Implementation of home energy management system based on reinforcement learning

The implementation of machine learning methods in home energy management have been shown to be a feasible alternative in the minimization of electricity cost. These methods regulate the home electric appliance systems, which contribute to the most critical loads in a household, thus enabling consumers to save electricity while still enhancing their comfort. Furthermore, renewable energy supplies are continuously integrating with other electricity resources in number of homes that is an important component to optimize energy consumption which result in the reduction of peak load and can bring economic benefits. In this paper, a reinforcement learning algorithm is explored for monitoring household electric appliances with the intention of lowering energy consumption through properly optimizing and addressing the best use renewable energy resources. The proposed method does not necessitate any previous information or knowledge of the uncertain dynamics and parameters of different household electric appliances. Simulation-based findings using real-time data validate the efficiency and reliability of the proposed method. (C) 2021 The Author(s). Published by Elsevier Ltd.

Automated summary

The feasibility of implementing machine learning methods in home energy management to minimize electricity cost by regulating home electric appliances systems and integrating renewable energy resources is explored in this paper. Simulation-based findings validate the efficiency and reliability of the proposed method without requiring previous information of household electric appliances.