Training free non-intrusive load monitoring of electronic appliances battery charging with low sampling rate

Abstract

Non-intrusive load monitoring (NILM) is a convenient method to determine the amount of energy consumed by individual electrical appliances of our household and operate them by analyzing the composite load measured directly at the main circuit panel or electric meter of the building. A significant reduction in the energy wastage can be achieved through this approach. A lot of remarkable researches were developed to establish the theory of NILM and introduced its innovative applications. However, forthcoming deployment of electronic vehicle battery (EVB) will challenge NILM systems as the previous methods are not suitable for recognizing the variable characteristics of it. In this paper, we propose an improved algorithm to disaggregate EV charging signals from aggregated real power signals. The proposed method can effectively mitigate interference coming from air-conditioner (AC) and detect EVB signals effectively under the presence of AC power signals. The results demonstrate that the EVB charging load is recognized as well as other traditional appliances.