How the quantity and quality of training data impacts re-identification of smart meter users?

We study the feasibility of linking two disjoint smart meter datasets for the purpose of re-identification. In particular, we present an empirical results of how the quantity of electricity consumption data and the quality of data (sampling granularity) affects the re-identification accuracy, using commercial & industrial (C&I) and residential energy usage datasets. We use publicly available C&I and residential electricity consumption traces to evaluate the performance of different algorithms and different feature spaces. Our goal is to provide empirical evidence to guide the discussion of how electric utilities, public utility commissions, and regulators should define policies for collecting and handling electricity consumption data.