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

被引：1
作者：
Erkmen, I
Topalli, AK
机构：
[1] TEON Software & Hardware Design Inc, Izmir 10001, Turkey
[2] Middle E Tech Univ, Dept Elect & Elect Engn, TR-06531 Ankara, Turkey
来源：
ELECTRICAL ENGINEERING | 2003年 / 85卷 / 04期
关键词：
artificial intelligence; clustering; data forecasting; hybrid learning; neural networks;
D O I：
10.1007/s00202-003-0163-9
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
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.
引用
收藏
页码：229 / 233
页数：5
相关论文
共 21 条
[1]  
[Anonymous], 1976, TIME SERIES ANAL
[2]  
[Anonymous], 1992, NEURAL NETWORKS FUZZ
[3]  
[Anonymous], P 1 IEEE INT C FUZZ
[4]  
BALYA B, 1994, THESIS MIDDLE E TU A
[5]   Very short-term load forecasting using artificial neural networks [J].
Charytoniuk, W ;
Chen, MS .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2000, 15 (01) :263-268
[6]  
Cichocki A., 1993, Neural Networks for Optimization and Signal Processing
[7]  
El-Sharkawi MA, 1999, ENG INTELL SYST ELEC, V7, P197
[8]   SHORT-TERM LOAD FORECASTING [J].
GROSS, G ;
GALIANA, FD .
PROCEEDINGS OF THE IEEE, 1987, 75 (12) :1558-1573
[9]   A neuro-fuzzy approach to short-term load forecasting in a price-sensitive environment [J].
Khotanzad, A ;
Zhou, EW ;
Elragal, H .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2002, 17 (04) :1273-1282
[10]   An artificial neural network hourly temperature forecaster with applications in load forecasting [J].
Khotanzad, A ;
Davis, MH ;
Abaye, A ;
Maratukulam, DJ .
IEEE TRANSACTIONS ON POWER SYSTEMS, 1996, 11 (02) :870-876
123