Federated Reinforcement Learning for Energy Management of Multiple Smart Homes With Distributed Energy Resources

This article proposesa novel federated reinforcement learning (FRL) approach for the energy management of multiple smart homes with home appliances, a solar photovoltaic system, and an energy storage system. The novelty of the proposed FRL approach lies in the development of a distributed deep reinforcement learning (DRL) model that consists of local home energy management systems (LHEMSs) and a global server (GS). Using energy consumption data, DRL agents for LHEMSs construct and upload their local models to the GS. Then, the GS aggregates the local models to update a global model for LHEMSs and broadcasts it to the DRL agents. Finally, the DRL agents replace the previous local models with the global model and iteratively reconstruct their local models. Simulation results obtained under heterogeneous home environments indicate the advantage of the proposed approach in terms of convergence speed, appliance energy consumption, and number of agents.

Automated summary

This article proposes a novel federated reinforcement learning approach for energy management in multiple smart homes. Using a distributed deep reinforcement learning model, the approach enables the updating and distribution of a global model through interactions between local home energy management systems and a global server, optimizing convergence speed, appliance energy consumption, and the number of agents.