Mining big building operational data for building cooling load prediction and energy efficiency improvement

Abstract

This paper aims to explore the potential application of advanced DM techniques for effective utilization of big building operational data. Case studies of mining the operational data of an institutional building for cooling load prediction and operation performance improvement is presented. Deep learning-based prediction techniques, decision tree and association rule mining are adopted to analyze the operational data. The results show that useful knowledge can be extracted for forecasting 24-hour ahead building cooling load profiles, identifying typical building operation patterns and spotting energy conservation opportunities.