PROJECT TITLE :

Influence of Data Granularity on Smart Meter Privacy

ABSTRACT:

Through sensible metering in the sensible grid finish-user domain, load profiles are measured per household. Personal information can be inferred from these load profiles by using nonintrusive appliance load monitoring methods, which has led to privacy issues. Privacy is predicted to increase with longer intervals between measurements of load curves. This paper studies the impact of data granularity jittery detection methods, which are the common 1st step in nonintrusive load monitoring algorithms. It's shown that when the time interval exceeds half the on-time of an appliance, the appliance use detection rate declines. Through a one-versus-rest classification modeling, the power to detect an appliance’s use is evaluated through F-scores. Representing these F-scores visually through a heatmap yields an easily understandable means of presenting potential privacy implications in sensible metering to the end-user or alternative decision makers.