Abstract
A non-intrusive monitoring system estimates the behavior of individual electric appliances from the measurement of the total household load demand curve. The total load demand curve is measured at the entrance of the power line into the house. The power consumption of individual appliances can be estimated using several machine learning techniques by analyzing the characteristic frequency contents from the load curve of the household. We have already developed the monitoring system of ON/OFF states. This system could establish sufficient accuracy. In the next phase, the monitoring system should be able to estimate the power consumption for an air conditioner with an inverter circuit. In this paper, we present results of applying several regression methods such as multilayered perceptrons (MLP), radial basis function networks (RBFN) and support vector regressors (SVR) to estimate the power consumption of an air conditioner. Our experiments show that RBFN can achieve the best accuracy for the non-intrusive monitoring system.
