Virtual power plant optimization scheduling method based on machine learning

Abstract

The invention belongs to the field of power system optimization scheduling, and particularly relates to a virtual power plant optimization scheduling method based on machine learning. Firstly, real-time data such as generating capacity and load demand of a distributed power supply, an energy storage device and a load management system in a virtual power plant are collected, cleaned and standardized; then, a comprehensive objective function is constructed, and multiple factors including economic benefits, environmental benefits and electricity market price fluctuation are covered; then, an improved NSGA-II algorithm is adopted for optimization, a dual selection mechanism is combined with local and global optimality to accelerate convergence, crowding degree measurement is improved to accurately evaluate individuals, and self-adaptive crossover and mutation operation is dynamically adjusted according to a population. Through the method, maximum balance of economic benefits and environmental benefits can be realized, equipment operation constraints are met, the operation efficiency and stability of the virtual power plant are improved, and an innovative scheme is provided for optimization of a power system.

Description

Technical Field

[0001] The present invention belongs to the field of power system optimization and scheduling, and in particular relates to a virtual power plant optimization and scheduling method based on machine learning. Background Art

[0002] Against the backdrop of accelerating energy transformation and electricity marketization, virtual power plants have emerged as a new model for integrating and optimizing power resources. The power system faces many challenges. For example, the large-scale access of distributed energy reduces the stability and controllability of power supply. The intermittent and volatile nature of its power generation easily leads to problems such as grid frequency and voltage fluctuations, threatening the safe operation of the grid. At the same time, with increasingly stringent environmental protection requirements, reducing carbon emissions has become a key task for the power industry. The traditional power generation structure dominated by thermal power urgently needs to be adjusted, and the proportion of clean energy in power supply needs to be increased. However, clean energy power generation is constrained by natural conditions, which further exacerbates the complexity of power supply and demand balance and scheduling. In the power market, prices fluctuate frequently, and existing scheduling methods are difficult to balance economic and environmental benefits, and cannot achieve efficient resource allocation based on market dynamics and equipment performance. Moreover, when considering the coordinated operation of multiple energy devices, the existing virtual power plant scheduling technology often ignores comprehensive factors such as the charging and discharging efficiency of energy storage equipment, the performance constraints of various equipment, and the volatility of power generation. It lacks a systematic optimization solution and is difficult to meet the needs of modern power systems for efficient, stable, and green operation. Summary of the invention

[0003] In view of the technical problems existing in the above-mentioned background technology, the present invention proposes a virtual power plant optimization scheduling method based on machine learning.

[0004] In order to achieve the above object, the technical solution adopted by the present invention comprises the following steps:

[0005] S1. First, collect real-time data from each distributed power source, energy storage device, and load management system in the virtual power plant;

[0006] S2. Clean and standardize the collected data;

[0007] S3. Construct an optimized objective function, which not only considers economic and environmental benefits, but also introduces price fluctuations in the electricity market, grid load forecasts, performance constraints of various energy equipment, charging and discharging efficiency of energy storage equipment, and power generation volatility factors of virtual power plants. The comprehensive objective function is: F(x) = α·C(x)-β·E(x)-γ·R(x), where C(x) represents economic benefits, E(x) represents environmental benefits, R(x) is a constraint function, and α, β, and γ are weight coefficients;

[0008] S4. Finally, the improved non-dominated sorting genetic algorithm NSGA-II is used to optimize the objective function with multiple objectives, which improves the optimization efficiency.

[0009] The implementation of the improved non-dominated sorting genetic algorithm NSGA-II is as follows:

[0010] S41, first initialize the population and initialize individual parameters;

[0011] S42, using a double selection mechanism to calculate the non-dominated order of individuals and improve the crowding measure;

[0012] S43, performing adaptive crossover and mutation operations;

[0013] S44. Generate a new population, terminate the algorithm when the maximum set number of iterations of 30 is reached, and output the results.

[0014] Preferably, the specific form of the economic benefit C(x) in step S3 is: Where P sell (t) represents the amount of electricity sold at time t, P buy (t) is the amount of electricity purchased at time t, λ(t), μ(t) are the sales and purchase prices in the electricity market, respectively, and C fuel,i (t), C op,i (t) represents the combustion cost and operating cost of the i-th type of equipment.

[0015] Preferably, the specific form of the environmental benefit E(x) in step S3 is: where α j , β eco is the environmental protection factor, CF j is the carbon emission factor of the jth type of power generation, P gen,j (t) is the amount of electricity generated by the jth type of equipment at time t, P gen,coal (t) is the amount of electricity generated by coal-fired power plants.

[0016] Preferably, the specific form of the constraint function R(x) in step S3 is: Where SOC(t) represents the state of charge of the device, and this constraint function ensures that all devices in the virtual power plant meet their operating constraints during the scheduling process.

[0017] Preferably, the steps of calculating the non-dominated order of individuals and improving the crowding degree metric by using the double selection mechanism in step S42 are as follows:

[0018] S421, first calculate the non-dominated relationship;

[0019] S422. The improved crowding measure considers the solution density in both the target space and the decision space at the same time. The specific approach is: where f k (x i ) is individual x i The function value on the kth target, f k (x i ′) is x i Adjacent individuals x i ′ is the function value on the kth target, x i (d) is the individual x i The value of the dth decision variable in the decision space;

[0020] S423. Filter the local optimal solution, sort the solutions in each non-dominated level from high to low according to the degree of congestion, and preferentially select the solution with high congestion degree: Priority local (x i )=-D crowd (x i ), select N from the current non-dominated level local local optimal solutions, forming a local solution set;

[0021] S424. Calculate the global priority by combining the non-dominated level and the congestion degree: global (x i )=F(x i )+D crowd (x i ), where F(x i ) is the non-dominated sorting level, sorted from low to high according to the global priority, and select N from the population global A global optimal solution;

[0022] S425. Finally, the local solution set and the global solution set are merged to obtain a candidate set.

[0023] Preferably, the specific implementation of the adaptive crossover and mutation operation in step S43 is as follows: the adaptive crossover implementation formula is: Diversity is a measure of population diversity; the operations of adaptive mutation are: Where s(x i ) is individual x i The fitness, s max is the individual with the best fitness in the population.

[0024] Compared with the prior art, the advantages and positive effects of the present invention are that, in the construction of the objective function, economic and environmental benefits are comprehensively integrated, and factors such as electricity market price fluctuations, grid load forecasts, energy equipment performance constraints, energy storage equipment charging and discharging efficiency, and power generation volatility are innovatively introduced, breaking through the single consideration limitations of traditional methods. The improved NSGA-II algorithm, with its dual selection mechanism integrating local and global optimality, can quickly locate local optimal solutions and guide global optimality in virtual power plant equipment scheduling, accelerating convergence. The improved congestion metric takes into account the density of multi-space solutions and accurately evaluates individuals. Adaptive genetic operations flexibly adjust the probability and amplitude of crossover mutations according to population dynamics, balance global and local searches, efficiently improve optimization effects, and enhance overall adaptability. DETAILED DESCRIPTION

[0025] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.

[0027] Embodiment, in the current energy landscape, with the large-scale access of distributed energy, the stability of power supply faces huge challenges. For example, in the power system of a certain region, the power generation of solar and wind power stations fluctuates violently in different seasons and weather conditions. In sunny and windy periods, power generation may exceed local demand, while in rainy or windless weather, power generation drops sharply, seriously affecting the supply and demand balance of the power grid. At the same time, environmental pressure has prompted the power industry to reduce carbon emissions, and the power generation structure dominated by traditional thermal power is in urgent need of adjustment. However, clean energy power generation is constrained by natural conditions, which further increases the complexity of power dispatch. In addition, electricity market prices fluctuate frequently, and existing dispatching methods are difficult to balance economic and environmental benefits, and cannot achieve efficient allocation of resources. Therefore, the present invention proposes a virtual power plant optimization dispatching method based on machine learning.

[0028] First, in the data collection link, the present invention is committed to extensively collecting rich real-time data from various distributed power sources, energy storage devices and load management systems within the virtual power plant. These data types are diverse, including power generation, load demand, energy storage status and market electricity price information. Since the collected data have various quality problems, data cleaning and standardization are required. In the data cleaning process, advanced filtering algorithms, such as the Kalman filtering algorithm, are used for noisy data to effectively remove high-frequency interference and measurement errors and restore the true appearance of the data. For missing values, reasonable interpolation methods are used to fill them according to the time series characteristics and correlation of the data.

[0029] Next, constructing the optimized objective function is one of the core links of the present invention. The objective function constructed by the present invention is highly comprehensive. It not only comprehensively considers the two key aspects of economic benefits and environmental benefits, but also innovatively introduces multiple important factors, including price fluctuations in the electricity market, grid load forecasts, performance constraints of various energy equipment, charging and discharging efficiency of energy storage equipment, and power generation volatility factors of virtual power plants. The specific form of economic benefits C(x) is: Where P sell (t) represents the amount of electricity sold at time t, P buy (t) is the amount of electricity purchased at time t, λ(t), μ(t) are the sales and purchase prices in the electricity market, respectively, and C fuel,i (t), C op,i (t) represents the combustion cost and operating cost of the i-th type of equipment. Through this formula, the economic benefits of the virtual power plant under different market electricity prices and equipment operating costs can be accurately calculated. The specific form of environmental benefit E(x) is: where α j , β eco is the environmental protection factor, CF j is the carbon emission factor of the jth type of power generation, P gen,j (t) is the amount of electricity generated by the jth type of equipment at time t, P gen,coal (t) is the amount of electricity generated by coal-fired power plants. Through this formula, in the process of optimizing scheduling, clean energy power generation equipment can be prioritized to reduce dependence on coal-fired power plants, thereby effectively reducing carbon emissions. The specific form of the constraint function R(x) is: Among them, SOC(t) represents the charging state of the equipment. This constraint function ensures that all equipment in the virtual power plant meets its operating restrictions during the scheduling process. Therefore, the comprehensive objective function is: F(x) = α·C(x)-β·E(x)-γ·R(x), where C(x) represents economic benefits, E(x) represents environmental benefits, R(x) is a constraint function, and α, β, and γ are weight coefficients; the weight coefficients are determined based on the hierarchical analysis method, and the calculation results are α = 0.5, β = 0.35, and γ = 0.15.

[0030] Considering that the traditional NSGA-II algorithm has many shortcomings, such as lack of selection pressure, easy to miss excellent individuals, slow population evolution; difficult to maintain population diversity, easy to converge to the local optimum prematurely, and miss the global optimal solution; extremely low computational efficiency when dealing with large-scale problems. The improved NSGA-II algorithm in the present invention integrates local and global optimality in a dual selection mechanism. In the virtual power plant, it can not only quickly explore optimization solutions locally, but also guide to the optimal solution from the global perspective to accelerate convergence. The improved congestion metric comprehensively considers the target and decision space solution density. The adaptive genetic operation is flexibly adjusted according to the state of the population. When the diversity is high, the crossover probability is increased to stimulate new solutions. The variation range of individuals with different fitness is reasonably changed to balance the global and local searches, effectively improve the optimization efficiency and quality, and enhance the adaptability of the algorithm. The improved non-dominated sorting genetic algorithm NSGA-II is implemented as follows: first, the population is initialized and the individual parameters are initialized; the non-dominated relationship is calculated, and for any two individuals x in the population i and x j , according to the objective function value f k (x) is compared to determine the dominant relationship between them, if x i Not inferior to x in all objectives j , and is better than x in at least one objective j , then x i Dominate x j , then the improved crowding measure is to consider the solution density in both the target space and the decision space at the same time, specifically: where f k (x i ) is individual x i The function value on the kth target, f k (x i ′) is x i Adjacent individuals x i ′ is the function value on the kth target, x i (d) is the individual x i The value of the dth decision variable in the decision space; then select the local optimal solution, sort from high to low according to the congestion in each non-dominated level, and preferably select the solution with high congestion: priority local (x i )=-D crowd (x i ), select N from the current non-dominated level local local optimal solutions to form a local solution set; combining non-dominated level and congestion degree to calculate the global priority: priority global (x i )=F(x i )+D crowd (x i), where F(x i ) is the non-dominated sorting level, sorted from low to high according to the global priority, and select N from the population global The global optimal solution is obtained; finally, the local solution set is merged with the global solution set to obtain the candidate set. Then, adaptive crossover and mutation operations are performed; when the population diversity is high, the crossover probability is increased, and when the population tends to converge, the crossover probability is reduced. The implementation formula is: Diversity is a measure of population diversity; individuals with poor fitness increase the variation range to try to jump out of the current solution area; individuals with good fitness reduce the variation range to finely explore the area near the current solution: Where s(x i ) is individual x i The fitness, s max is the individual with the best fitness in the population. Finally, a new population is generated. When the maximum set number of iterations is 30, the algorithm is terminated and the results are output. The optimal scheduling plan of the virtual power plant in different time periods is obtained to achieve the maximum balance between economic and environmental benefits, while ensuring that various constraints on equipment operation are met.

[0031] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A virtual power plant optimization scheduling method based on machine learning, characterized in that: The following steps are involved: S1. First, collect real-time data from each distributed power source, energy storage device, and load management system in the virtual power plant; S2. Clean and standardize the collected data; S3. Construct an optimized objective function, which not only considers economic and environmental benefits, but also introduces price fluctuations in the electricity market, grid load forecasts, performance constraints of various energy equipment, charging and discharging efficiency of energy storage equipment, and power generation volatility factors of virtual power plants. The comprehensive objective function is: F(x) = α·C(x)-β·E(x)-γ·R(x), where C(x) represents economic benefits, E(x) represents environmental benefits, R(x) is a constraint function, and α, β, and γ are weight coefficients; S4. Finally, the improved non-dominated sorting genetic algorithm NSGA-II is used to optimize the objective function with multiple objectives, which improves the optimization efficiency. The implementation of the improved non-dominated sorting genetic algorithm NSGA-II is as follows: S41, first initialize the population and initialize individual parameters; S42, using a double selection mechanism to calculate the non-dominated order of individuals and improve the crowding measure; S43, performing adaptive crossover and mutation operations; S44. Generate a new population, terminate the algorithm when the maximum set number of iterations of 30 is reached, and output the results.

2. The virtual power plant optimization scheduling method based on machine learning according to claim 1 is characterized in that: The specific form of the economic benefit C(x) in step S3 is: Where P sell (t) represents the amount of electricity sold at time t, P buy (t) is the amount of electricity purchased at time t, λ(t), μ(t) are the sales and purchase prices in the electricity market, respectively, and C fuel,i (t), C op,i (t) represents the combustion cost and operating cost of the i-th type of equipment.

3. The virtual power plant optimization scheduling method based on machine learning according to claim 1 is characterized in that: The specific form of the environmental benefit E(x) in step S3 is: where α j , β eco is the environmental protection factor, CF j is the carbon emission factor of the jth type of power generation, P gen,j (t) is the amount of electricity generated by the jth type of equipment at time t, P gen,coal (t) is the amount of electricity generated by coal-fired power plants.

4. The virtual power plant optimization scheduling method based on machine learning according to claim 1 is characterized in that: The specific form of the constraint function R(x) in step S3 is: Where SOC(t) represents the state of charge of the device, and this constraint function ensures that all devices in the virtual power plant meet their operating constraints during the scheduling process.

5. The virtual power plant optimization scheduling method based on machine learning according to claim 1 is characterized in that: The implementation steps of using the double selection mechanism to calculate the non-dominated order of individuals and improve the crowding degree metric in step S42 are: S421, first calculate the non-dominated relationship; S422. The improved crowding measure considers the solution density in both the target space and the decision space at the same time. The specific approach is: where f k (x i ) is individual x i The function value on the kth target, f k (x′ i ) is x i Adjacent individual x′ i The function value on the kth target, x i (d) is the individual x i The value of the dth decision variable in the decision space; S423. Filter the local optimal solution, sort the solutions in each non-dominated level from high to low according to the degree of congestion, and preferentially select the solution with high congestion degree: Priority local (x i )=-D crowd (x i ), select N from the current non-dominated level local local optimal solutions, forming a local solution set; S424. Calculate the global priority by combining the non-dominated level and the congestion degree: global (x i )=F(x i )+D crowd (x i ), where F(x i ) is the non-dominated sorting level, sorted from low to high according to the global priority, and select N from the population global A global optimal solution; S425. Finally, the local solution set and the global solution set are merged to obtain a candidate set.

6. The virtual power plant optimization scheduling method based on machine learning according to claim 1 is characterized in that: The specific implementation of the adaptive crossover and mutation operation in step S43 is: the adaptive crossover implementation formula is: Diversity is a measure of population diversity; the operations of adaptive mutation are: Where s(x i ) is individual x i The fitness, s max is the individual with the best fitness in the population.

Images