Risk Quantification for ANN Based Short-Term Load Forecasting

• Iwashita Daisuke

  Dept. of Electrical and Electronics Eng., Meiji University

• Mori Hiroyuki

  Dept. of Electrical and Electronics Eng., Meiji University

Bibliographic Information

Other Title

• ＡＮＮモデルを用いた短期電力負荷予測におけるリスクの定量化
• ANN モデル オ モチイタ タンキ デンリョク フカ ヨソク ニ オケル リスク ノ テイリョウカ

Abstract

A new risk assessment method for short-term load forecasting is proposed. The proposed method makes use of an Artificial Neural Network (ANN) to forecast one-step ahead daily maximum loads and evaluate uncertainty of in load forecasting. As ANN the model, the Radial Basis Function (RBF) network is employed to forecast loads due to the good performance. Sufficient realistic pseudo-scenarios are required to carry out quantitative risk analysis. The multivariate normal distribution with the correlation between input variables is used to give more realistic results to ANN. In addition, the method of Moment Matching is used to improve the accuracy of the multivariate normal distribution. The Peak Over Threshold (POT) approach is used to evaluate risk that exceeds the upper bounds of generation capacity. The proposed method is successfully applied to real data of daily maximum load forecasting.

Journal

• IEEJ Transactions on Power and Energy

  IEEJ Transactions on Power and Energy 126 (1), 29-35, 2006

  The Institute of Electrical Engineers of Japan

Keywords

• short-term load forecasting
• risk analysis
• neural network
• moment matching
• extreme value theory

Details

• CRID: 1390001204601298560
• NII Article ID: 10016922316
• NII Book ID: AN10136334
• DOI: 10.1541/ieejpes.126.29
• ISSN: 13488147
• ISSN: 03854213
• NDL BIB ID: 7759818
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I7759818
• Web Site: http://www.jstage.jst.go.jp/article/ieejpes/126/1/126_1_29/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed