A Novel Multi-agent Cooperative Reinforcement Learning Method for Home Energy Management under a Peak Power-limiting

摘要

Home energy management plays a key role in demand response for residential customers to reduce the total cost via scheduling household loads energy consumption. However, excessive energy consumption by customers will bring a great challenge to the stability of the grid. To address the challenge, a day-ahead multi-agent reinforcement learning method is proposed for home energy management under a peak power-limiting. We first formulate the total cost minimization problem as a Markov game, and then a novel household loads energy consumption scheduling algorithm is proposed based on Mutil-agent Deep Deterministic Policy Gradient (MADDPG). It is worth mentioning that the proposed algorithm can achieve cooperation between agents so that it can meet the peak power-limiting constraint. Simulation results are provided in this paper to show the effectiveness of the proposed method.