Home Energy Recommendation System (HERS): A Deep Reinforcement Learning Method Based on Residents’ Feedback and Activity

Smart home appliances can take command and act intelligently, making them suitable for implementing optimization techniques. Artificial intelligence (AI) based control of these smart devices enables demand-side management (DSM) of electricity consumption. By integrating human feedback and activity in the decision process, this work proposes a deep Reinforcement Learning (RL) method for managing smart devices to optimize electricity cost and comfort residents. Our contributions are twofold. Firstly, we incorporate human feedback in the objective function of our DSM technique that we name Home Energy Recommendation System (HERS). Secondly, we include human activity data in the RL state definition to enhance the energy optimization performance. We perform comprehensive experimental analyses to compare the proposed deep RL approach with existing approaches that lack the aforementioned critical decision-making features. The proposed model is robust to varying resident activities and preferences and applicable to a broad spectrum of homes with different resident profiles.