Comfort-aware Cognitive Buildings LeveragingDeep Reinforcement Learning
Contributo in Atti di convegno
Data di Pubblicazione:
2020
Abstract:
This paper presents a novel approach for the management of buildings by leveraging cognitive technologies. The proposed approach exploits the Deep Reinforcement Learningparadigm to learn from both a physical and a simulated environment so as to optimize people comfort and energy consumption.
Tipologia CRIS:
04.01 Contributo in Atti di convegno
Keywords:
Deep Reinforcement Learning; Smart Buildings; Energy Saving; Simulation; Cognitive Systems
Elenco autori:
Palopoli, Fabio; Spezzano, Giandomenico; Mastroianni, Carlo; Cicirelli, FRANCO DOMENICO; Guerrieri, Antonio; Vinci, Andrea
Link alla scheda completa: