4th International Engineering Conference on Developments in Civil & Computer Engineering Applications (IEC2018)
Title: MODELLING ENERGY DEMAND FORECASTING USING NEURAL NETWORKS WITH UNIVARIATE TIME SERIES
Authors: S. Cankurt, M. Yasin
DOI: 10.23918/iec2018.26
Abstract: The new era of consumption and change in the behavior of people in developing countries that we facing in recent decades has made not only the energy sector but also all resource suppliers in different sectors not to fulfill the demand in the field. The electricity, which is one of the main power resources, has become one of the major issues to be overcome for the governments. Predicting the future energy demand is always the most valuable information to achieve any success in many sectors. In this paper, a daily forecasting of the maximum energy demand in Kurdistan region of Iraq is investigated based on an artificial natural network and sliding window techniques. The standard mean absolute percentage error method is used to evaluate the accuracy of forecasting models.
Keywords: Neural networks, Sliding window technique, Energy demand forecasting.
Full Paper (PDF)