Title :
Pattern analysis for load forecasting
Author :
YingJu Xia ; Yuhang Yang ; Fujiang Ge ; Jian Su ; Hao Yu
Author_Institution :
Ocean Int. Center, Fujitsu R&D Center Co., Ltd., Beijing, China
Abstract :
Short term load forecasting is an essential part of electric power system planning and operation. Effective load forecasting is difficult due to the complicated effects on load by variety of factors. This paper presents a novel forecasting method that combining the pattern analysis of different factors. A pattern analysis method which exploits features of peaks and valleys on curves instead of directly comparing values is proposed in this study. The approach proposed in this paper not only performs load pattern clustering, but also extract typical pattern for the load forecasting. The experimental results have shown that this method provides accurate predictions.
Keywords :
load forecasting; pattern recognition; power system planning; electric power system planning; load forecasting; pattern analysis; Artificial neural networks; Forecasting; Training; load prediction; pattern analysis;
Conference_Titel :
Computing Technology and Information Management (ICCM), 2012 8th International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4673-0893-9