© univariate modeling and forecasting of monthly energy demand time series using abductive and...
Post on 01-Jan-2016
215 Views
Preview:
TRANSCRIPT
©
Univariate Modeling And Forecasting Of Monthly Energy
Demand Time
Series Using Abductive And Neural Networks
Abdel-Aal, RE
PERGAMON-ELSEVIER SCIENCE LTD, COMPUTERS INDUSTRIAL ENGINEERING;
pp: 903-917; Vol: 54
King Fahd University of Petroleum & Minerals
http://www.kfupm.edu.sa
Summary
Neural networks have been widely used for short-term, and to a lesser degree medium
and long-term, demand forecasting. In the majority of cases for the latter two
applications, multivariate modeling was adopted, where the demand time series is
related to other weather, socio-economic and demographic time series. Disadvantages
of this approach include the fact that influential exogenous factors are difficult to
determine, and accurate data for them may not be readily available. This paper uses
univariate modeling of the monthly demand time series based only on data for 6 years
to forecast the demand for the seventh year. Both neural and abductive networks were
used for modeling, and their performance was compared. A simple technique is
described for removing the upward growth trend prior to modeling the demand time
series to avoid problems associated with extrapolating beyond the data range used for
training. Two modeling approaches were investigated and compared: iteratively using
a single next-month forecaster, and employing 12 dedicate(] models to forecast the 12
individual months directly. Results indicate better performance by the first approach,
with mean percentage error (MAPE) of the order of 3% for abductive networks.
Performance is superior to naive forecasts based on persistence and seasonality, and is
better than results quoted in the literature for several similar applications using
multivariate abductive modeling, multiple regression, and univariate ARIMA
analysis. Automatic selection of only the most relevant model inputs by the abductive
learning algorithm provides better insight into the modeled process and allows
Copyright: King Fahd University of Petroleum & Minerals;http://www.kfupm.edu.sa
©
constructing simpler neural network models with reduced data dimensionality and
improved forecasting performance. (C) 2007 Elsevier Ltd. All rights reserved.
References:1. *ABTECH CORP, 1990, AIM US MAN2. ABDELAAL RE, 1997, ENERGY, V22, P9113. ABDELAAL RE, 2004, IEEE T POWER SYST, V19, P164, DOI4. 10.1109/TPWRS.2003.8206955. ALFUHAID AS, 1997, IEEE T POWER SYST, V12, P15246. ALGARNI AZ, 1994, ENERGY, V19, P10437. ALHAMADI HM, 2006, IEE P-GENER TRANSM D, V153, P217, DOI8. 10.1049/ip-gtd:200500889. ALSABA T, 1999, ARTIF INTELL ENG, V13, P18910. BARAKAT EH, 1989, IEE PROC-C, V136, P3511. BARAKAT EH, 1992, IEEE T POWER SYST, V7, P148312. BARRON AR, 1984, SELF ORG METHODS MOD, P8713. BIELINSKA EM, 1994, 3 IEEE C CONTR APPL, P183514. CHATFIELD C, 1998, P 1998 IEEE SIGN PRO, P41915. DESILVA A, 2001, IEEE POW TECH C PORT16. DILLON TS, 1975, P 5 POW SYST COMP C17. ELKATEB MM, 1998, NEUROCOMPUTING, V23, P318. FARLOW SJ, 1984, SELF ORG METHODS MOD, P119. FRANCEY RJ, 2000, P 2 INT S CO2 OC JAN, P23720. FUJIMORI S, 1998, IEEE INT S ELECT INS, P53021. GHIASSI M, 2006, ELECTR POW SYST RES, V76, P302, DOI22. 10.1016/j.epsr.2005.06.01023. GONZALEZROMERA E, 2007, COMPUT IND ENG, V52, P336, DOI24. 10.1016/j.cie.2006.12.01025. HIPPERT HS, 2001, IEEE T POWER SYST, V16, P4426. ISLAM SM, 1995, ELECTR POW SYST RES, V34, P127. KERMANSHAHI B, 2002, INT J ELEC POWER, V24, P78928. KHOTANZAD A, 1998, IEEE T POWER SYST, V13, P141329. LEWIS HW, 2001, P MOUNT WORKSH SOFT, P2530. LIU XQ, 1991, IEEE INT JOINT C NEU, P125431. MATSUI T, 2001, IEEE POW ENT SOC WIN, P40532. MONTGOMERY GJ, 1991, NEUROCOMPUTING, V2, P9733. PARK DC, 1991, IEEE T POWER SYST, V6, P44234. SFORNA M, 1995, ELECTR POW SYST RES, V32, P135. SHIMAKURA Y, 1993, 2 INT FOR APPL NEUR, P23336. THIESING FM, 1997, INT C NEUR NETW, P212537. TOYADA J, 1970, IEEE T POWER SYST, V89, P167838. VIRILI F, 2000, P INT JOINT C NEUR N, V5, P129
For pre-prints please write to: radwan@kfupm.edu.sa
Copyright: King Fahd University of Petroleum & Minerals;http://www.kfupm.edu.sa
©Copyright: King Fahd University of Petroleum & Minerals;http://www.kfupm.edu.sa
top related