An Improved Non-Intrusive Load Monitoring Method for Recognition of Electric Vehicle Battery Charging Load

Non-intrusive load monitoring (NILM) is a convenient method to determine the electrical energy consumption and operation of individual appliances based on analysis of composite load measured at the entry of a building. It avoids installation of parallel sensors for monitoring individual appliances and could be applied in the smart metering system to obtain useful information for load management. This paper presents an improved NILM method that is capable of recognizing Electric Vehicle Battery (EVB) charging as a load type. Based on the proposed framework, a special pattern recognition algorithm is used to perform load disaggregation. A random switching simulator is developed to examine the performance of the improved NILM under various scenarios. The results demonstrate that the EVB charging load is recognized as well as other traditional appliances. The overall success rate of the disaggregation reaches 94.5% at typical circumstance. Through sensitivity analysis it is also shown that the EVB charging load makes a small impact on the overall performance.