Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads
This addresses the challenge of coordinating residential loads for grid stability, offering a scalable solution for renewable energy integration, though it appears incremental as it builds on existing multi-agent methods.
The paper tackled the problem of fast-timescale demand response for frequency regulation in power grids with renewable energy by proposing a decentralized multi-agent reinforcement learning approach with localized communication, achieving robust performance and seamless scalability to arbitrary numbers of houses with constant processing times.
To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale variations in power generation. Frequency regulation through demand response has the potential to coordinate temporally flexible loads, such as air conditioners, to counteract these variations. Existing approaches for discrete control with dynamic constraints struggle to provide satisfactory performance for fast timescale action selection with hundreds of agents. We propose a decentralized agent trained with multi-agent proximal policy optimization with localized communication. We explore two communication frameworks: hand-engineered, or learned through targeted multi-agent communication. The resulting policies perform well and robustly for frequency regulation, and scale seamlessly to arbitrary numbers of houses for constant processing times.