Hourly Electric Load Forecasting Algorithm based on Echo State Neural Network

摘要：

An algorithm for hourly electric load forecasting based on echo state neural networks (ESN) is proposed in this paper. ESN is a new paradigm for using recurrent neural networks (RNNs) with a simpler training method. While the prediction, load patterns are treated as time series signals; no further information is used than the past load data records, such as weather, seasonal variations. The relation between key parameter of the ESN and the predicting performance is discussed; ESN and feedforward neural network (FNN) are compared with the same task also. Simulation experiment results demonstrate that the proposed ESN algorithm is valid and can obtain more accurate predicting results than the FNN for the short-term load prediction problem.

关键词： Hourly electric load prediction Neural networks Echo state network linear regression

作者: Qingsong Song Xiangmo Zhao Zuren Feng Yisheng An Baohua Song

作者单位: School of Information Engineering,Chang’an University, Xi’an 710064, China, on leave from the System School of Information Engineering,Changan University,Xian 710064,China Systems Engineering Institute, Xi’an Jiaotong University, and with the State Key Laboratory of Manuf Qingyang Petroleum Machinery company,Changqing Drilling company,Qingyang 745100,China

会议类型: 国际会议

会议名称: 2011 China Control and Decision Conference(2011中国控制与决策会议 CCDC)

会议地点: 四川绵阳

会议语种:英文

页码: 3901-3905

在线出版日期: 2011-05-23（万方平台首次上网日期，不代表论文的发表时间）