Multi-energy power generation system optimal configuration method based on genetic algorithm

Abstract

The invention discloses a multi-energy power generation system optimization configuration method based on a genetic algorithm, and the method comprises the following steps: constructing a wind power, photovoltaic, thermal power and energy storage complementary power generation system model, calculating the initial investment cost apportionment, the operation maintenance cost, the thermal power fuel total cost and the equipment replacement cost apportionment of the power generation system model, and determining the annual value AC of project cost; calculating a wind curtailment and light curtailment rate and a green electricity proportion, setting constraint conditions, and optimizing the power generation system model through a genetic algorithm; according to the method, the limitation of fixed-proportion configuration of each energy in a traditional mode is broken through, and dynamic optimal configuration of energy storage and thermal power capacity is realized for a wind-solar-thermal storage integrated project; through a multi-energy cooperative power supply mode, an energy storage system plays a regulating role to stabilize power supply, wind and light clean energy is preferentially utilized, and meanwhile, stable and reliable operation of a power grid is guaranteed by combining wind and light abandoning rate and green power proportion constraint control.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power generation system configuration optimization method, and relates to a multi-energy power generation system optimization configuration method based on a genetic algorithm. BACKGROUND

[0002] With large-scale grid connection of new energy, a wind-solar-thermal-storage integrated system has become an important direction of energy transformation, and the optimization configuration of the system is crucial for power supply reliability, energy utilization rate and reduction of construction and operation cost of the system. However, the traditional optimization method has problems of low calculation efficiency and insufficient optimization precision in large-scale projects. The existing technology usually adopts fixed proportion configuration of energy storage and thermal power, which is difficult to dynamically balance economy and stability, and does not fully consider the randomness of wind-solar power generation and grid constraint conditions. In actual operation, the intermittency and volatility of new energy power generation make it difficult to maintain power balance of the power system, and the phenomenon of curtailment of wind and solar power is still serious, which not only causes waste of energy, but also increases the operation cost and risk of the power system. In addition, the capacity optimization configuration of multi-energy has not found an efficient and accurate method to maximize the system benefit. At present, most of the researches are concentrated on the optimization configuration of single energy, and there are still certain limitations for the collaborative optimization configuration among multiple energies. SUMMARY

[0003] The purpose of the application is to provide a multi-energy power generation system optimization configuration method based on a genetic algorithm, which solves the problem that the optimization method in the prior art does not fully consider the randomness of wind-solar power generation and grid constraint conditions.

[0004] The technical scheme adopted by the application is a multi-energy power generation system optimization configuration method based on a genetic algorithm, which comprises the following steps: Step 1: constructing a power generation system model complementary to wind power, photovoltaic power, thermal power and energy storage; Step 2: calculating the initial investment cost allocation, operation and maintenance cost, total fuel cost of thermal power and equipment replacement cost allocation of the power generation system model, and determining the annual value of project cost AC ; Step 3: calculating the curtailment rate of wind and solar power and the proportion of green electricity , and setting constraint conditions; Step 4: optimizing the power generation system model by a genetic algorithm.

[0005] The application has the following characteristics: The power generation system model in step 1 includes a wind-solar coupling power generation model, an energy storage battery model and a thermal power model.

[0006] The coupling power generation power of the wind-solar coupling power generation model is:

[0007] Pcoupled is the coupled power, kW; Ppv is the photovoltaic generator output power, kW; Pwind is the wind turbine output power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power Pcoupled is the coupled power

[0008] Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; 2 Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW;

[0009] Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; 2 Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW;

[0010] Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW; Pcoupled is the coupled power, kW;

[0011] Pcoupled is the coupled power, kW; t charging process during a period of time

[0012] t Periodic discharge process

[0013] in, , The first t Passing the exam t -1 period of energy storage battery capacity, kWh; for t The sum of electricity generated by photovoltaic power generation units and wind power generation units during the same period, in kWh; for t The system's electrical load demand during a given time period, in kWh; The inverter's conversion efficiency is % The charging efficiency of energy storage batteries, % The discharge efficiency of the energy storage battery is % %. The maximum charging and discharging power and state of charge constraints of the energy storage battery satisfy:

[0014]

[0015] in, This is the minimum constraint on the energy storage battery capacity, set to 10%. For the capacity of energy storage batteries t Time constraints; To constrain the maximum capacity of the energy storage battery, a value of 90% is set. The minimum charging power for the energy storage battery is set to 0.2. ; This represents the minimum discharge power of the energy storage battery, and is set to 0.2. ; The maximum charging power for the energy storage battery is set to 0.9. ; This represents the maximum discharge power of the energy storage battery, and is set to 0.9. .

[0016] The thermal power model is as follows:

[0017] in, The power generation capacity of thermal power plants is expressed in W. For power generation efficiency, % The flow rate of fuel is expressed in kg / s. for the heat value of the fuel, J / kg; for the acceleration of gravity, taking the value 9.8 m / s 2 .

[0018] Step 2 is performed according to the following steps: Step 2.1, calculation of the initial investment cost allocation of the power generation system model :

[0019]

[0020] wherein, is the total investment cost of the wind power, A is the annuity, P is the present value, is the service life of the power generation equipment, is the discount rate, is the annual allocation cost of the wind power, is the total investment cost of the photovoltaic, is the service life of the photovoltaic equipment, is the annual allocation cost of the photovoltaic, is the total investment cost of the thermal power, is the service life of the thermal power equipment, is the annual allocation cost of the thermal power, is the total investment cost of the energy storage, is the service life of the energy storage equipment, is the annual allocation cost of the energy storage; Step 2.2, calculation of the operation and maintenance cost of the power generation system model :

[0021] wherein: is the annual maintenance cost per unit installed capacity of the power generation equipment, is the unit installed capacity of the power generation equipment, is the annual maintenance cost per unit installed capacity of the photovoltaic equipment, is the unit installed capacity of the photovoltaic equipment, is the annual maintenance cost per unit installed capacity of the thermal power equipment, is the unit installed capacity of the thermal power equipment, is the annual maintenance cost per unit installed capacity of the energy storage equipment, is the unit installed capacity of the energy storage equipment; Step 2.3, calculation of the total fuel cost of the thermal power :

[0022] wherein: is the power generation efficiency, Annual generation capacity, Fuel unit price; Step 2.4, calculate the cost allocation of equipment replacement :

[0023]

[0024]

[0025]

[0026]

[0027] Wherein: Wind power equipment replacement cost allocation, Wind power equipment replacement period, Annual allocation of wind power, Photovoltaic equipment replacement cost allocation, Photovoltaic equipment replacement period, Annual allocation of photovoltaic, Thermal power equipment replacement cost allocation, Thermal power equipment replacement period, Annual allocation of thermal power, Energy storage replacement cost allocation, Energy storage equipment replacement period, Annual allocation of energy storage; The annual value of project cost is:

[0028] Wherein The annual value of project cost.

[0029] Step 3 is as follows: Step 3.1, encode the energy storage capacity and thermal power installed capacity, and each individual is represented as a two-dimensional vector[ , ] Wherein Indicates the energy storage capacity, Indicates the thermal power installed capacity, randomly generate individuals with population size In the value range of energy storage capacity and thermal power installed capacity, form the initial population; Step 3.2, collect wind and photovoltaic installed capacity, generation cost, energy storage construction cost, thermal power generation and fuel cost, and grid load demand data, calculate wind and photovoltaic generation capacity in different time periods combined with meteorological data, and calculate the wind and light rejection rate according to the grid load:

[0030] wherein, is the abandoned wind and light rate, is the abandoned wind power of the wind power generation system, is the theoretical wind power generation of the wind power generation system, is the abandoned light power of the photovoltaic power generation system, is the theoretical photovoltaic power generation of the photovoltaic power generation system; the constraint condition is set as: not more than , is the maximum allowable abandoned wind and light rate; the green electricity proportion is calculated as:

[0031] wherein, is the green electricity proportion, is the wind power generation, is the photovoltaic power generation, is the total power generation of the power generation system model; the constraint condition is set as: not more than the individual not meeting the constraint is given a maximum cost annual value by the penalty function method.

[0032] Step 4 is performed according to the following steps: Step 4.1, taking the cost annual value as the optimization target, the fitness function is: according to the roulette selection, the selection probability of the individual is calculated as: the roulette is rotated for multiple times, and the individuals entering the next generation population are determined according to the roulette position; the tournament selection is performed, and individuals are randomly selected each time to compete, and the one with the highest fitness is selected to enter the next generation, and the selection is repeated for multiple times to complete the selection; Step 4.2, two individuals are selected as parents according to a certain crossover probability, and a random number is generated for the parent individuals , , the child individual , is generated by linear combination between the coding vectors of the two parent individuals; Step 4.3, the individual is mutated according to a certain mutation probability, and for each individual needing mutation , the mutation is performed on and in their respective value ranges, the mutation range of the energy storage capacity is set as , the mutation range of the thermal power installed capacity is set as , and new values are randomly generated in the respective mutation ranges to replace the original and , get the individual after variation; Step 4.4, set the maximum number of iterations, when the average fitness value of the population of several generations in succession changes less than a certain threshold, the algorithm is considered to converge, and the iteration is terminated, if the termination condition is not met, return to step 4.1, continue iteration optimization, after the algorithm is terminated, select the individual with the highest fitness value in the final population and decode it into the corresponding energy storage capacity and thermal power capacity.

[0033] The beneficial effects of the present application are: The present application focuses on a multi-energy complementary power generation system, deeply explores the output characteristics, complementary mechanism and capacity optimization configuration of each energy, builds a detailed power generation system model, simulates the power generation process of multi-energy at different time scales, analyzes the power dynamic balance change rule, and uses genetic algorithm to explore the optimal capacity ratio of wind power, photovoltaic, energy storage and thermal power with the annual cost as the optimization target, breaks through the limitations of fixed proportion configuration of each energy in traditional way, realizes dynamic optimization configuration of energy storage and thermal power capacity for large-scale wind-solar-thermal-storage integrated project, effectively solves the optimization problem of capacity ratio; taking the minimum of the annual cost of the whole life cycle of the project as the target, considering various factors such as initial investment cost allocation, operation and maintenance cost, fuel cost and equipment replacement cost, accurately optimizing the capacity of each energy component, effectively reducing the annual cost of the project, and significantly improving the economic benefit; through the multi-energy collaborative power supply mode, the energy storage system plays a regulating role to stabilize the power supply, preferentially uses wind-solar-clean energy, and combines the abandoned wind and light rate and green electricity ratio constraint control, which not only guarantees the stable and reliable operation of the power grid, but also meets the environmental protection requirements; genetic algorithm has strong global optimization ability and can avoid falling into local optimal solution; the wind-solar capacity is fixed in advance, which effectively reduces the dimension of optimization variables and greatly improves the calculation efficiency; by determining the wind-solar installed capacity in advance, the genetic algorithm is used to optimize the ratio of energy storage and thermal power to minimize the annual cost, and the penalty function is used to handle the abandoned wind and light rate and green electricity ratio constraint, which has good compatibility for multiple constraints, and significantly improves the economy and calculation efficiency of large-scale wind-solar-thermal-storage integrated project. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 is the architecture diagram of the multi-energy power generation system based on genetic algorithm in the present application; Figure 2 is the coordination optimization simulation flow chart of the power generation system in the present application; Figure 3 is the flow chart of the genetic algorithm in the present application. DETAILED DESCRIPTION

[0035] The present application will be described in detail below in combination with the drawings and specific embodiments.

[0036] The genetic algorithm-based multi-energy power generation system optimization configuration method comprises the following steps: Step 1: Construct a wind power, photovoltaic, thermal power and energy storage complementary power generation system model, see Figure 1 The power generation system model includes a wind-solar coupling power generation model, an energy storage battery model and a thermal power model, comprehensively covering the output characteristics and complementary relationship of wind power, photovoltaic power, thermal power and energy storage; The coupling power generation power of the wind-solar coupling power generation model is:

[0037] Wherein, is the coupling power generation power, kW; is the output power of the photovoltaic generator set, kW; is the output power of the wind turbine, kW; The coupling power generation power is:

[0038] Wherein, is the derating factor, taking a value of 0.95; is the installed capacity, kW; is the solar radiation intensity at the ambient temperature, kW / m 2 ; is the power temperature coefficient, taking a value of -0.005% / ℃; is the actual working temperature of the photovoltaic cell, ℃; is the working temperature under standard test conditions, taking a value of 25℃; is:

[0039] Wherein, is the ambient temperature of the photovoltaic panel, ℃; is the surface temperature of the photovoltaic generator set under the rated operating conditions, taking a value of 45℃-48℃; is the ambient temperature of the photovoltaic generator set under the rated operating conditions, taking a value of 20℃; is the solar radiation intensity of the photovoltaic generator set under the rated operating conditions, taking a value of 800W / m 2 ; is the efficiency at the maximum power position under the standard test conditions, taking a value of 0.15; is the solar energy absorption rate, taking a value of 0.9; is the solar energy transmittance of the cover, taking a value of 0.9; The output power of the wind turbine is:

[0040] where, is the cut-in wind speed, m / s; is the cut-out wind speed, m / s; is the rated wind speed of the wind turbine, m / s; is the real-time wind speed, m / s; is the wind turbine power characteristic function; is the installed capacity of the wind turbine generator system; The charging and discharging process of the energy storage battery model is: t Period charging process

[0041] t Period discharging process

[0042] where, , are the energy storage battery energy of the first t and the first t -1 period, kWh; is the sum of the PV and wind turbine generation of the t period, kWh; is the demand of the system electrical load of the t period, kWh; is the conversion efficiency of the inverter, %; is the charging efficiency of the energy storage battery, %; is the discharging efficiency of the energy storage battery, %; The maximum charging and discharging power and state of charge constraints of the energy storage battery satisfy:

[0043]

[0044] where, is the minimum constraint of the energy storage battery capacity, taking the value of 10%; is the t period constraint of the energy storage battery capacity; is the maximum constraint of the energy storage battery capacity, taking the value of 90%; is the minimum value of the energy storage battery charging power, taking the value of 0.2 ; is the minimum value of the energy storage battery discharging power, taking the value of 0.2 ; is the maximum value of the energy storage battery charging power, taking the value of 0.9 ; is the maximum value of the energy storage battery discharging power, taking the value of 0.9 ; The thermal power model is:

[0045] wherein, is the thermal power generation, W; is the power generation efficiency, %; is the flow rate of fuel, kg / s; is the heat value of fuel, J / kg; is the gravitational acceleration, taking 9.8 m / s 2 ; The power generation system model aims to efficiently meet the power grid load demand. In terms of operation strategy, given the wide distribution and short construction period of light resources, photovoltaic power supply mode is preferred. When the photovoltaic power generation capacity is sufficient, stable power can be transmitted to the power grid to undertake the main power supply task. If insufficient light leads to insufficient photovoltaic power generation capacity, the power generation system model will quickly switch to wind power supply to make full use of wind resources to fill the power gap. At the same time, the energy storage system plays a key role in regulating the power generation. When photovoltaic and wind power generation is surplus, it stores excess power to reserve energy for subsequent power consumption peaks. When photovoltaic and wind power generation are both insufficient to guarantee the power grid load, the energy storage system immediately releases the stored power to maintain stable power supply. If the above allocation still cannot meet the entire power grid load demand, thermal power will accurately supplement the missing power load according to the power shortage. Through this layer-by-layer progressive and complementary power supply mode, the power grid can be reliably operated in all directions, the energy utilization efficiency is maximized, and diversified power consumption demand is met. In actual operation, the power components of the multi-energy power generation system are affected by various factors, such as wind-solar coupling output, which is closely related to local climate, light, wind, and complementary characteristics. Good weather and stable wind can meet part of the load, while rainy days or windless periods can significantly reduce the output. The energy storage power is affected by device type, capacity, charging and discharging efficiency, and SOC. The thermal power output is flexible, but is limited by fuel, start-up and shutdown costs, and environmental protection requirements. The real-time power of the power grid load has time variability, and the power generation and energy storage units need to track the load dynamics in real time to maintain power balance, as shown in Figure 2 , which is expressed as:

[0046] In the formula: , , , , are the real-time powers of the wind-solar coupling output, energy storage discharge, thermal power output, energy storage charging, and electrical load of the multi-energy power generation system at t ; Step 2: Calculate the initial investment cost allocation of the power generation system model :

[0047]

[0048] wherein, is the total investment cost of wind power, A is the annual payment, P is the present value, is the service life of power generation equipment, is the discount rate, is the annual allocation cost of wind power, is the total investment cost of photovoltaic, is the service life of photovoltaic equipment, is the annual allocation cost of photovoltaic, is the total investment cost of thermal power, is the service life of thermal power equipment, is the annual allocation cost of thermal power, is the total investment cost of energy storage, is the service life of energy storage equipment, is the annual allocation cost of energy storage; Calculate the operation and maintenance cost of the power generation system model :

[0049] wherein: is the annual maintenance cost per unit installed capacity of power generation equipment, is the unit installed capacity of power generation equipment, is the annual maintenance cost per unit installed capacity of photovoltaic equipment, is the unit installed capacity of photovoltaic equipment, is the annual maintenance cost per unit installed capacity of thermal power equipment, is the unit installed capacity of thermal power equipment, is the annual maintenance cost per unit installed capacity of energy storage equipment, is the unit installed capacity of energy storage equipment; Calculate the total fuel cost of thermal power :

[0050] wherein: is the power generation efficiency, is the annual power generation, is the unit price of fuel; Calculate the equipment replacement cost allocation :

[0051]

[0052]

[0053]

[0054]

[0055] wherein: is the wind power equipment replacement cost allocation, is the wind power equipment replacement period, is the wind power annual allocation cost, is the photovoltaic equipment replacement cost allocation, is the photovoltaic equipment replacement period, is the photovoltaic annual allocation cost, is the thermal power equipment replacement cost allocation, is the thermal power equipment replacement period, is the thermal power annual allocation cost, is the energy storage replacement cost allocation, is the energy storage equipment replacement period, is the energy storage annual allocation cost; the project cost annual value is:

[0056] wherein is the project cost annual value; the optimization target aims to reduce the cost annual value to the greatest extent under the premise of ensuring stable power supply of the multi-energy power generation system and meeting the power grid load demand by fine adjustment of the capacity of each energy component, so as to realize economic optimization in the whole life cycle, which needs to comprehensively consider many factors such as initial investment cost allocation, operation and maintenance cost, fuel cost, equipment replacement cost allocation (part of key components), and provide clear and explicit direction for the subsequent optimization process; Step 3: Encode the energy storage capacity and thermal power installed capacity, and each individual is represented as a two-dimensional vector [ , ], wherein represents the energy storage capacity, represents the thermal power installed capacity, and a population size of individuals are randomly generated in the value range of the energy storage capacity and the thermal power installed capacity to form an initial population; Collect wind and photovoltaic installed capacity, power generation cost, energy storage construction cost, thermal power generation and fuel cost, and power grid load demand data, calculate wind and photovoltaic power generation in different time periods combined with meteorological data, and calculate the wind and light rejection rate according to the power grid load:

[0057] wherein, For wind and solar curtailment rates, This refers to the amount of wind power curtailed by wind power generation systems. This represents the theoretical power generation of the wind power system. This refers to the amount of solar power curtailed by photovoltaic power generation systems. The theoretical power generation of the photovoltaic power generation system; set constraints: No more than , The maximum permissible wind and solar curtailment rate; Calculate the proportion of green electricity:

[0058] in, For the proportion of green electricity, For wind power generation, For photovoltaic power generation, Set the total power generation of the power generation system model; set the constraints: No more than Individuals that do not meet the constraints are assigned a maximum annual cost value through the penalty function method; considering the key boundary conditions of actual operation, the wind and solar curtailment rate is limited to no more than 40% to ensure the efficient use of energy, avoid unnecessary waste, and ensure that the proportion of green electricity is no less than 75%, which is in line with the trend of clean energy development and environmental protection requirements. Step 4: See Figure 3 With annual cost as the optimization objective, the fitness function is: The probability of an individual's choice is calculated based on the roulette wheel selection: The roulette wheel is spun multiple times to determine which individuals will enter the next generation of the population; a tournament selection process is then conducted, with individuals randomly selected each time. Individuals compete to select the one with the highest fitness to enter the next generation, and this selection is repeated multiple times. Two individuals are selected as parents with a certain crossover probability. For the parent individuals... and Generate a random number , offspring individuals , A new offspring individual is generated by linearly combining the encoding vectors of two parent individuals. Individuals are mutated with a certain mutation probability. For each individual that needs to be mutated... Within its range of values, respectively for and Let the variation range of energy storage capacity be denoted as follows: The range of variation in thermal power installed capacity is Within their respective mutation ranges, new values ​​are randomly generated to replace the original ones. and , get the individual after mutation; Set the maximum number of iterations, when the average fitness value of the population of consecutive generations changes less than a certain threshold, the algorithm is considered to converge, terminate iteration, if the termination condition is not met, return to the fitness function calculation step, continue iteration optimization, after the algorithm terminates, select the individual with the highest fitness value in the final population and decode it into the corresponding energy storage capacity and thermal power capacity.

[0059] The power generation system model has obvious seasonal advantages. In winter and spring, wind and light are limited, energy storage starts less, and thermal power bears the main power supply guarantee for the stability of the power grid. In summer and autumn, wind and light are abundant, photovoltaic is dominant, wind power is auxiliary, energy storage is frequently adjusted, and thermal power is reserved to maintain supply and demand balance. Due to the inherent intermittency and randomness of wind energy and solar energy, their output fluctuates violently, and it is difficult to accurately match the power grid load demand, often with large deviations, leading to frequent wind and light curtailment, seriously affecting energy utilization efficiency and power supply reliability. The present application realizes the optimal allocation and collaborative operation of energy through the multi-energy complementary mechanism. The energy storage system effectively suppresses the volatility of wind and light generation, and the flexible adjustment of thermal power further enhances its ability to cope with extreme working conditions and load mutations. The power generation system model can dynamically adjust the output proportion of each energy according to the real-time load demand of the power grid, realize stable, efficient and sustainable power supply, greatly improve the energy utilization efficiency and grid accommodation capacity, and provide a reliable solution for energy transformation and stable operation of the power system, which highlights the important value and broad application prospect in the modern energy system. The present application is used to optimize a certain base project. The original scheme configuration is photovoltaic 7.5 million kW, wind power 3.5 million kW, energy storage capacity 2 million kWh, and thermal power capacity 4 million kW. The photovoltaic and wind power capacity is fixed. After optimizing the energy storage and thermal power capacity, the energy storage capacity is 2 million kWh, and the thermal power capacity is 3,557.74 million kW. The results show that under the condition of green electricity ratio of 78.59% and wind and light curtailment rate of 37.19%, the annual cost is reduced by 3.2% compared with the traditional method, and the battery annual charge and discharge frequency is reduced to 510 times, which fully verifies its economy and practicality.

[0060] Example 1: The multi-energy power generation system optimization configuration method based on genetic algorithm comprises the following steps: Step 1: Construct a power generation system model of wind power, photovoltaic, thermal power and energy storage complementation, which includes a wind-light coupled power generation model, an energy storage battery model and a thermal power model; Step 2: Calculate the initial investment cost allocation, operation and maintenance cost, total fuel cost of thermal power and equipment replacement cost allocation of the power generation system model to determine the annual project cost AC ; Step 3: Encode the energy storage capacity and thermal power capacity, and each individual is represented as a two-dimensional vector , ],wherein represents the energy storage capacity, represents the thermal power installed capacity, and a population size of individuals is randomly generated within the value range of the energy storage capacity and the thermal power installed capacity to form an initial population; The wind power and photovoltaic installed capacity, power generation cost, energy storage construction cost, thermal power generation and fuel cost, and power grid load demand data are collected, and the wind power and photovoltaic power generation in different time periods is calculated in combination with meteorological data, and the wind and light curtailment rate is calculated according to the power grid load:

[0061] wherein, is the wind and light curtailment rate, is the wind power curtailment amount of the wind power generation system, is the theoretical power generation amount of the wind power generation system, is the light curtailment amount of the photovoltaic power generation system, is the theoretical power generation amount of the photovoltaic power generation system; the constraint condition is set as: not more than , is the maximum allowed wind and light curtailment rate; The green electricity proportion is calculated as:

[0062] wherein, is the green electricity proportion, is the wind power generation amount, is the photovoltaic power generation amount, is the total power generation amount of the power generation system model; the constraint condition is set as: not more than , and the individual not meeting the constraint is given a maximum cost value per year by the penalty function method; Step 4: Taking the cost value per year as the optimization target, the fitness function is: , and the selection probability of the individual is calculated according to the roulette selection: , the roulette is rotated multiple times, and the individual entering the next generation population is determined according to the roulette position; the tournament selection is performed, and individuals are randomly selected each time to compete, and the one with the highest fitness enters the next generation, and the selection is repeated multiple times to complete the selection; Two individuals are selected as parents at a certain crossover probability, and a random number is generated for the parent individuals and , , and the child individual , is generated by linear combination between the coding vectors of the two parent individuals. mutate the individual with a mutation probability, for each individual that needs to be mutated , respectively, within their value ranges , and , respectively, within their value ranges, let the mutation range of the energy storage capacity be , and the mutation range of the thermal power installed capacity be , randomly generate new values within the respective mutation ranges, replace the original and , to obtain the mutated individual; set a maximum number of iterations, when the average fitness value of the population of consecutive generations changes by less than a certain threshold, consider the algorithm to have converged, terminate the iteration, if the termination condition is not met, return to the fitness function calculation step and continue the iteration optimization, after the algorithm terminates, select the individual with the highest fitness value in the final population and decode it into the corresponding energy storage capacity and thermal power installed capacity.

[0063] Example 2: The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm includes the following steps: Step 1: Construct a wind power, photovoltaic, thermal power, and energy storage complementary power generation system model, the power generation system model includes a wind-solar coupling power generation model, an energy storage battery model, and a thermal power model; Step 2: Calculate the initial investment cost allocation of the power generation system model :

[0064]

[0065] wherein, is the total investment cost of wind power, A is the annuity, P is the present value, is the service life of the power generation equipment, is the discount rate, is the annual allocation cost of wind power, is the total investment cost of photovoltaic, is the service life of the photovoltaic equipment, is the annual allocation cost of photovoltaic, is the total investment cost of thermal power, is the service life of the thermal power equipment, is the annual allocation cost of thermal power, is the total investment cost of energy storage, is the service life of the energy storage equipment, is the annual allocation cost of energy storage; Calculate the operation and maintenance cost of the power generation system model :

[0066] wherein: is the annual maintenance cost per unit installed capacity of the power generation equipment, is the unit installed capacity of the power generation equipment, is the annual maintenance cost per unit installed capacity of the photovoltaic equipment, is the unit installed capacity of the photovoltaic equipment, is the annual maintenance cost per unit installed capacity of the thermal power equipment, is the unit installed capacity of the thermal power equipment, is the annual maintenance cost per unit installed capacity of the energy storage equipment, is the unit installed capacity of the energy storage equipment; calculating the total fuel cost of thermal power :

[0067] wherein: is the power generation efficiency, is the annual power generation, is the unit price of fuel; calculating the cost allocation of equipment replacement :

[0068]

[0069]

[0070]

[0071]

[0072] wherein: is the cost allocation of wind power equipment replacement, is the replacement period of wind power equipment, is the annual allocation of wind power, is the cost allocation of photovoltaic equipment replacement, is the replacement period of photovoltaic equipment, is the annual allocation of photovoltaic, is the cost allocation of thermal power equipment replacement, is the replacement period of thermal power equipment, is the annual allocation of thermal power, is the cost allocation of energy storage replacement, is the replacement period of energy storage equipment, is the annual allocation of energy storage; the annual value of the project cost is:

[0073] wherein The project cost annual value is calculated; Step 3: Calculate the wind and light abandonment rate And the green electricity proportion And set the constraint condition; Step 4: Take the cost annual value as the optimization target, and the fitness function is: According to the roulette selection, the selection probability of the individual is calculated: Multiple rotations of the roulette are performed, and the individuals entering the next generation population are determined according to the roulette position; tournament selection is performed, and each time Individuals are randomly selected for competition, and the one with the highest fitness enters the next generation; the selection is repeated multiple times to complete the selection; two individuals are selected as parents with a certain crossover probability, and for the parent individuals And A random number , , the child individual , Linear combination is performed between the coding vectors of the two parent individuals to generate a new child individual; The individual is mutated with a certain mutation probability, and for each individual that needs to be mutated , the values of And are mutated within their respective value ranges, the mutation range of the energy storage capacity is set as , and the mutation range of the thermal power installed capacity is set as New values are randomly generated within the respective mutation ranges to replace the original And , and the mutated individual is obtained; The maximum number of iterations is set, when the average fitness value of the population of consecutive generations changes less than a certain threshold, it is considered that the algorithm converges, and the iteration is terminated, if the termination condition is not met, the fitness function calculation step is returned, and the iteration optimization is continued, after the algorithm is terminated, the individual with the highest fitness value in the final population is selected and decoded into the corresponding energy storage capacity and thermal power installed capacity.

[0074] Example 3 The multi-energy power generation system optimization configuration method based on the genetic algorithm comprises the following steps: Step 1: Construct a wind power, photovoltaic, thermal power and energy storage complementary power generation system model, the power generation system model comprises a wind-solar coupling power generation model, an energy storage battery model and a thermal power model; Step 2: Calculate the initial investment cost allocation of the power generation system model :

[0075]

[0076] Among them, Total investment cost of wind power, A Annual payment, P Present value, Service life of power generation equipment, Discount rate, Annual amortization of wind power, Total investment cost of photovoltaic, Service life of photovoltaic equipment, Annual amortization of photovoltaic, Total investment cost of thermal power, Service life of thermal power equipment, Annual amortization of thermal power, Total investment cost of energy storage, Service life of energy storage equipment, Annual amortization of energy storage; Calculate the operation and maintenance cost of the power generation system model :

[0077] Where: Annual maintenance cost per unit installed capacity of power generation equipment, Unit installed capacity of power generation equipment, Annual maintenance cost per unit installed capacity of photovoltaic equipment, Unit installed capacity of photovoltaic equipment, Annual maintenance cost per unit installed capacity of thermal power equipment, Unit installed capacity of thermal power equipment, Annual maintenance cost per unit installed capacity of energy storage equipment, Unit installed capacity of energy storage equipment; Calculate the total cost of thermal power fuel :

[0078] Where: Power generation efficiency, Annual power generation, Unit price of fuel; Calculate equipment replacement cost allocation :

[0079]

[0080]

[0081]

[0082]

[0083] wherein: is the wind power equipment replacement cost allocation, is the wind power equipment replacement period, is the wind power annual allocation cost, is the photovoltaic equipment replacement cost allocation, is the photovoltaic equipment replacement period, is the photovoltaic annual allocation cost, is the thermal power equipment replacement cost allocation, is the thermal power equipment replacement period, is the thermal power annual allocation cost, is the energy storage replacement cost allocation, is the energy storage equipment replacement period, is the energy storage annual allocation cost; the project cost annual value is:

[0084] wherein is the project cost annual value; Step 3: Encode the energy storage capacity and thermal power installed capacity, and each individual is represented as a two-dimensional vector , ] wherein represents the energy storage capacity, represents the thermal power installed capacity, randomly generate a population size of individuals within the value range of the energy storage capacity and the thermal power installed capacity to form an initial population; Collect wind and photovoltaic installed capacity, power generation cost, energy storage construction cost, thermal power generation and fuel cost, and grid load demand data, calculate wind and photovoltaic power generation in different time periods combined with meteorological data, and calculate the wind and light curtailment rate according to the grid load:

[0085] wherein, is the wind and light curtailment rate, is the wind power system wind curtailment, is the wind power system theoretical power generation, is the photovoltaic power system light curtailment, is the photovoltaic power system theoretical power generation; Set the constraint condition: not more than , is the maximum allowed wind and light curtailment rate; Calculate the green power ratio:

[0086] wherein, Green electricity proportion, Wind power generation, Photovoltaic power generation, Total power generation of the power generation system model; Set constraints: No more than Individuals that do not meet the constraints are given a maximum cost value through the penalty function method; Step 4: Optimize the power generation system model by genetic algorithm.

[0087] Example 4: The multi-energy power generation system optimization configuration method based on genetic algorithm includes the following steps: Step 1: Construct a power generation system model complementary to wind power, photovoltaic power, thermal power and energy storage, which includes a wind-solar coupling power generation model, an energy storage battery model and a thermal power model; The coupling power generation power of the wind-solar coupling power generation model is:

[0088] Wherein, The coupling power generation power is kW; The output power of the photovoltaic generator set is kW; The output power of the wind turbine is kW; The coupling power generation power is:

[0089] Wherein, The derating factor is 0.95; The installed capacity is kW; The solar radiation intensity at the ambient temperature is kW / m 2 ; The power temperature coefficient is -0.005% / ℃; The actual working temperature of the photovoltaic cell is ℃; The working temperature under standard test conditions is 25℃; is:

[0090] Wherein, The ambient temperature of the photovoltaic panel is ℃; The surface temperature of the photovoltaic generator set under rated operating conditions is 45-48℃; The ambient temperature of the photovoltaic generator set under rated operating conditions is 20℃; The solar radiation intensity of the photovoltaic generator set under rated operating conditions is 800W / m2 ; ηp is the efficiency of the maximum power position under standard test conditions, taking the value 0.15; ηs is the absorption rate of solar energy, taking the value 0.9; ηsh is the solar energy transmittance of the shading, taking the value 0.9; The output power of the wind turbine is:

[0091] wherein, Vci is the cut-in wind speed, m / s; Vco is the cut-out wind speed, m / s; Vr is the rated wind speed of the wind turbine, m / s; Vr is the real-time wind speed, m / s; Pw is the wind turbine power characteristic function; Pw is the installed capacity of the wind turbine generator set; The charging and discharging processes of the energy storage battery model are: t Period charging process

[0092] t Period discharging process

[0093] wherein, , are the energy storage battery capacity of the first t and the first t -1 period, kWh; Ppv is the sum of the photovoltaic generator and the wind turbine generator in the t period, kWh; Pd is the demand amount of the system electrical load in the t period, kWh; ηinv is the conversion efficiency of the inverter, %; ηb is the charging efficiency of the energy storage battery, %; ηb is the discharging efficiency of the energy storage battery, %; The maximum charging and discharging power and the state of charge constraint of the energy storage battery satisfy:

[0094]

[0095] wherein, Smin is the minimum constraint of the energy storage battery capacity, taking the value 10%; Smax is the t period constraint of the energy storage battery capacity; The maximum constraint of the energy storage battery capacity is 90%; The minimum value of the energy storage battery charging power is 0.2 ; The minimum value of the energy storage battery discharging power is 0.2 ; The maximum value of the energy storage battery charging power is 0.9 ; The maximum value of the energy storage battery discharging power is 0.9 ; The thermal power model is:

[0096] wherein, is the thermal power generation power, W; is the power generation efficiency, %; is the flow rate of fuel, kg / s; is the heat value of fuel, J / kg; is the gravitational acceleration, taking 9.8 m / s 2 ; Step 2: Calculate the initial investment cost allocation of the power generation system model, the operation and maintenance cost, the total cost of thermal power fuel and the equipment replacement cost allocation, and determine the annual value of the project cost AC ; Step 3: Calculate the wind and light abandonment rate and the proportion of green electricity , and set the constraint condition; Step 4: Take the annual cost as the optimization target, and the fitness function is: According to the roulette selection, the selection probability of the individual is calculated: , the wheel is rotated many times, and the individuals entering the next generation population are determined according to the wheel position; the tournament selection is performed, and individuals are randomly selected each time to compete, and the one with the highest fitness enters the next generation, and the selection is repeated many times to complete the selection; Two individuals are selected as parents at a certain crossover probability, and a random number is generated for the parent individuals , , , and the child individual , is generated by linear combination between the coding vectors of the two parent individuals; The individual is mutated at a certain mutation probability, and for each individual that needs to be mutated , the mutation is performed on and in their respective value ranges, and the mutation range of the energy storage capacity is , the variation range of the thermal power installed capacity is , a new value is randomly generated in the respective variation range to replace the original and , to obtain the mutated individual; The maximum number of iterations is set, when the average fitness value of the population of several generations in succession changes less than a certain threshold, it is considered that the algorithm converges, the iteration is terminated, if the termination condition is not met, the fitness function calculation step is returned, the iteration optimization is continued, after the algorithm is terminated, the individual with the highest fitness value in the final population is selected and decoded into the corresponding energy storage capacity and thermal power installed capacity.

[0097] Example 5: The multi-energy power generation system optimization configuration method based on the genetic algorithm comprises the following steps: Step 1: Construct a wind power, photovoltaic, thermal power and energy storage complementary power generation system model, the power generation system model includes a wind-solar coupling power generation model, an energy storage battery model and a thermal power model; The coupling power generation power of the wind-solar coupling power generation model is:

[0098] wherein, is the coupling power generation power, kW; is the photovoltaic generator set output power, kW; is the wind turbine output power, kW; The coupling power generation power is:

[0099] wherein, is the derating factor, taking the value 0.95; is the installed capacity, kW; is the solar radiation intensity at the ambient temperature, kW / m 2 ; is the power temperature coefficient, taking the value -0.005% / ℃; is the actual working temperature of the photovoltaic cell, ℃; is the working temperature under standard test conditions, taking the value 25℃; is:

[0100] wherein, is the ambient temperature of the photovoltaic panel, ℃; is the surface temperature of the photovoltaic generator set under the rated operating conditions, taking the value 45℃-48℃; is the ambient temperature of the photovoltaic generator set under the rated operating conditions, taking the value 20℃; 800 W / m2, which is the solar radiation intensity of the photovoltaic generator set under rated operating conditions 2 ; 0.15, which is the efficiency at the maximum power point under standard test conditions; 0.9, which is the solar absorption rate; 0.9, which is the solar transmittance of the cover; Wind turbine output power is:

[0101] wherein, is the cut-in wind speed, m / s; is the cut-out wind speed, m / s; is the rated wind speed of the wind turbine, m / s; is the real-time wind speed, m / s; is the wind turbine power characteristic function; is the installed capacity of the wind turbine generator set; The charging and discharging processes of the energy storage battery model are: t Period charging process

[0102] t Period discharging process

[0103] wherein, , are the energy storage battery energy of the first t and the first t -1 periods, kWh, respectively; is the sum of the photovoltaic generator set and the wind turbine generator set in the t period, kWh; is the demand of the system electrical load in the t period, kWh; is the conversion efficiency of the inverter, %; is the charging efficiency of the energy storage battery, %; is the discharging efficiency of the energy storage battery, %; The maximum charging and discharging power and the state of charge constraints of the energy storage battery satisfy:

[0104]

[0105] wherein, is the minimum constraint of the energy storage battery capacity, taking the value of 10%; For the capacity of energy storage batteries t Time constraints; To constrain the maximum capacity of the energy storage battery, a value of 90% is set. The minimum charging power for the energy storage battery is set to 0.2. ; This represents the minimum discharge power of the energy storage battery, and is set to 0.2. ; The maximum charging power for the energy storage battery is set to 0.9. ; This represents the maximum discharge power of the energy storage battery, and is set to 0.9. The thermal power model is as follows:

[0106] in, The power generation capacity of thermal power plants is expressed in W. For power generation efficiency, % The flow rate of fuel is expressed in kg / s. The calorific value of the fuel is expressed in J / kg. The acceleration due to gravity is taken as 9.8 m / s². 2 ; Step 2: Calculate the initial investment cost allocation, operation and maintenance costs, total thermal power fuel costs, and equipment replacement cost allocation for the power generation system model to determine the annual value of project expenses. AC ; Step 3: Encode the energy storage capacity and thermal power installed capacity, with each individual represented as a two-dimensional vector. , ],in Indicates energy storage capacity. This represents the installed capacity of thermal power plants. Within the range of values ​​for energy storage capacity and installed thermal power capacity, a population size is randomly generated. Individuals form the initial population; Collect data on wind and solar power installed capacity, power generation costs, energy storage construction costs, thermal power generation and fuel costs, and grid load demand. Combine this with meteorological data to calculate wind and solar power generation at different times, and calculate the wind and solar curtailment rate based on grid load.

[0107] in, For wind and solar curtailment rates, This refers to the amount of wind power curtailed by wind power generation systems. This represents the theoretical power generation of the wind power system. This refers to the amount of solar power curtailed by photovoltaic power generation systems. The theoretical power generation of the photovoltaic power generation system; set constraints: No more than , is the maximum allowed wind and light abandonment rate; Calculate the green electricity proportion:

[0108] wherein, is the green electricity proportion, is the wind power generation, is the photovoltaic power generation, is the total power generation of the power generation system model; Set the constraint condition: not more than Individuals that do not meet the constraint are given a maximum cost value per year by the penalty function method; Step 4: Optimize the power generation system model by genetic algorithm.

[0109] Embodiment 6: The multi-energy power generation system optimization configuration method based on genetic algorithm comprises the following steps: Step 1: Construct a power generation system model complementary to wind power, photovoltaic power, thermal power and energy storage, which includes a wind-solar coupling power generation model, an energy storage battery model and a thermal power model; The coupling power generation power of the wind-solar coupling power generation model is:

[0110] wherein, is the coupling power generation power, kW; is the photovoltaic generator set output power, kW; is the wind turbine output power, kW; The coupling power generation power is:

[0111] wherein, is the derating factor, taking a value of 0.95; is the installed capacity, kW; is the solar radiation intensity at the ambient temperature, kW / m 2 ; is the power temperature coefficient, taking a value of -0.005% / ℃; is the actual working temperature of the photovoltaic cell, ℃; is the working temperature under standard test conditions, taking a value of 25℃; is:

[0112] wherein, is the ambient temperature of the photovoltaic panel, ℃; The surface temperature of the photovoltaic generator set under rated operating conditions is 45℃-48℃. The ambient temperature of the photovoltaic generator set under rated operating conditions is taken as 20℃. The solar radiation intensity of the photovoltaic generator under rated operating conditions is taken as 800 W / m. 2 ; The efficiency at the maximum power position under standard test conditions is set to 0.15; The absorptivity of solar energy is 0.9. The solar transmittance of the shading material is taken as 0.9; Wind turbine output power for:

[0113] in, Cut-in wind speed, m / s; Cut-off wind speed, m / s; The rated wind speed of the wind turbine is in m / s; This is the real-time wind speed, in m / s; This is the power characteristic function of the wind turbine; This refers to the installed capacity of wind turbine generator sets; The charging and discharging process of the energy storage battery model is as follows: t charging process during the period

[0114] t Periodic discharge process

[0115] in, , The first t Passing the exam t -1 period of energy storage battery capacity, kWh; for t The sum of electricity generated by photovoltaic power generation units and wind power generation units during the same period, in kWh; for t The system's electrical load demand during a given time period, in kWh; The inverter's conversion efficiency is % The charging efficiency of energy storage batteries, % The discharge efficiency of the energy storage battery is % %. The maximum charging and discharging power and state of charge constraints of the energy storage battery satisfy:

[0116]

[0117] where, is the minimum constraint of the energy storage battery capacity, taking the value of 10%; is the maximum constraint of the energy storage battery capacity, t is the time period constraint; is the maximum constraint of the energy storage battery capacity, taking the value of 90%; is the minimum value of the energy storage battery charging power, taking the value of 0.2 ; is the minimum value of the energy storage battery discharging power, taking the value of 0.2 ; is the maximum value of the energy storage battery charging power, taking the value of 0.9 ; is the maximum value of the energy storage battery discharging power, taking the value of 0.9 ; The thermal power model is:

[0118] where, is the thermal power generation power, W; is the power generation efficiency, %; is the flow rate of fuel, kg / s; is the heat value of fuel, J / kg; is the gravitational acceleration, taking the value of 9.8 m / s 2 ; Step 2: Calculate the initial investment cost allocation of the power generation system model :

[0119]

[0120] where, is the total investment cost of wind power, A is the annuity, P is the present value, is the service life of the power generation equipment, is the discount rate, is the annual allocation cost of wind power, is the total investment cost of photovoltaic, is the service life of the photovoltaic equipment, is the annual allocation cost of photovoltaic, is the total investment cost of thermal power, is the service life of the thermal power equipment, is the annual allocation cost of thermal power, is the total investment cost of energy storage, is the service life of the energy storage equipment, is the annual allocation cost of energy storage; Calculate the operation and maintenance cost of the power generation system model :

[0121] wherein: is the annual maintenance cost per unit installed capacity of the power generation equipment, is the unit installed capacity of the power generation equipment, is the annual maintenance cost per unit installed capacity of the photovoltaic equipment, is the unit installed capacity of the photovoltaic equipment, is the annual maintenance cost per unit installed capacity of the thermal power equipment, is the unit installed capacity of the thermal power equipment, is the annual maintenance cost per unit installed capacity of the energy storage equipment, is the unit installed capacity of the energy storage equipment; Calculate the total cost of fuel for thermal power :

[0122] wherein: is the power generation efficiency, is the annual power generation, is the unit price of fuel; Calculate the cost allocation of equipment replacement :

[0123]

[0124]

[0125]

[0126]

[0127] wherein: is the wind power equipment replacement cost allocation, is the wind power equipment replacement period, is the annual allocation of wind power, is the photovoltaic equipment replacement cost allocation, is the photovoltaic equipment replacement period, is the annual allocation of photovoltaic, is the thermal power equipment replacement cost allocation, is the thermal power equipment replacement period, is the annual allocation of thermal power, is the energy storage replacement cost allocation, is the energy storage equipment replacement period, is the annual allocation of energy storage; The annual value of the project cost is:

[0128] wherein is the annual value of the project cost; Step 3: Calculate the wind and light abandonment rate and the green electricity proportion , and set the constraint condition; Step 4: Optimize the power generation system model by genetic algorithm.

Claims

1. A method for optimizing the configuration of multi-energy power generation systems based on genetic algorithms, characterized in that, Includes the following steps: Step 1: Construct a power generation system model that integrates wind power, photovoltaic power, thermal power, and energy storage; Step 2: Calculate the initial investment cost allocation, operation and maintenance costs, total thermal power fuel costs, and equipment replacement cost allocation for the power generation system model to determine the annual value of project expenses. AC ; Step 3: Calculate the wind and solar curtailment rate and the proportion of green electricity And set constraints; Step 4: Optimize the power generation system model using a genetic algorithm.

2. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 1, characterized in that, The power generation system model in step 1 includes a wind-solar coupled power generation model, an energy storage battery model, and a thermal power model.

3. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 2, characterized in that, The coupled power generation of the wind-solar power generation model is: in, The coupled power generation capacity is expressed in kW. The output power of the photovoltaic generator set is expressed in kW. The output power of the wind turbine is expressed in kW. Coupled power generation for: in, The factor for reducing the amount is set to 0.95; The installed capacity is expressed in kW. Solar radiation intensity at ambient temperature, kW / m² 2 ; This is the power temperature coefficient, with a value of -0.005% / ℃; The actual operating temperature of the photovoltaic cell is ℃; The operating temperature under standard test conditions is 25℃. for: in, The ambient temperature around the photovoltaic panel, in °C; The surface temperature of the photovoltaic generator set under rated operating conditions is 45℃-48℃. The ambient temperature of the photovoltaic generator set under rated operating conditions is taken as 20℃. The solar radiation intensity of the photovoltaic generator under rated operating conditions is taken as 800 W / m. 2 ; The efficiency at the maximum power position under standard test conditions is set to 0.

15. The absorptivity of solar energy is 0.

9. The solar transmittance of the shading material is taken as 0.9; Wind turbine output power for: in, Cut-in wind speed, m / s; Cut-off wind speed, m / s; The rated wind speed of the wind turbine is in m / s; This is the real-time wind speed, in m / s; This is the power characteristic function of the wind turbine; This refers to the installed capacity of wind turbine generator sets.

4. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 2, characterized in that, The charging and discharging process of the energy storage battery model is as follows: t charging process during a period of time t Periodic discharge process in, , The first t Passing the exam t -1 period of energy storage battery capacity, kWh; for t The sum of electricity generated by photovoltaic power generation units and wind power generation units during the same period, in kWh; for t The system's electrical load demand during a given time period, in kWh; The inverter's conversion efficiency is % The charging efficiency of energy storage batteries, % The discharge efficiency of the energy storage battery is % %. The maximum charging and discharging power and state of charge constraints of the energy storage battery satisfy: in, This is the minimum constraint on the energy storage battery capacity, set to 10%. For the capacity of energy storage batteries t Time constraints; To constrain the maximum capacity of the energy storage battery, a value of 90% is set. The minimum charging power for the energy storage battery is set to 0.

2. ; This represents the minimum discharge power of the energy storage battery, and is set to 0.

2. ; The maximum charging power for the energy storage battery is set to 0.

9. ; This represents the maximum discharge power of the energy storage battery, and is set to 0.

9. .

5. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 2, characterized in that, The thermal power model is as follows: in, The power generation capacity of thermal power plants is expressed in W. For power generation efficiency, % The flow rate of fuel is expressed in kg / s. The calorific value of the fuel is expressed in J / kg. The acceleration due to gravity is taken as 9.8 m / s². 2 .

6. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 1, characterized in that, Step 2 is performed as follows: Step 2.1, calculate the initial investment cost allocation for the power generation system model. : in, This represents the total investment cost of wind power. A For annuities, P For present value, For the lifespan of power generation equipment, The discount rate is... The cost of wind power is shared annually. The total investment cost of photovoltaic power. For the lifespan of photovoltaic equipment, The cost of photovoltaic power is shared annually. This represents the total investment cost of thermal power plants. For the service life of thermal power equipment, The costs of thermal power plants are shared annually. The total investment cost for energy storage, For the lifespan of energy storage equipment, The cost of energy storage is shared annually; Step 2.2: Calculate the operation and maintenance costs of the power generation system model. : in: The annual maintenance cost per unit installed capacity of power generation equipment. For the unit installed capacity of power generation equipment, Annual maintenance cost per unit installed capacity of photovoltaic equipment For photovoltaic equipment, the unit installed capacity Annual maintenance cost per unit installed capacity of thermal power equipment. For thermal power equipment, the unit installed capacity The annual maintenance cost per unit installed capacity of energy storage equipment. Unit installed capacity of energy storage equipment; Step 2.3, calculate the total cost of fuel for thermal power. : in: For power generation efficiency, Annual power generation This refers to the unit price of fuel. Step 2.4, calculate the cost allocation for equipment replacement. : in: To share the cost of replacing wind power equipment. This refers to the replacement cycle of wind power equipment. The cost of wind power is shared annually. To share the cost of replacing photovoltaic equipment. The replacement cycle for photovoltaic equipment. The cost of photovoltaic power is shared annually. To share the cost of replacing thermal power equipment. This refers to the replacement cycle of thermal power equipment. The costs of thermal power plants are shared annually. To share the cost of energy storage replacement, For the replacement cycle of energy storage equipment, The cost of energy storage is shared annually; The annual cost of the project is: in This represents the annual value of project costs.

7. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 1, characterized in that, Step 3 is performed as follows: Step 3.1: Encode the energy storage capacity and thermal power installed capacity, with each individual represented as a two-dimensional vector. , ],in Indicates energy storage capacity. This represents the installed capacity of thermal power plants. Within the range of values ​​for energy storage capacity and installed thermal power capacity, a population size is randomly generated. Individuals form the initial population; Step 3.2: Collect data on wind and solar power installed capacity, power generation costs, energy storage construction costs, thermal power generation and fuel costs, and grid load demand. Combine this with meteorological data to calculate wind and solar power generation at different times, and calculate the wind and solar curtailment rate based on grid load. in, For wind and solar curtailment rates, This refers to the amount of wind power curtailed by wind power generation systems. This represents the theoretical power generation of the wind power system. This refers to the amount of solar power curtailed by photovoltaic power generation systems. The theoretical power generation of the photovoltaic power generation system; set constraints: No more than , The maximum allowable wind and solar curtailment rate; Calculate the proportion of green electricity: in, For the proportion of green electricity, For wind power generation, For photovoltaic power generation, Set the total power generation of the power generation system model; set the constraints: No more than Individuals that do not meet the constraints are assigned a maximum cost annual value through the penalty function method.

8. The method for optimizing the configuration of a multi-energy power generation system based on a genetic algorithm according to claim 7, characterized in that, Step 4 is performed as follows: Step 4.1, with the annual cost as the optimization objective, the fitness function is: The probability of an individual's choice is calculated based on the roulette wheel selection: The roulette wheel is spun multiple times to determine which individuals will enter the next generation of the population; a tournament selection process is then conducted, with individuals randomly selected each time. Individuals compete to select the one with the highest fitness to enter the next generation, and this selection is repeated multiple times. Step 4.2: Select two individuals as parents with a certain crossover probability. For the parent individuals... and Generate a random number , offspring individuals , A new offspring individual is generated by linearly combining the encoding vectors of two parent individuals. Step 4.3: Mutate the individuals with a certain mutation probability. For each individual that needs to be mutated... Within its range of values, respectively for and Let the variation range of energy storage capacity be denoted as follows: The range of variation in thermal power installed capacity is Within their respective mutation ranges, new values ​​are randomly generated to replace the original ones. and This yields the mutated individual; Step 4.4: Set the maximum number of iterations. When the average fitness value of the population changes less than a certain threshold for several consecutive generations, the algorithm is considered to have converged and the iteration is terminated. If the termination condition is not met, return to step 4.1 and continue iterative optimization. After the algorithm terminates, select the individual with the highest fitness value from the final population and decode it into the corresponding energy storage capacity and thermal power installed capacity.

Images