Statistical and machine learning methods for electricity demand prediction

  • Authors:

  • Alexandra Kotillova;Irena Koprinska;Mashud Rana

  • Affiliations:

  • Department of Macro and Microeconomics, University of Žilina, Žilina, Slovakia;School of Information Technologies, University of Sydney, Sydney, Australia;School of Information Technologies, University of Sydney, Sydney, Australia

  • Venue:
  • ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We evaluate statistical and machine learning methods for half-hourly 1-step-ahead electricity demand prediction using Australian electricity data. We show that the machine learning methods, that use autocorrelation feature selection and Backpropagation Neural Networks, Linear Regression and Support Vector Regression as prediction algorithms, outperform the statistical methods Exponential Smoothing and ARIMA and also a number of baselines. We analyse the effect of the day time on the prediction error and show that there are time intervals associated with higher and lower errors and that the prediction methods also differ in their accuracy during the different time intervals. This analysis provides the foundation for a hybrid prediction model that achieved a prediction error MAPE of 0.51%.