Artificial Neural Network Model for Hourly Peak Load Forecast

Authors

  • V. Ramesh Kumar Research Scholar Department of Electrical & Electronics Engineering, School of Engineering & Technology, Jain University, JGI Global Campus-562112 Karnataka, India
  • Pradipkumar Dixit Professor, Department of Electrical & Electronics Engineering, Ramaiah Institute of Technology, Bengaluru-560054, Karnataka, India.

Abstract

Artificial Neural Network model for short-term demand forecast of hourly peak load is proposed in this paper. For learning of the ANN model Levenberg-Marquardt algorithm is adopted because of its ability to handle the large number of non-linear load data. The training of network is done by using hourly peak load data of preceding five years from the period of forecast and the temperature data. The validation of the developed ANN model is tested with historical load data of BESCOM (Bangalore Electricity Supply Company Limited) power system.  The comparison of conventional methods and ANN model with respect to percentage error is evaluated, from the results it has been found that the proposed ANN model with optimal number of hidden layer neurons gives accurate predictions.Keywords: Artificial Neural Network, Normalization, ForecastingJEL Classifications: C8, Q470

Downloads

Download data is not yet available.

Downloads

Published

2018-09-05

How to Cite

Kumar, V. R., & Dixit, P. (2018). Artificial Neural Network Model for Hourly Peak Load Forecast. International Journal of Energy Economics and Policy, 8(5), 155–160. Retrieved from https://econjournals.com/index.php/ijeep/article/view/6792

Issue

Vol. 8 No. 5 (2018)

Section

Articles

License

Submission of an article implies that the work described has not been published previously , that it is not under consideration for publication elsewhere, that its publication is approved by all authors and tacitly or explicitly by the responsible authorities where the work was carried out, and that, if accepted, will not be published elsewhere in the same form, without the written consent of the Publisher. The Editors reserve the right to edit or otherwise alter all contributions, but authors will receive proofs for approval before publication.