Title: Application of adaptive neuro fuzzy inference system in demand forecasting for power engineering company
Authors: Golam Kabir; M. Ahsan Akhtar Hasin
School of Engineering, University of British Columbia (UBC), Kelowna, British Columbia, V1V 1V7, Canada
Department of Industrial and Production Engineering, Bangladesh University of Engineering and Technology, Dhaka-1000, Bangladesh
Abstract: To enhance the commercial competitive advantage in a constantly fluctuating business environment, an organisation has to make the right decisions in time depending on demand information. Therefore, estimating the demand quantity for the next period most likely appears to be crucial. Forecasting becomes a crucial process for manufacturing companies to effectively guiding several activities, and research has devoted particular attention to this issue. The objective of the paper is to propose a new forecasting mechanism which is modelled by adaptive neuro-fuzzy inference system (ANFIS) techniques to manage the fuzzy demand with incomplete information. ANFIS is utilised to harness the power of the fuzzy logic and artificial neural networks (ANN) through utilising the mathematical properties of ANNs in tuning rule-based fuzzy systems that approximate the way human's process information. To accredit the proposed model, it is implemented to forecast the demand of distribution transformer of a power engineering company of Bangladesh.
Keywords: adaptive neuro-fuzzy inference system; ANFIS; demand forecasting; distribution transformers; ANNs; artificial neural networks; fuzzy logic; power engineering; modelling; Bangladesh.
Int. J. of Industrial and Systems Engineering, 2014 Vol.18, No.2, pp.237 - 255
Available online: 04 Sep 2014