Poster: Exposing the location of anonymous solar-powered homes

Abstract

Due to the decline of solar module prices, more and more people install solar panel energy systems. To better analyze the solar performance, solar generation data are transmitted on the Internet, stored in the cloud, even making the data available to the public. These data can leak privacy information, such as, the occupancy. However, people believe this information is not useful as the solar energy are "anonymous", which means the data cannot be associated to any identification information, such as account number or address, thus these solar-powered home energy data is often not treated as sensitive. Our key insight is solar energy data is not anonymous: since every location on the earth has unique solar and weather signature. We design a system to localize the "anonymous" solar-powered homes. We first localize the source home to a small region of interest by inferring the latitude and longitude from the information inherently embedded in the solar data. We then identify solar-powered homes within this region using satellite image processing by extracting and detecting rooftop solar deployment using a hybrid convolution neural networks (CNN) approach to identify a specific home without extra cost.