Development of feed-forward network models to predict gas consumption

Author

Brown, Ronald H. ; Kharouf, Paul ; Feng, Xin ; Piessens, Luc P. ; Nestor, Dick

Author_Institution

Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA

Volume

2

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

802

Abstract

The development of feedforward artificial neural network based models to predict gas consumption on a daily basis is the subject of this paper. An iterative process based on network sensitivities and intuition to determine the proper input factors is discussed. The methods are applied to gas consumption for a region in metropolitan Milwaukee, WI. The obtained results indicate that the feedforward artificial neural network based models reduce the residual predicted consumption root mean squared errors by more than half when compared to models based on linear regression

Keywords

feedforward neural nets; iterative methods; public utilities; USA; Wisconsin; daily gas consumption prediction; feedforward neural network based models; intuition; iterative process; metropolitan Milwaukee; network sensitivities; residual predicted consumption root mean squared errors; Artificial neural networks; Companies; Feedforward systems; Heating; Linear regression; Mathematical model; Predictive models; Temperature sensors; Weather forecasting; Wind;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374281

Filename

374281