Research Of Cost Optimization Of Wind Power System Based On Hybrid Algorithm Such As Particle Swarm Optimization

In recent years,the problems of environmental pollution and the increasing shortage of fossil energy have become more and more serious,and the traditional power system has been unable to meet the national strategic requirements of "energy saving and emission reduction".In this background,wind power systems have gradually become the main development direction of power systems of China.Especially in recent years,wind power system of China has developed rapidly,and the wind power penetration rate of the grid in various regions always soars.However,traditional wind power models often only take the minimum power generation cost as the objective function,ignoring the pollutants emitted by the wind power system.Therefore,it is of great significance to establish a multi-objective optimization model that considers the lowest emission cost and the lowest economic cost comprehensively.Because of the wind power system studied in this paper including wind farms,the wind power system can be divided into two parts: the model with only thermal power units and the model with wind farms.Therefore,when establishing the wind power system cost optimization model,the objective function can be to minimize the total cost of power generation and minimize the cost of pollutant emissions,considering the constraints of thermal power unit output and system power balance to establish the mathematical model of thermal power unit.On the basis of this model,considering the operating cost of the wind farm and the constraints of the wind power unit part,mathematical model of the wind power system is established.In the algorithm design,introducing the gravity search algorithm into the particle swarm algorithm,change its speed update formula,and use the dynamic inertia weight of the sinusoidal improvement strategy,the improved gravity particle swarm algorithm is proposed.The algorithm can avoid the particle swarm algorithm falling into the local optimum to certain extent.On this basis,the improved gravitational search algorithm will be paralleled by the ant colony algorithm,and then serialized by the tabu search algorithm to obtain a hybrid optimization algorithm(GAT-PSO).In the parallel ant colony algorithm,the assignment area and K value are set.Among them,the function of the assignment area is to compare the results of the two algorithms and assign values.On the one hand,it avoids the problem of slow convergence of the ant colony algorithm in early stage.On the other hand,it avoids the premature convergence of the particle swarm algorithm.The function of the K value is to set an access mechanism for the assignment area to avoid too many assignments and waste of running time.This algorithm can take advantage of the hybrid algorithm each other,and improve the performance of the algorithm.Finally,GAT-PSO is used to solve the above models,and the solution results are compared with the experimental results of other algorithms.According to the comparison,the results obtained by using GAT-PSO are reduced by about 3.98%,1.53%,and 1.89% respectively compared with the PSO or ACO algorithm and improved gravity search algorithm,and the pollutant gas emissions have been reduced by about 0.96%,0.81%,0.83%,verifying the effectiveness of the algorithm,which not only reduces economic costs,but also reduces pollution.