IEL’s PhD student Jose presented his research on reinforcement learning for buildings today at CISBAT in Lausanne, Switzerland. The research was recognized by the committee with a Best Paper Award!! Well done, Jose!
Abstract:
In this study, a heat pump satisfies the heating and cooling needs of a building, and two water tanks store heat and cold respectively. Reinforcement learning (RL) is a model-free control approach that can learn from the behaviour of the occupants, weather conditions, and the thermal behaviour of the building in order to make near-optimal decisions. In this work we use of a specific RL technique called batch Q-learning, and integrate it into the urban building energy simulator CitySim. The goal of the controller is to reduce the energy consumption while maintaining adequate comfort temperatures.
Vazquez-Canteli, J., Kämpf, J., Nagy, Z., 2017. Balancing comfort and energy consumption of a heat pump using batch reinforcement learning with fitted Q-iteration, in: CISBAT 2017 Int’l. Conf. Future Buildings and Districts.