Home > Research > Publications & Outputs > The impact of preprocessing on forecasting elec...
View graph of relations

The impact of preprocessing on forecasting electrical load: an empirical evaluation of segmenting time series into subseries

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Publication date2011
Host publicationThe 2011 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationNew York
PublisherIEEE
Pages3285-3292
Number of pages8
ISBN (Print)978-1-4244-9636-5
<mark>Original language</mark>English
EventInternational Joint Conference on Neural Networks (IJCNN) - San Jose
Duration: 31/07/20115/08/2011

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN)
CitySan Jose
Period31/07/115/08/11

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN)
CitySan Jose
Period31/07/115/08/11

Abstract

Forecasting future electricity load represents one of the most prominent areas of electrical engineering, in which artificial neural networks (NN) are routinely applied in practice. The common approach to overcome the complexity of building NNs for high-frequency load data is to segment the time series into simpler and more homogeneous subseries, e. g. seven subseries of hourly loads of only Mondays, Tuesdays etc. These are forecasted independently, using a separate NN model, and then recombined to provide a complete trace forecast for the next days ahead. Despite the empirical importance of load forecasting, and the high operational cost associated with forecast errors, the potential benefits of segmenting time series into subseries have not been evaluated in an empirical comparison. This paper assesses the accuracy of segmenting continuous time series into daily subseries, versus forecasting the original, continuous time series with NNs. Accuracy on hourly UK load data is provided in a valid experimental design, using multiple rolling time origins and robust error metrics in comparison to statistical benchmark algorithms. Results indicate the superior performance of NN on continuous, non-segmented time series, in contrast to best practices in research, practice and software implementations.