Tag
This paper proposes a proxy-guided hierarchical reinforcement learning framework to defend against diverse inference attacks on smart meter data by learning battery-based load-shaping policies that disrupt non-intrusive load monitoring patterns.
From July 2026, energy retailers in NSW, South Australia, and South-East Queensland must provide at least three hours of free daytime electricity daily, leveraging solar power. The scheme, called the Solar Sharer Offer, requires a smart meter and opt-in, aiming to pass on cheap midday solar energy to households.