Results (
Thai) 1:
[Copy]Copied!
Effective feedback can reduce building power consumption and carbon emissions. Therefore, providinginformation to building managers and tenants is the first step in identifying ways to reduce powerconsumption. Since reducing anomalous consumption can have a large impact, this study proposes anovel approach to using large sets of data for a building space to identify anomalous power consumption.This method identifies anomalies in two stages: consumption prediction and anomaly detection.Daily real-time consumption is predicted by using a hybrid neural net ARIMA (auto-regressive integratedmoving average) model of daily consumption. Anomalies are then identified by differences betweenreal and predicted consumption by applying the two-sigma rule. The experimental results for a17-week study of electricity consumption in a building office space confirm that the method can detectanomalous values in real time. Another contribution of the study is the development of a formalizedmethodology for detecting anomalous patterns in large data sets for real-time of building office spaceenergy consumption. Moreover, the prediction component can be used to plan electricity usage whilethe anomaly detection component can be used to understand the energy consumption behaviors oftenants.
Being translated, please wait..
