Comparative Study of Short-term Electric Load Forecasting

被引:7
作者
Koo, Bon-gil [1 ]
Lee, Sang-wook [1 ]
Kim, Wook [1 ]
Park, June ho [1 ]
机构
[1] Pusan Natl Univ, Dept Elect & Comp Engn, Busan, South Korea
来源
PROCEEDINGS FIFTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS, MODELLING AND SIMULATION | 2014年
基金
新加坡国家研究基金会;
关键词
component; formatting; Short-term electric load foreacasting; ARIMA; k-NN; Artificial Neural Network; Simple Exponential Smoothing; GMDH; NEURAL NETWORKS;
D O I
10.1109/ISMS.2014.85
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we performed short-term electric load forecasting using three methods and compared each results. We classified before making a forecasting model using K-means and k-NN to eliminate error from calendar based classification. Classified load data used as inputs of forecasting model. We compared three methods such as ANN, SES, GMDH. We carried out 1-day ahead prediction for two weeks, January 10 to 16, March 14 to 20, 2011 using hourly Korean electric load data. The results of forecasting, all methods were mostly good in general without applying meteorological data. Most of them, GMDH expressed the most performance in MAPE except for Saturday.
引用
收藏
页码:463 / 467
页数:5
相关论文
共 14 条
[1]   Short-term hourly load forecasting using time-series modeling with peak load estimation capability [J].
Amjady, N .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2001, 16 (04) :798-805
[2]   FUZZY NEURAL NETWORKS FOR TIME-SERIES FORECASTING OF ELECTRIC-LOAD [J].
DASH, PK ;
RAMAKRISHNA, G ;
LIEW, AC ;
RAHMAN, S .
IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION, 1995, 142 (05) :535-544
[3]   Short-term load forecasting with local ANN predictors [J].
Drezga, I ;
Rahman, S .
IEEE TRANSACTIONS ON POWER SYSTEMS, 1999, 14 (03) :844-850
[4]  
Han Jiawei, 2006, DATA MINING CONCEPTS, P402
[5]   Neural networks for short-term load forecasting: A review and evaluation [J].
Hippert, HS ;
Pedreira, CE ;
Souza, RC .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2001, 16 (01) :44-55
[6]   Short-term load forecasting via ARMA model identification including non-Gaussian process considerations [J].
Huang, SJ ;
Shih, KR .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2003, 18 (02) :673-679
[7]   POLYNOMIAL THEORY OF COMPLEX SYSTEMS [J].
IVAKHNENKO, AG .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1971, SMC1 (04) :364-+
[8]  
Kang D.-J., 2010, INT J ENERGY INFORM, V1, P64
[9]   Kohonen neural network and wavelet transform based approach to short-term load forecasting [J].
Kim, CI ;
Yu, IK ;
Song, YH .
ELECTRIC POWER SYSTEMS RESEARCH, 2002, 63 (03) :169-176
[10]  
Kondo Tadashi, 1992, SYSTEMS INFORM CONTR, V5, P391