Application of data analytics for advanced demand profiling of residential load using smart meter data

This paper proposes a methodology for demand profiling, namely load decomposition, of aggregated residential load based on smart meter (SM) data. The methodology is applicable to both active and reactive load, following an assumption that SMs can monitor real-time active power consumption of individual appliances. Only a number of households in the aggregation are equipped with SMs in this study. The non-monitored users' load is decomposed using artificial neural network (ANN) trained with the available SM data. Information about load composition, in terms of load categories or load controllability, can be highly beneficial for various demand response (DR) applications. Different levels of SM coverage are considered in the study to illustrate the effect of the level of SM coverage on the accuracy of total aggregated load decomposition. The results show that the consumption of some load categories can be estimated with high confidence, even at lower levels of SM coverage.