Adaptive threshold event detection method based on standard deviation

Abstract

Event detection is the foundation of event-based non-intrusive load detection solutions. Conventional event detection methods require a comprehensive consideration of the rated power levels of all devices within the detection scenario to define an appropriate threshold value. However, it cannot accurately detect both high- and low-power load events because of their fixed thresholds when loads with widely varying power change amplitudes are present simultaneously. Thus, an adaptive threshold event detection method based on standard deviation is proposed in this study. First, the aggregated power data are intercepted by a sliding window for a short period of time, and the standard deviation is calculated for the aggregated power data within the window. The event ends when the standard deviation reaches its maximum value. Next, the threshold for event detection is calculated based on the standard deviation, and event detection based on the calculated threshold and on the bilateral sliding window cumulative sum method is performed. Finally, various load tests are performed with Electricity Consumption & Occupancy (Kleiminger et al 2015 Proc. 2015 ACM Int. Joint Conf. on Pervasive and Ubiquitous Computing) datasets and private datasets. The F1 values exceeded 90% in all three scenarios, namely, office, factory and laboratory, indicating that the proposed method in this study has high event detection performance.