated until the termination condition is met, at which point a Pareto front solution set is generated.

6. The multi-objective optimization scheduling method for wind, solar, and water resources according to claim 1, wherein the multi-objective function is constrained by a preset set of constraints, including... Based on the system power balance constraints, the output power constraints of photovoltaic power plants and wind farms, the water balance constraints of hydropower stations, the reservoir capacity constraints of hydropower stations, the water level constraints of hydropower stations, and the discharge flow constraints of hydropower stations, the multi-objective function is constrained to construct and establish a multi-objective optimization scheduling model.

7. A multi-objective optimization scheduling device for wind, solar, and water resources, characterized in that, include The acquisition module is configured to acquire wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data. The first construction module is configured to construct a multi-objective function based on wind and solar power forecast data, load demand forecast data, reservoir parameter data, watershed hydrological and meteorological data, and market electricity price data; The second construction module is configured to establish a multi-objective optimization scheduling model based on the multi-objective function and a preset set of constraints. Calculation module; It is configured to solve the multi-objective optimization scheduling model according to the non-dominated sorting genetic algorithm to obtain the Pareto front solution set; The confirmation module is configured to select a compromise solution from the Pareto front solution set based on the fitness function, the compromise solution being used for multi-objective optimization scheduling of wind, solar and water resources.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 6.

9. A computer device, characterized in that, include: One or more processors and one or more memories, one or more programs stored in one or more memories and configured to be executed by one or more processors, the one or more programs including instructions for performing the method of any one of claims 1 to 6.

Images