基于GA-PSO算法优化BP网络的短期电力负荷预测-计算机应用技术专业论文.docxVIP

ABSTRACT With constantly developing of power market, forecasting electrical load becomes an important work for the power system management department. Accurately making a prediction for power load can better make power network planning and power units of maintenance plan, and more reasonably arrange operation mode of power network. It is of great significance to improve economic benefit and social benefit of power enterprises, keep power system safe and stable, and ensure peoples daily life in order. Firstly, the thesis introduces the research background, research status at home and abroad, and research significance of power load prediction. This thesis describes the basic theory of power load prediction. Secondly, the key technologies of modern prediction were introduced in detail. The thesis introduces the basic theory of artificial neural network. This thesis particularly studies BP neural network, include the structures, corresponding learning algorithm steps, advantage and disadvantage. Meanwhile characteristics and fundamentals of Genetic Algorithm and Particle Swarm Optimization Algorithm are also researched and analyzed. Thirdly, the thesis design forecasting model of BP neural network, include the input layer, output layer, hidden layer and the definition of transfer function. Finally, genetic algorithm (GA), particle swarm III optimization (PSO) and GA-PSO algorithm are respectively applied to optimize the weights and thresholds of BP neural network. Establish a forecasting model of GA-BP neural network, a forecasting model of PSO-BP neural network and a forecasting model of GA-PSO-BP neural network. The historical load data, historical temperature and date in a certain region of European were used for simulation test. Forecast the hourly load of 24 hours in a day this area. The prediction results were analyzed to compare the performance of forecasting models. The simulation results showed that the forecasting model of GA-PSO-BP neural netwo