Implementing a weighted least squares procedure in training a neural network to solve the short-term load forecasting problem

Author

Choueiki, M. Hisham ; Mount-Campbell, Clark A. ; Ahalt, Stanley C.

Author_Institution

Public Utilities Commission of Ohio, Columbus, OH, USA

Volume

12

Issue

4

fYear

1997

fDate

11/1/1997 12:00:00 AM

Firstpage

1689

Lastpage

1694

Abstract

The use of a weighted least squares procedure when training a neural network to solve the short-term load forecasting (STLF) problem is investigated. Our results indicate that a neural network that implements the weighted least squares procedure outperforms a neural network that implements the least squares procedure during the on-peak period for the two performance criteria specified; MAE% and COST, during the entire period for the COST criterion. It is therefore, recommended that the weighted least squares procedure be further studied by electric utilities which use neural networks to forecast their short-term load, and experience large variabilities in their hourly marginal energy costs during a 24-hour period

Keywords

economics; learning (artificial intelligence); least squares approximations; load forecasting; neural nets; power system analysis computing; COST; MAE%; hourly marginal energy costs variation; neural network training; on-peak period; performance criteria; short-term load forecasting; weighted least squares procedure; Costs; Economic forecasting; Industrial training; Intelligent networks; Least squares methods; Load forecasting; Neural networks; Power industry; Power system economics; Production;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/59.627877

Filename

627877