Title: An integrated fuzzy regression algorithm for improved electricity consumption estimation

Authors: Ali Azadeh, Morteza Saberi, Anahita Gitiforouz

Addresses: Department of Industrial Engineering, Center of Excellence for Intelligent Experimental Mechanics, College of Engineering, University of Tehran, P.O. Box 11365-4563, Tehran, Iran. ' Department of Industrial Engineering, University of Tafresh, Tafresh, Iran; Young Researcher Club, Azad University of Tafresh, Tafresh, Iran; School of Information Systems, Curtin University of Technology, Perth, Australia. ' Department of Industrial Engineering, Center of Excellence for Intelligent Experimental Mechanics, College of Engineering, University of Tehran, P.O. Box 11365-4563, Tehran, Iran

Abstract: This study presents an integrated fuzzy regression and time-series technique to estimate and predict electricity demand. Furthermore, it is difficult to model uncertain behaviour of energy consumption with only conventional time-series and fuzzy regression, which could be an ideal substitute for such cases. After reviewing various fuzzy regression models and studying their advantages and shortcomings, the best model is selected. Also, the impact of data preprocessing and post-processing on the fuzzy regression performance is to study and to show that this method does not contribute to the efficiency of the model. In addition, another unique feature of this study is utilisation of autocorrelation function to define input variables versus trial and error method. At last, the comparison of actual data with fuzzy regression and ARIMA model, using Granger–Newbold test, is achieved. Monthly electricity consumption of Iran from 1995 to 2005 is considered as the case of this study.

Keywords: fuzzy regression; forecasting; data preprocessing; time series; electricity consumption; power consumption; electricity demand; demand prediction; modelling; autocorrelation; Iran.

DOI: 10.1504/IJOR.2010.034358

International Journal of Operational Research, 2010 Vol.9 No.1, pp.1 - 22

Published online: 01 Aug 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article