AI learns to cut building energy costs while keeping the lights on
Researchers deployed an AI system that manages energy in school buildings without needing weather forecasts, automatically balancing solar power, EV charging, and user comfort while staying within safety limits. The approach could help facility managers cut costs and emissions while adapting to renewable energy's unpredictability.
Originaltitel: Safe Deep Reinforcement Learning Based Energy Management for Educational Buildings With Guaranteed Constraints
<p>Driven by sustainability goals and the increasing integration of renewable energy sources, effective energy management systems (EMS) are crucial for enabling smart buildings to operate efficiently. This paper proposes a safe real-time scheduling method based on deep reinforcement learning (DRL), employing the deep deterministic policy gradient (DDPG) algorithm to handle uncertainties in solar PV generation and energy demand without explicit forecasting. Compared to conventional DDPG, the proposed safe DDPG framework introduces a projection layer after the actor and target actor networks to ensure that all actions remain within operational constraints. A case study conducted on an educational building in Stockholm demonstrates the effectiveness of the proposed method in maintaining user comfort, satisfying EV charging requirements, ensuring dishwasher operation, and effectively utilizing the flexibility of both EVs and the dishwasher.</p>