Multiagent DRL-Based Demand Response Optimization for IoT-Based Smart Home Energy Management Systems

The integration of IoT devices with smart home energy management systems (SHEMS) presents a significant advancement in energy demand response (DR) optimization. However, due to the rapid proliferation of home appliances with varying operating characteristics as well as the variable comfort level demands of users, making effective DR decisions becomes more challenging. In this paper, we propose a hierarchical Stackelberg game-based incentive mechanism with multi-agent deep reinforcement learning (MADRL) to optimize DR in IoT-based SHEMS. We formulate the hierarchical decision-making problem as a Markov decision process (MDP) and then adopt the multi-agent deep deterministic policy gradient (MADDPG) algorithm to solve it by finding an equilibrium solution. Through extensive simulations, we demonstrate that our proposed DR optimization approach can effectively reduce overall energy consumption and peak load by 30.41% and 28.57% from the benchmark approaches, respectively. In addition, the proposed approach maintains user comfort and increases system utility by 13.11% and 15.74% than the benchmark schemes, respectively, resulting in improved energy efficiency.