DocumentCode :
2629504
Title :
Forecasting of electricity consumption: a comparison between an econometric model and a neural network model
Author :
Liu, X.Q. ; Ang, B.W. ; Goh, T.N.
Author_Institution :
Dept. of Ind. & Syst. Eng., Nat. Univ. of Singapore, Singapore
fYear :
1991
fDate :
18-21 Nov 1991
Firstpage :
1254
Abstract :
The authors compare two forecasting models, an econometric model and a neural network model, through a case study on electricity consumption forecasting for Singapore. The results show that the two models forecast the historical consumption from 1960 to 1984 equally well but, when used to make forecasts for 1985-90, they give very different results. This anomaly arises partly from the differences in the structure of the two models, and the problem is examined using the concept of elasticity in econometric studies. The results also show that a fully trained neural network model with a good fitting performance for the past may not give a good forecasting performance for the future
Keywords :
load forecasting; neural nets; power engineering computing; Singapore; econometric model; electricity consumption forecasting; forecasting models; load forecasting; neural network model; Econometrics; Economic forecasting; Economic indicators; Elasticity; Energy consumption; Neural networks; Predictive models; Systems engineering and theory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
Type :
conf
DOI :
10.1109/IJCNN.1991.170569
Filename :
170569
Link To Document :
بازگشت