Comprehensive energy optimization scheduling method based on SPEA-II algorithm

Abstract

The invention discloses a comprehensive energy optimization scheduling method based on an SPEA-II algorithm, relates to the field of energy optimization systems, and comprises the steps of determining a comprehensive energy model, and considering economic cost, pollution emission and renewable energy sources. Hydroelectricity, photoelectricity, wind power and thermal power are used as constraint conditions. And according to each constraint condition, constructing a wind-light-water-fire combined power generation model. An SPEA-II algorithm is adopted to solve the multi-target problem; and solving an optimal comprehensive energy optimization scheduling method based on an SPEA-II algorithm. Updating the population generation by generation by using an SPEA-II algorithm until a set number of times is reached; and according to the updated archiving set, a plurality of scheduling schemes of wind-light-water-fire combined power generation are obtained, and complementarity among wind energy, light energy, water energy and fire energy is brought into full play. The method has excellent performance in the aspects of small calculation amount and optimal solution (namely comprehensive energy optimization scheduling).

Description

Technical Field

[0001] The invention belongs to the field of energy planning and relates to a comprehensive energy optimization scheduling method based on a SPEA-II genetic algorithm. Background Art

[0002] With the transformation of the global energy structure and the rapid development of renewable energy, various energy forms such as wind power, solar power, hydropower and thermal power are playing an increasingly important role in the power system. Comprehensive utilization of these energy sources and optimization of dispatching strategies can effectively improve the economy, reliability and environmental protection of the system.

[0003] Wind and solar power generation are intermittent and volatile, and are greatly affected by natural conditions. This may lead to insufficient power supply during peak load periods or bad weather. Hydropower stations have strong regulation capabilities and can respond quickly to changes in power demand, but their power generation is affected by water resources and has large seasonal and interannual variations. Thermal power has high stability and reliability and is an important support for traditional power systems. However, the fuel consumption and carbon emissions of thermal power have a great impact on the environment.

[0004] In the integrated energy dispatch optimization, SPEA-II (Strength Pareto Evolutionary Algorithm2) as an advanced multi-objective evolutionary algorithm can effectively handle optimization problems, especially when faced with complex multi-objectives and constraints. SPEA-II aims to optimize multiple conflicting objectives simultaneously, such as cost, reliability, and environmental impact. Through population evolution, the Pareto optimal solution set is gradually found. The algorithm uses strength and sparsity to evaluate individual fitness, ensuring that diverse solutions are found in the solution space and improving the global search capability of the algorithm.

[0005] Combining SPEA-II with wind, solar, thermal and hydropower integrated energy dispatch optimization can achieve efficient resource allocation in multi-objective optimization and improve the economy and environmental friendliness of the power system. This method not only enhances the flexibility and adaptability of dispatch, but also provides strong technical support for achieving sustainable energy management.

[0006] After searching, the application publication number CN116822978A, a method for optimizing the dispatching of a comprehensive energy park based on a hybrid energy storage system, includes four steps: establishing a hybrid energy storage model, forming distributed energy storage system constraints, establishing objective functions for maximizing economic benefits and minimizing carbon emissions, and performing multi-objective optimization. First, a hybrid comprehensive energy park energy storage system with traditional generators and wind and solar generators is established to form the operating constraints of the hybrid energy storage system. Then, the goal is to maximize the comprehensive benefits of the entire comprehensive energy park and minimize carbon dioxide emissions. Finally, the strong memory advantage of the non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem, improve the optimization efficiency, and achieve reasonable coordinated optimization and dispatching of the hybrid energy storage of the entire comprehensive energy park.

[0007] Although the above patents use non-dominated sorting genetic algorithms as a method for solving multi-objective problems, and although crowding distance is used to maintain the diversity of the solution space, in some cases, crowding distance may not be able to completely avoid the concentration or uneven distribution of solutions, especially when dealing with highly complex or highly nonlinear objective functions. Secondly, when there are many objectives, there may be excessive concentration in some solution areas, resulting in poor solution quality in some areas. It does not have a built-in mechanism to handle dynamically changing environments or problems. When the optimization problem itself changes (such as changes in objectives or constraints), it may not be able to adjust and adapt to new situations in a timely manner. SPEA-II has an archive set (Archive) that can store and manage historical solutions. The solutions in the archive set are non-dominated solutions, and are pruned by density distance to ensure the uniform distribution of solutions. This is crucial for integrated energy optimization problems because we need to consider how to balance multiple objectives such as economic benefits and carbon emissions. Compared with traditional methods, SPEA-II can provide decision makers with a variety of scheduling solutions through effective archive set management, avoiding over-reliance on a single goal. At the same time, SPEA-II adopts an efficient fitness evaluation mechanism. By combining non-dominated sorting and strength evaluation, the algorithm can quickly distinguish between good solutions and bad solutions. This is particularly advantageous for solving complex scheduling problems, because in large-scale optimization problems with complex constraints, it is very important to quickly and effectively evaluate the fitness of individuals. Through this mechanism, SPEA-II can efficiently update the population in each generation of optimization process and avoid excessive redundant calculations. Summary of the invention

[0008] The present invention aims to solve the above problems of the prior art. A comprehensive energy optimization scheduling method based on the SPEA-II algorithm is proposed. The technical solution of the present invention is as follows:

[0009] A comprehensive energy optimization scheduling method based on SPEA-II algorithm comprises the following steps:

[0010] Determine the model of the integrated energy system, including thermal power generation system, solar photovoltaic power generation system, wind power generation system, and hydropower generation system;

[0011] Taking the maximum combined total power generation of hydropower stations, wind power stations, thermal power stations and photovoltaic power stations as the first objective function and the minimum combined output as the second objective function, a comprehensive energy model is constructed according to the constraints of each power station; the power station constraints are the quantity balance, interactive power and the constraints of wind turbines and photovoltaic equipment themselves;

[0012] The second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the multi-objective problem;

[0013] The optimal comprehensive energy optimization scheduling is solved based on the second-generation non-dominated genetic sorting SPEA-II algorithm.

[0014] Furthermore, the maximum combined total power generation of the hydropower station, wind power station, photovoltaic power station, and thermal power station is taken as the first objective function, specifically:

[0015]

[0016] Among them, F1 represents hydropower station, wind power station, N h The total power generation of photovoltaic power stations and thermal power stations, T represents the total number of time periods, t represents the time sequence number, t∈[1,T], represents the hydropower output, N w Indicates wind power output, N l Indicates photoelectric output, N f represents thermal power output; Δt represents unit time.

[0017] The hydroelectric generator converts the mechanical energy of water flow into electrical energy. The difference in water levels between upstream and downstream determines the output. The efficiency of the hydroelectric generator determines the amount of energy loss. The formula is as follows:

[0018] N h =K h QΔH

[0019] Where Q represents the speed of water flowing through the turbine, ΔH represents the head difference of the hydropower station; K h It represents the hydropower output coefficient;

[0020] Wind power generation is related to wind speed, air density, fan efficiency and rotor. The formula is:

[0021]

[0022] Where ρ represents the air density; A represents the area swept by the fan blades, C p represents the power generation coefficient, v represents the wind speed;

[0023] Photovoltaic output is mainly related to light intensity, photoelectric conversion efficiency and the size of the photovoltaic panel. The formula is as follows:

[0024]

[0025] Among them, H A represents the total horizontal solar radiation, P AZ Indicates the capacity of the solar cell, E S It represents the irradiance under standard conditions, and K1 represents the photoelectric output coefficient;

[0026] The output of thermal power is expressed as:

[0027]

[0028] Where: Formula F cp (t) represents the standard coal consumption of coal-fired power units in the t period; P cp (t) represents the power generation of the coal-fired power unit in period t; α CB b represents the quadratic coefficient of coal consumption characteristics; cp The coefficient that represents its coal consumption characteristics; c CB A constant term representing its coal consumption characteristics.

[0029] Furthermore, the combined minimum output is used as the second objective function, and a comprehensive energy model is constructed according to the constraints of each power station, specifically including:

[0030] The second objective function:

[0031] MaxF2=max{min(N h +N w +N l +N f )}

[0032] Among them, F2 represents the combined minimum output of hydropower stations, wind power stations, photovoltaic power stations and thermal power stations;

[0033] The constraints are;

[0034] The power balance constraint equation is:

[0035] P w (t)+P v (t)+P b (t)+P f (t) = P LD (t)

[0036] Where P w (t), P v (t), P b (t), P f(t) are the output power of wind power generation, photovoltaic power generation, hydropower generation, and thermal power generation, respectively, P LD (t) is the load requirement.

[0037] Furthermore, the quantity balance, interactive power and wind turbine and photovoltaic equipment constraints are used as constraint conditions, specifically including: constraints are divided into equipment constraints and interactive power constraints:

[0038] In the integrated energy system, the output constraints of wind power, photovoltaic power, hydropower and thermal power are:

[0039] 0≤P w (t)≤P wmax , 0≤P V (t)≤P vmax , 0≤P b (t)≤P bmax (t), 0≤P l (t)≤P lmax (t)

[0040] Where P wmax , P vmax , P bmax , P fmax They are the maximum output powers of wind turbines, photovoltaic power generation systems, hydropower generation and thermal power generation respectively.

[0041] Furthermore, the second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the multi-objective problem, specifically including:

[0042] Initialize the first population and the archive set and evolution parameters in the belief space according to the constraints of the power station; the evolution parameters include the crossover evolution parameter F and the variation evolution parameter CR;

[0043] Calculate the fitness of the first population and perform non-dominated sorting on the first population, select non-dominated individuals from the first population and put them into the archive set, delete the dominated individuals from the archive set, and update the archive set;

[0044] Check whether the number of individuals in the updated archive set exceeds the set value; if so, trim the archive set according to the individual density; if not, proceed to the next step;

[0045] Using the improved SPEA-II algorithm, the first population and belief space are updated generation by generation until a set number of times;

[0046] According to the archive set after the update, the dispatching methods of multiple wind, solar, water and thermal combined power generation are obtained.

[0047] Furthermore, the specific updating step of the archive set is population updating selection: using a binary tournament method to select better individuals from the first population to form a second population;

[0048] Crossover mutation: Use the crossover mutation mode of the differential evolution algorithm to update the second population and calculate the fitness of the individuals in the updated population;

[0049] Non-dominated sorting: Perform non-dominated sorting on the individuals in the third population and calculate the crowding distance of the individuals in the third population;

[0050] Evolution parameter update: according to the population update status of each generation, update the crossover evolution parameter F and the mutation evolution parameter CR;

[0051] Archive set update: Update the archive set for the new generation population according to the above steps.

[0052] Furthermore, the pruning of the archive set is specifically as follows: the pruning method in the SPEA-II algorithm is used: the objective function is evaluated for each individual (solution) to check whether it violates the constraint condition. If a constraint condition is violated, the solution needs to be pruned. The pruned individual will recalculate the fitness and continue to participate in the genetic operation. The dense distance of each individual in the archive set is calculated. Where N(i) is the set of neighboring individuals of individual i, d(i,j) is the distance between individual i and individual j, and individuals with smaller dense distances in the archive set are deleted.

[0053] Furthermore, the second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the multi-objective function optimization problem of the integrated energy system, including:

[0054] (1) Initialization: Initialize an evolutionary population P0 and an empty archive set Q0;

[0055] (2) Fitness allocation: Evolving the current evolution population P t and the current archive set Q t The fitness value of individuals in ;

[0056] (3) Environment selection: Use the next generation archive set Q t+1 Save P t and Q t All non-dominated individuals in; if Q t+1 The number of individuals in exceeds M, and the pruning process is used to reduce Q t+1 The number of individuals in t+1 The number of individuals in is smaller than M, then we need to select P t and Q t The dominant individuals in fill Q t+1 ;

[0057] (4) Ending condition: If t ≥ T, or other ending conditions are met, Q t+1 The non-dominated individuals in are saved into NDset, and as the final result, the evolution process ends;

[0058] (5) Pairing selection: Pair Q t+1 Make your tournament selections in the Next Generation Archive Set Q t+1 Select suitable individuals to enter the pairing library;

[0059] (6) Evolutionary Operation: Q t+1 Perform crossover and mutation operations and save the results to Q t+1 In the above example, let t = t + 1 and go to step (2).

[0060] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for comprehensive energy optimization scheduling based on the SPEA-II algorithm as described in any one of the items is implemented.

[0061] A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the comprehensive energy optimization scheduling method based on the SPEA-II algorithm as described in any one of the items.

[0062] The advantages and beneficial effects of the present invention are as follows:

[0063] The present invention proposes an integrated energy system optimization method based on improved SPEA-II, establishes a model of a combined power generation system consisting of wind power generation, solar power generation, hydropower generation, and thermal power generation, takes combined power generation and minimum output as the objective function, and takes maximum power and energy consumption as constraints. To a certain extent, the utilization rate of renewable energy is improved, while ensuring the economy and stability of the combined power generation system, and obtaining the best economic benefits under the condition of safe operation.

[0064] SPEA-II can optimize multiple objectives at the same time. In the joint dispatch of wind and solar power generation and traditional power generation units, SPEA-II can find the optimal solution between comprehensive output and output power. SPEA-II can effectively find a set of Pareto optimal solutions, that is, the optimal balance between various objectives through non-dominated sorting and density distance. SPEA-II has a strong global search capability. By continuously evaluating individuals in the population and using density distance to ensure the diversity of the population, it avoids the problem of premature convergence near the local optimal solution. This enables SPEA-II to explore in a wide solution space and find better solutions, especially when facing complex energy scheduling and optimization problems. When multiple power generation units (including renewable energy and traditional energy) are jointly dispatched, SPEA-II can avoid missing the opportunity for overall optimization due to local optimality and ensure the overall superiority of the scheduling scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 The present invention provides a flow chart of a comprehensive energy optimization scheduling method based on the SPEA-II algorithm in a preferred embodiment;

[0066] Figure 2 It is a diagram of comprehensive energy optimization scheduling model. DETAILED DESCRIPTION

[0067] The following will describe the technical solutions in the embodiments of the present invention in detail in conjunction with the accompanying drawings in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention.

[0068] The technical solution of the present invention to solve the above technical problems is:

[0069] The embodiment of the present invention provides a comprehensive energy scheduling method based on an improved SPEA-II algorithm, comprising:

[0070] Taking the maximum combined total power generation of hydropower stations, wind power stations, photovoltaic power stations, and thermal power stations as the first objective function, and maximizing the combined minimum output as the second objective function, a wind-solar-hydro-thermal combined power generation model is constructed according to the power generation constraints of each power station;

[0071] (1.1) The first objective function:

[0072]

[0073] F1 represents the total power generation of hydropower stations, wind power stations, photovoltaic power stations, and thermal power stations, T represents the total number of time periods, t represents the time sequence number, t∈[1,T], N h Indicates hydropower treatment capacity, N w Indicates sharp force, N l Indicates photoelectric output, N fIndicates thermal power output.

[0074] The hydroelectric generator converts the mechanical energy of water flow into electrical energy. The difference in water levels between upstream and downstream determines the output. The efficiency of the hydroelectric generator determines the amount of energy loss. The formula is as follows:

[0075] N h =K h QΔH

[0076] Where Q represents the speed of water flowing through the turbine, ΔH represents the head difference of the hydropower station; K h Represents the hydropower output coefficient.

[0077] Wind power output is related to wind speed, air density, fan efficiency and rotor. The formula is:

[0078]

[0079] Where ρ represents the air density; A represents the area swept by the fan blades, C p represents the power generation coefficient, v represents the wind speed;

[0080] Photovoltaic output is mainly related to light intensity, photoelectric conversion efficiency and the size of the photovoltaic panel. The formula is as follows:

[0081]

[0082] Among them, H A represents the total horizontal solar radiation, P AZ Indicates the capacity of the solar cell, E S It represents the irradiance under standard conditions, and K1 represents the photoelectric output coefficient;

[0083] The output of thermal power is expressed as:

[0084]

[0085] Where: Formula F cp (t) represents the standard coal consumption of coal-fired power units in the t period; P cp (t) represents the power generation of the coal-fired power unit in period t; α CB b represents the quadratic coefficient of coal consumption characteristics; cp The coefficient that represents its coal consumption characteristics; c CB The constant term representing its coal consumption characteristics

[0086] (1.2) The second objective function:

[0087] MaxF2=max{min(N h +N w +N l+N f )}

[0088] Among them, F2 represents the combined minimum output of hydropower stations, wind power stations, photovoltaic stations and thermal power stations.

[0089] (1.3) Constraints;

[0090] Furthermore, the constraints are determined and the power balance constraint equation is:

[0091] P w (t)+P v (t)+P b (t)+P f (t) = P LD (t)

[0092] Where P w (t), P v (t), P b (t), P f (t) are the output power of wind power generation, photovoltaic power generation, hydropower generation, and thermal power generation respectively. LD (t) is the load requirement.

[0093] Furthermore, the quantity balance, interactive power and wind turbine and photovoltaic equipment constraints are used as constraint conditions, specifically including: constraints are divided into equipment constraints and interactive power constraints:

[0094] In the integrated energy system, the output constraints of wind power, photovoltaic power, hydropower and thermal power are:

[0095] 0≤P w (t)≤P wmax , 0≤P V (t)≤P vmax , 0≤P b (t)≤P bmax (t), 0≤P l (t)≤P lmax (t)

[0096] Where P wmax , P vmax , P bmax , P fmax They are the maximum output powers of wind turbines, photovoltaic power generation systems, hydropower generation and thermal power generation respectively.

[0097] Furthermore, the second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the four-objective function optimization problem of the integrated energy system, including:

[0098] Initialization: Initialize an evolution population P0 and an empty archive set Q0 (t=0).

[0099] Fitness allocation: Evolution of the current evolution population P t and the current archive set Q t The fitness value of the individual.

[0100] Environment selection: Use the next generation archive set Q t+1 Save P t and Q t All non-dominated individuals in. If Q t+1 The number of individuals in exceeds M, and the pruning process is used to reduce Q t+1 The number of individuals in t+1 The number of individuals in is smaller than M, then we need to select P t and Q t The dominant individuals in fill Q t+1 .

[0101] End condition: If t ≥ T, or other end conditions are met, Q t+1 The non-dominated individuals in are saved to NDset, and as the final result, the evolution process ends.

[0102] Pairing options: Pair Q t+1 Make your tournament selections in the Next Generation Archive Set Q t+1 Select suitable individuals to enter the pairing library.

[0103] Evolution Operation: Q t+1 Perform crossover and mutation operations and save the results to Q t+1 In the above example, let t = t + 1 and go to step (2).

[0104] (1) Taking the maximum combined total power generation of hydropower stations, wind power stations, photovoltaic power stations, and thermal power stations as the first objective function and maximizing the combined minimum output as the second objective function, a wind-solar-hydro-thermal combined power generation model is constructed according to the constraints of each power station;

[0105] (2) Initializing the first population and the archive set and evolution parameters in the belief space according to the constraints of the power plant; the evolution parameters include the crossover evolution parameter F and the variation evolution parameter CR;

[0106] (3) Calculate the fitness of the first population and perform non-textual sorting on the first population, select non-dominated individuals from it and put them into the archive set, delete the dominated individuals from the archive set, and update the archive set;

[0107] (4) Check whether the number of individuals in the updated archive set exceeds the set value; if so, trim the archive set according to the individual density; if not, proceed to step (5);

[0108] (5) Using the improved SPEA-II algorithm to update the first population and belief space generation by generation until the set number of times;

[0109] (6) Based on the updated archive set, a scheduling method for multiple wind, solar and hydropower combined power generation is obtained.

[0110] Further, step (5) specifically includes:

[0111] (5.1) Population update;

[0112] (5.2) Fitness allocation: Calculate the current P t (current evolutionary group) and Q t The fitness of all individuals in (the current archive set).

[0113] (5.3) Environmental selection: P t and Q t All non-dominated individuals in are saved to Q t+1 In. If Q t+1 If the number of individuals in exceeds M, the file truncation method (i.e., pruning method) is used to reduce its size. The pruning method selects the individuals closest to other individuals and deletes them until Q t+1 The size of is M, if Q t+1 The size of is less than M, then from P t and Q t Select the dominant individual to fill Q t+1 .

[0114] (5.4) Termination condition: If the current number of iterations t is greater than or equal to 1, or other conditions are met, then Q t+1 All non-dominated individuals in are returned as results and saved in NDset.

[0115] (5.5) Pairing selection: Pair Q t+1 Perform tournament selection and place selected individuals into the mating pool.

[0116] (5.6) Pairing selection: Perform crossover and mutation operations on the individuals in the mating pool to generate new individuals, and save the results to P t+1 Update the number of iterations t = t + 1, then return to the fitness allocation step and continue the next round of iterations.

[0117] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0118] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0119] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0120] The above embodiments should be understood to be only used to illustrate the present invention and not to limit the protection scope of the present invention. After reading the contents of the present invention, technicians can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A comprehensive energy optimization scheduling method based on SPEA-II algorithm, characterized in that: The following steps are involved: Determine the model of the integrated energy system, including thermal power generation system, solar photovoltaic power generation system, wind power generation system, and hydropower generation system; Taking the maximum combined total power generation of hydropower stations, wind power stations, thermal power stations and photovoltaic power stations as the first objective function and the minimum combined output as the second objective function, a comprehensive energy model is constructed according to the constraints of each power station; the power station constraints are the quantity balance, interactive power and the constraints of wind turbines and photovoltaic equipment themselves; The second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the multi-objective problem; The optimal comprehensive energy optimization scheduling is solved based on the second-generation non-dominated genetic sorting SPEA-II algorithm.

2. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 1 is characterized in that: The first objective function is to maximize the total combined power generation of the hydropower station, wind power station, photovoltaic power station, and thermal power station, specifically: Among them, F1 represents the total power generation of hydropower stations, wind power stations, photovoltaic power stations, and thermal power stations, T represents the total number of time periods, t represents the time sequence number, t∈[1,T], N h Indicates hydropower output, N w Indicates wind power output, N l Indicates photoelectric output, N f represents thermal power output; Δt represents unit time. The hydroelectric generator converts the mechanical energy of water flow into electrical energy. The difference in water levels between upstream and downstream determines the output. The efficiency of the hydroelectric generator determines the amount of energy loss. The formula is as follows: N h =K h QΔH Where Q represents the speed of water flowing through the turbine, ΔH represents the head difference of the hydropower station; K h It represents the hydropower output coefficient; Wind power generation is related to wind speed, air density, fan efficiency and rotor. The formula is: Where ρ represents the air density; A represents the area swept by the fan blades, C p represents the power generation coefficient, v represents the wind speed; Photovoltaic output is mainly related to light intensity, photoelectric conversion efficiency and the size of the photovoltaic panel. The formula is as follows: Among them, H A represents the total horizontal solar radiation, P AZ Indicates the capacity of the solar cell, E S It represents the irradiance under standard conditions, and K1 represents the photoelectric output coefficient; The output of thermal power is expressed as: Where: Formula F cp (t) represents the standard coal consumption of coal-fired power units in the t period; P cp (t) represents the power generation of the coal-fired power unit in period t; α CB b represents the quadratic coefficient of coal consumption characteristics; cp The coefficient that represents its coal consumption characteristics; c CB A constant term representing its coal consumption characteristics.

3. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 2 is characterized in that: The combined minimum output is used as the second objective function, and a comprehensive energy model is constructed according to the constraints of each power station, specifically including: The second objective function: MaxF2=max{min(N h +N w +N l +N f )} Among them, F2 represents the combined minimum output of hydropower stations, wind power stations, photovoltaic power stations and thermal power stations; The constraints are; The power balance constraint equation is: P w (t)+P v (t)+P b (t)+P f (t)=P LD (t) Where P w (t), P v (t), P b (t), P f (t) are the output power of wind power generation, photovoltaic power generation, hydropower generation, and thermal power generation, respectively, P LD (t) is the load requirement.

4. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 3 is characterized in that: The constraint conditions are quantity balance, interactive power and wind turbine and photovoltaic equipment constraints. Specifically, the constraints are divided into equipment constraints and interactive power constraints: In the integrated energy system, the output constraints of wind power, photovoltaic power, hydropower and thermal power are: 0≤P w (t)≤P wmax ,0≤P V (t)≤P vmax ,0≤P b (t)≤P bmax (t),0≤P l (t)≤P lmax (t) Where P wmax , P vmax , P bmax , P fmax They are the maximum output powers of wind turbines, photovoltaic power generation systems, hydropower generation and thermal power generation respectively.

5. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 4 is characterized in that: The specific updating step of the archive set is population updating selection: using the binary tournament method to select better individuals from the first population to form the second population; Crossover mutation: Use the crossover mutation mode of the differential evolution algorithm to update the second population and calculate the fitness of the individuals in the updated population; Non-dominated sorting: Perform non-dominated sorting on the individuals in the third population and calculate the crowding distance of the individuals in the third population; Evolution parameter update: according to the population update status of each generation, update the crossover evolution parameter F and the mutation evolution parameter CR; Archive set update: Update the archive set for the new generation population according to the above steps.

6. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 5 is characterized in that: The pruning of the archive set is specifically as follows: the pruning method in the SPEA-II algorithm is used: the objective function is evaluated for each individual (solution) to check whether it violates the constraint condition. If a constraint condition is violated, the solution needs to be pruned. The pruned individual will recalculate the fitness and continue to participate in the genetic operation. The dense distance of each individual in the archive set is calculated. Where N(i) is the set of neighboring individuals of individual i, d(i,j) is the distance between individual i and individual j, and individuals with smaller dense distances in the archive set are deleted.

7. The comprehensive energy optimization scheduling method based on the SPEA-II algorithm according to claim 1 is characterized in that: The second generation non-dominated genetic sorting SPEA-II algorithm is used to solve the multi-objective function optimization problem of the integrated energy system, including: (1) Initialization: Initialize an evolutionary population P0 and an empty archive set Q0; (2) Fitness allocation: Evolving the current evolution population P t and the current archive set Q t The fitness value of individuals in ; (3) Environment selection: Use the next generation archive set Q t+1 Save P t and Q t All non-dominated individuals in; if Q t+1 The number of individuals in exceeds M, and the pruning process is used to reduce Q t+1 The number of individuals in t+1 The number of individuals in is smaller than M, then we need to select P t and Q t The dominant individuals in fill Q t+1 ; (4) Ending condition: If t ≥ T, or other ending conditions are met, Q t+1 The non-dominated individuals in are saved into NDset, and as the final result, the evolution process ends; (5) Pairing selection: Pair Q t+1 Make your tournament selections in the Next Generation Archive Set Q t+1 Select suitable individuals to enter the pairing library; (6) Evolutionary Operation: Q t+1 Perform crossover and mutation operations and save the results to Q t+1 In the above example, let t = t + 1 and go to step (2).

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the comprehensive energy optimization scheduling method based on the SPEA-II algorithm as described in any one of claims 1 to 8 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the comprehensive energy optimization scheduling method based on the SPEA-II algorithm as claimed in any one of claims 1 to 8 is implemented.

Images