Energy Cost Forecasting for Event Venues

Authors

Katarina Grolinger, Western UniversityFollow
Andrea Zagar
Miriam AM Capretz, Western University
Luke Seewald

Document Type

Conference Proceeding

Publication Date

2015

Journal

Proceedings of the IEEE Electrical Power & Energy Conference

Abstract

Electricity price, consumption, and demand forecasting has been a topic of research interest for a long time. The proliferation of smart meters has created new opportunities in energy prediction. This paper investigates energy cost forecasting in the context of entertainment event-organizing venues, which poses significant difficulty due to fluctuations in energy demand and wholesale electricity prices. The objective is to predict the overall cost of energy consumed during an entertainment event. Predictions are carried out separately for each event category and feature selection is used to select the most effective combination of event attributes for each category. Three machine learning approaches are considered: k-nearest neighbor (KNN) regression, support vector regression (SVR) and neural networks (NN). These approaches are evaluated on a case study involving a large event venue in Southern Ontario. In terms of prediction accuracy, KNN regression achieved the lowest average error. Error rates varied greatly among different event categories.

Notes

Paper to be presented at the IEEE Electrical Power & Energy Conference in October 2015.