Evaluation of a case-based Reasoning Energy Prediction Tool for Commercial Buildings

Abstract

This paper presents the results of an energy predictor that predicts the energy demand of commercial buildings using Case Based Reasoning (CBR). The proposed approach is evaluated using monitored data in a real office building located in Varennes, Quebec. The energy demand is predicted at every hour for the following three hours using weather forecasts. The results show that during occupancy, 7:00 to 17:00, the coefficient of variance of the root-mean-square-error (CVRMSE) is below 12.3%, the normalized mean bias error (NMBE) is below 1.3% and the root-meansquare- error (RMSE) is below 16.6 kW. When the statistical criteria are calculated for all hours of the day, the CV-RMSE is 13.9%, the NMBE is 2.7% and the RMSE is 17.9 kW. The case study demonstrates that CBR can be used for energy demand prediction and could be implemented in building operation systems.