Improving the Model for Energy Consumption Load Demand Forecasting

電気学会 電子図書館 Verified independent store

→

カテゴリ: 論文誌(論文単位)グループ名: 【B】電力・エネルギー部門発行日: 2012/03/01タイトル(英語): Improving the Model for Energy Consumption Load Demand Forecasting著者名: Pituk Bunnoon (Electrical Engineering Department, Engineering Faculty, Prince of Songkla University), Kusumal Chalermyanont (Electrical Engineering Department, Engineering Faculty, Prince of Songkla University), Chusak Limsakul (Electrical Engineering Dep著者名(英語): Pituk Bunnoon (Electrical Engineering Department, Engineering Faculty, Prince of Songkla University), Kusumal Chalermyanont (Electrical Engineering Department, Engineering Faculty, Prince of Songkla University), Chusak Limsakul (Electrical Engineering Department, Engineering Faculty, Prince of Songkla University)キーワード: HP-filter，trend and cyclical component，double neural networks，preprocessing，forecasting要約(英語): This paper proposes an application of a filter method in preprocessing stage for mid-term load demand forecasting to improve electricity load forecasting and to guarantee satisfactory forecasting accuracy. Case study employs the historical electricity consumption demand data in Thailand which were recorded in the 12 years of 1997 through to 2007. The load demand forecasted value is used for unit commitment and fuel reserve planning in the power system. This method consists of a trend component and a cyclical component decomposed from the original load demand using the Hodrick-Prescott (HP) filter in the preprocessing stage and the forecasting of each component using Double Neural Networks (DNNs) in the forecasting stage. Experimental results show that with preprocessing before forecasting can predict the load demand better than that without preprocessing.本誌: 電気学会論文誌B（電力・エネルギー部門誌） Vol.132 No.3 （2012）本誌掲載ページ: 235-243 p原稿種別: 論文／英語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejpes/132/3/132_3_235/_article/-char/ja/ Show more