Four methods for short-term load forecasting using the benefits of artificial intelligence

Erkmen I., Topalli A.

ELECTRICAL ENGINEERING, vol.85, no.4, pp.229-233, 2003 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 85 Issue: 4
  • Publication Date: 2003
  • Doi Number: 10.1007/s00202-003-0163-9
  • Journal Name: ELECTRICAL ENGINEERING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.229-233
  • Keywords: artificial intelligence, clustering, data forecasting, hybrid learning, neural networks, NEURAL-NETWORKS
  • Middle East Technical University Affiliated: Yes

Abstract

Four methods are developed for short-term load forecasting and are tested with the actual data from the Turkish Electrical Authority. The method giving the most successful forecasts is a hybrid neural network model which combines off-line and on-line learning and performs real-time forecasts 24-hours in advance. Loads from all day types are predicted with 1.7273% average error for working days, 1.7506% for Saturdays and 2.0605% for Sundays.