Long-termmid-term electric load forecasting based on.docxVIP

Electric Power Systems Research 74 (2005) 353–361Long-term/mid-term electric load forecasting based on short-term correlation and annual growthH.M. Al-Hamadi, S.A. Soliman ?Power System Research Group, Department of Electrical Engineering, College of Engineering, University of Qatar, P.O. Box 2713, Doha, QatarReceived 3 February 2004; accepted 26 October 2004Available online 7 April 2005AbstractThis paper presents a novel approach for long-term/mid-term electric power load forecasting. The strong short-term correlations of daily (24 h) and yearly (52 weeks) load behavior are implemented to predict future load demand. The algorithm is suitable for forecasting weekly average load profiles for 24 h of a day with a lead-time from several weeks to a few years. It successively incorporates alternating daily and weekly simple (1st order) linear regression models of previous (1 year) data augmented with annual load growth to predict future load demand. The results demonstrate successful (one year ahead) load forecast with a mean absolute error of less than 3.8% and with a standard deviation of less than 4.2, which prove superior to other techniques published earlier in the literature.? 2005 Elsevier B.V. All rights reserved.Keywords: Electric load forecasting; Long-term/mid-term forecasting; Annual growth; Short-term correlation1. IntroductionAccurate long-/mid-term electric load forecasting plays an essential role for electric power system planning. It cor- responds to load forecasting with lead times long enough to plan for long-/mid-term maintenance, construction schedul- ing for developing new generation facilities, purchasing of generating units, developing transmission and distribution systems. The accuracy of the long-term load forecast has significant effect on developing future generation and distri- bution planning. An extensive overestimation of load demand will result in substantial investment for the construction of excess power facilities, while underestimatio