Deep reinforcement learning for home energy management system control

ning techniques has been proven to be a viable solution for smart home energy management. These techniques autonomously control heating and domestic hot water systems, which are the most relevant loads in a dwelling, helping consumers to reduce energy consumption and also improving their comfort. Moreover, the number of houses equipped with renewable energy resources is increasing, and this is a key element for energy usage optimization, where coordinating loads and production can bring additional savings and reduce peak loads. In this regard, we propose the development of a deep reinforcement learning (DRL) algorithm for indoor and domestic hot water temperature control, aiming to reduce energy consumption by optimizing the usage of PV energy production. Furthermore, a methodology for a new dynamic indoor temperature setpoint definition is presented, thus allowing greater flexibility and savings. The results show that the proposed DRL algorithm combined with the dynamic setpoint achieved on average 8% of energy savings compared to a rule-based algorithm, reaching up to 16% of savings over the summer period. Moreover, the users comfort has not been compromised, as the algorithm is calibrated to not exceed more than 1% of the time out the specified temperature setpoints. Additional analysis shows that further savings could be achieved if the time out of comfort is increased, which could be agreed according to users needs. Regarding demand side management, the DRL control shows efficiency by anticipating and delaying actions for a PV self-consumption optimization, performing over 10% of load shifting. Finally, the renewable energy consumption is 9.5% higher for the DRL-based model compared to the rule-based, which means less energy consumed from the grid.