Record number :
2337447
Title of article :
Novel effects of demand side management data on accuracy of electrical energy consumption modeling and long-term forecasting
Author/Authors :
Ardakani، نويسنده , , F.J. and Ardehali، نويسنده , , M.M.، نويسنده ,
Issue Information :
روزنامه با شماره پیاپی سال 2014
Pages :
8
From page :
745
To page :
752
Abstract :
Worldwide implementation of demand side management (DSM) programs has had positive impacts on electrical energy consumption (EEC) and the examination of their effects on long-term forecasting is warranted. The objective of this study is to investigate the effects of historical DSM data on accuracy of EEC modeling and long-term forecasting. To achieve the objective, optimal artificial neural network (ANN) models based on improved particle swarm optimization (IPSO) and shuffled frog-leaping (SFL) algorithms are developed for EEC forecasting. For long-term EEC modeling and forecasting for the U.S. for 2010–2030, two historical data types used in conjunction with developed models include (i) EEC and (ii) socio-economic indicators, namely, gross domestic product, energy imports, energy exports, and population for 1967–2009 period. Simulation results from IPSO-ANN and SFL-ANN models show that using socio-economic indicators as input data achieves lower mean absolute percentage error (MAPE) for long-term EEC forecasting, as compared with EEC data. Based on IPSO-ANN, it is found that, for the U.S. EEC long-term forecasting, the addition of DSM data to socio-economic indicators data reduces MAPE by 36% and results in the estimated difference of 3592.8 MBOE (5849.9 TW h) in EEC for 2010–2030.
Keywords :
optimization , ANN , Demand side management , Electrical energy consumption , Forecasting
Journal title :
Energy Conversion and Management
Serial Year :
2014
Link To Document :
بازگشت