Sometimes, Money Does Grow On Trees: Data-Driven Demand Response with DR-Advisor

摘要: Real-time electricity pricing and demand response has become a clean, reliable cost-effective way of mitigating peak on the grid. We consider problem end-user (DR) for large commercial buildings which involves predicting baseline, evaluating fixed DR strategies synthesizing control actions load curtailment in return financial reward. Using historical data from building, we build family regression trees learn data-driven models power consumption building real-time. present method called DR-Advisor DR-Advisor, acts as recommender system building's facilities manager provides suitable to meet desired while maintaining operations maximizing economic evaluate performance using real office virtual test-bed.