Forecasting of the electric energy demand trend and monthly fluctuation with neural networks

被引：45

作者：

Gonzalez-Romera, Eva ^{[1
]}

Jaramillo-Moran, Miguel Angel ^{[1
]}

Carmona-Fernandez, Diego ^{[1
]}

机构：

[1] Univ Extremadura, Escuela Ingn Ind, E-06071 Badajoz, Spain

来源：

COMPUTERS & INDUSTRIAL ENGINEERING | 2007年 / 52卷 / 03期

关键词：

demand forecasting; neural networks; time series;

D O I：

10.1016/j.cie.2006.12.010

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Electric energy demand forecasting is a fundamental tool for production and distribution companies because it provides them with a prediction of the market demand of electric energy. Two kinds of forecasting may be performed: short term and medium to long term. This work is focused on monthly prediction, which is useful for the maintenance planning of grids and as market research for electricity producers and resellers. The timed series of monthly electric energy demands presents a rising tendency due to the influence of economic and technological evolution on the electric market. Embedded in this general trend is a fluctuation caused by the difference in demand from month to month. This paper proposes the extraction of that trend to perform separate predictions of both tendency and fluctuation with neural networks, which will be summed up to obtain the series forecasting. A Mean Absolute Percentage Error (MAPE) of about 2% has been obtained. (c) 2007 Elsevier Ltd. All rights reserved.

引用

页码：336 / 343

页数：8

共 14 条

[1] Forecasting monthly electric energy consumption in eastern Saudi Arabia using univariate time-series analysis [J].

AbdelAal, RE ;

AlGarni, AZ .

ENERGY, 1997, 22 (11) :1059-1069

[2]

Bishop CM., 1995, Neural networks for pattern recognition

[3]

Box G. E., 1976, TIME SERIES ANAL FOR

[4]

Carmona D, 2002, IEEE IND ELEC, P1860

[5] RECURRENT NEURAL NETWORKS AND ROBUST TIME-SERIES PREDICTION [J].

CONNOR, JT ;

MARTIN, RD ;

ATLAS, LE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :240-254

[6]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[7] FORECASTING MONTHLY ELECTRIC-LOAD AND ENERGY FOR A FAST-GROWING UTILITY USING AN ARTIFICIAL NEURAL-NETWORK [J].

ISLAM, SM ;

ALALAWI, SM ;

ELLITHY, KA .

ELECTRIC POWER SYSTEMS RESEARCH, 1995, 34 (01) :1-9

[8] LOAD FORECASTING VIA SUBOPTIMAL SEASONAL AUTOREGRESSIVE MODELS AND ITERATIVELY REWEIGHTED LEAST-SQUARES ESTIMATION [J].

MBAMALU, GAN ;

ELHAWARY, ME .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1993, 8 (01) :343-348

[9] A REGRESSION-BASED APPROACH TO SHORT-TERM SYSTEM LOAD FORECASTING [J].

PAPALEXOPOULOS, AD ;

HESTERBERG, TC .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1990, 5 (04) :1535-1547

[10] ELECTRIC-LOAD FORECASTING USING AN ARTIFICIAL NEURAL NETWORK [J].

PARK, DC ;

ELSHARKAWI, MA ;

MARKS, RJ ;

ATLAS, LE ;

DAMBORG, MJ .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1991, 6 (02) :442-449

← 1 2 →