Title: A robust fuzzy linear regression model for forecasting electricity consumption of residential sector in Iran
Authors: H. Omrani; S.G. Jalali Naini; M. Alinaghian
Addresses: Department of Industrial Engineering, Urmia University of Technology, Band Road, Urmia, Iran. ' Department of Industrial Engineering, Iran University of Science and Technology, Resalat Sq., Narmak, Tehran, Iran. ' Department of Industrial Engineering, Iran University of Science and Technology, Resalat Sq., Narmak, Tehran, Iran
Abstract: Many fuzzy linear regression (FLR) models are normally very sensitive to the changes on the input data so that the results could significantly be changed even with some small change on one or more input parameters. Therefore, many researchers have been interested in creating a so called robust model to increase the reliability of the estimated parameters. In this paper, a simple robust fuzzy linear regression (RFLR) model is suggested for forecasting the electricity consumption. Our RFLR model uses the robust optimisation (RO) technique introduced by Ben-Tal and Nemirovski (2000). The performance of the proposed model is illustrated through a numerical example and is applied for estimating electricity consumption of residential sector in Iran.
Keywords: robust optimisation; perturbation; uncertainty; fuzzy linear regression; FLR; Iran; forecasting; electricity consumption; energy consumption; residential sector; robust modelling.
International Journal of Applied Management Science, 2012 Vol.4 No.4, pp.425 - 438
Published online: 19 Oct 2012 *Full-text access for editors Access for subscribers Purchase this article Comment on this article