Disaggregating Solar Generation Using Smart Meter Data and Proxy Measurements from Neighbouring Sites

Abstract

This paper investigates the problem of disaggregating solar generation from smart meter data when historical disaggregated data from the target home is unavailable and deployment characteristics of the PV system are unknown. The proposed method takes advantage of solar generation data (aka proxy measurements) from a few sites located in the same area as the target home, and solar generation data synthesized using a physical PV model. We evaluate our method with 4 different proxy settings on around 140 homes in Australia, and show that the solar disaggregation accuracy is improved by 33.84% and 15.41% over two state-of-the-art methods using only one real proxy along with three synthetic proxies. Furthermore, we show that using the disaggregated home load instead of the net load measured by a smart meter could improve the accuracy of two popular non-intrusive load monitoring techniques by at least 22%.