A Time Series Data Feature Based Back Propagation Neural Network Approach for Non-intrusive Load Monitoring

With the advent of advanced metering infrastructure and data analytics, there is an increasing focus of nonintrusive load monitoring application (NILM) towards residential buildings and industrial systems. In this paper, a data- driven approach for NILM analysis is implemented using an actual chiller plant system operation dataset as the case study. The opportunities and challenges of NILM application from the dataset collection perspective are then briefly discussed. Unlike NILM residential buildings applications for on-off equipment status determination, NILM for industrial system focuses on estimating the power level of the disaggregated components.