Short-Term Electricity Price Forecasting Based on MPSO-BP Algorithm

摘要：

　　In this paper,we exploited the short-term electricity price forecasting issue by introducing a global search mechanism based on the improved particle swarm optimization (MPSO)algorithm for the neural network training.The proposed MPSO algorithm is used for the initial weights and threshold of BP neural network in the process of optimization.We then proposed a novel short-term electricity price forecasting model based on MPSO-BP neural network.The paper provides a number of examples of bidding model of the California electricity market to forecasting market clear price using BP neural network trained by MPSO.Through the comparative study of the conventional BP neural network and the proposed MPSO-BP neural network,the proposed method demonstrates improved performance in finding the optimal solution with excellent convergence time for all the simulated scenarios.

关键词： Electricity Price Forecasting BP Neural Network PSO MPSO-BP

作者: Yu Dong Qiang Yang Wenjun Yan

作者单位: College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China

会议类型: 国际会议

会议名称: the 2012 International Conference on Manufacturing Engineering and Automation (2012年制造工程与自动化国际会议(ICMEA2012))

会议地点: 广州

会议语种:英文

页码: 1351-1355

在线出版日期: 2012-11-16（万方平台首次上网日期，不代表论文的发表时间）