Smart Control Automation and Learning for Energy (SCALE)

This project will deploy an integration of Internet of Things, hardware, and software as a service control that uses machine learning to drive down the cost of powerful Model Predictive Control (MPC) in 10–50 K-12 sites across the state. The goal is to demonstrate a scalable, affordable solution for disadvantaged communities needing to manage changing utility rates, heating, ventilation, and air conditioning electrification, as well as energy codes. Widespread adoption of low-cost MPC in commercial buildings can collectively reduce peak energy demand, improve grid stability, and lower blackout risks.