Power load forecasting by neural network with a new learning process for considering overtraining problem

Author

Hwang, Rey-Chue ; Huang, Huang-Chu ; Chen, Yu-Ju ; Hsieh, Jer-Guans

Author_Institution

Dept. of Electr. Eng., I-Shou Univ., Kaohsiung, Taiwan

Volume

1

fYear

1998

fDate

3-5 Mar 1998

Firstpage

317

Abstract

In this paper, a neural network (NN) with a new learning process is proposed for power load forecasting to overcome the problem of over-training. This new learning process is developed to solve the problems of underfitting, resulting from under-training, and overfitting, resulting from over-training. As a comparison of the traditional method of cross-validation (CV) and our proposed learning process, Taipower load signals and relevant weather information from 1990 to 1993 are investigated

Keywords

learning (artificial intelligence); load forecasting; neural nets; power system analysis computing; Taipower load signals; cross-validation method; learning process; load forecasting; neural network; overfitting; overtraining problem; underfitting; weather information; Engineering management; IEEE members; Load forecasting; Neural networks; Power engineering and energy; Predictive models; Signal processing; Technology management; Testing; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Energy Management and Power Delivery, 1998. Proceedings of EMPD '98. 1998 International Conference on

Print_ISBN

0-7803-4495-2

Type

conf

DOI

10.1109/EMPD.1998.705545

Filename

705545