Title: Developing an integrated approach for optimum prediction and forecasting of renewable and non-renewable energy consumption in Iran

Authors: Reza Babazadeh; Shima Pashapour; Abbas Keramati

Addresses: Faculty of Engineering, Urmia University, Urmia, West Azerbaijan Province, Iran ' School of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran ' School of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran; Ted Rogers School of Information Technology Management, Ryerson University, Toronto, Canada

Abstract: Energy planning for mid and long term periods needs forecasting the energy demands in the future. The artificial neural network (ANN) is an efficient forecasting tool which have been widely applied in different fields. One of the weaknesses of the ANN method is appeared when the studied case has many input parameters affecting on the performance of output factor. Noteworthy, there is not reliable data in many applications of real world. The canonical correlation analysis (CCA) method is an efficient tool for data reduction purpose keeping useful information of the used data. The purpose of this paper is to estimate and predict the renewable and non-renewable energy consumption considering environmental and economic factors. To this aim, an integrated approach based on the CCA and ANN method is utilised. The results show that the proposed approach reduces dimension of data without losing valuable information.

Keywords: renewable energy; non-renewable energy; canonical correlation analysis; CCA; artificial neural network; ANN; environmental and economic factors; Iran.

DOI: 10.1504/IJETP.2020.105505

International Journal of Energy Technology and Policy, 2020 Vol.16 No.2, pp.119 - 135

Received: 19 Jul 2017
Accepted: 21 Dec 2017
Published online: 03 Mar 2020 *

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