Home energy management under realistic and uncertain conditions: A comparison of heuristic, deterministic, and stochastic control methods.

Home energy management systems (HEMS) have been shown to reduce energy bills and to provide grid services including peak demand reduction and demand flexibility. However, uncertainty in residential energy systems is a significant issue and can reduce the benefits of a HEMS to the homeowner or grid operator. Sources of uncertainty include weather forecasts, predictions of energy-related occupant activities (e.g., hot water draws), and parameter estimation for the building envelope and energy-consuming equipment. This paper tackles the problem of uncertainty by developing a framework that simulates HEMS in uncertain conditions and evaluates the performance of multiple control strategies. A linear, reduced-order residential building model for model predictive control applications is derived and compared to a full-order model. Stochastic model predictive control is shown to perform better than deterministic and heuristic methods when considering realistic forecasts with uncertainty. The framework can evaluate the performance of HEMS in real-world applications, which can help de-risk HEMS deployment. • Uncertainty from weather and occupant forecasts impact home energy management. • A stochastic control framework is developed for a home energy management system. • A reduced-order linear house model is developed for model predictive control. • Incorporating uncertain forecasts reduces control performance in HEMS. • Stochastic MPC outperforms common deterministic and heuristic control methods. [ABSTRACT FROM AUTHOR]