Can HVAC really learn from users? A simulation-based study on the effectiveness of voting for comfort and energy use optimization

•A system that tracks the occupants’ groups preferences, learns from them, and manages HVAC automatically is proposed.•The envisioned system aims at controlling HVAC to minimize the energy consumption while maximizing average user comfort.•A prototype solution is described and evaluated by simulation.•Results show that a machine learning technique enables to reduce energy consumption while keeping acceptable comfort levels.