Protecting privacy in microgrids using federated learning and deep reinforcement learning

Chen, Wenzhi; Sun, Hongjian; Jiang, Jing; You, Minglei; Piper, William

doi:10.1049/icp.2023.0100

Protecting privacy in microgrids using federated learning and deep reinforcement learning

Chen, Wenzhi; Sun, Hongjian; Jiang, Jing; You, Minglei; Piper, William

Authors

Michael Chen wenzhi.chen@durham.ac.uk
PGR Student Doctor of Philosophy

Professor Hongjian Sun hongjian.sun@durham.ac.uk
Professor

Jing Jiang

Minglei You

William Piper

Abstract

This paper aims to improve the energy management efficiency of home microgrids while preserving privacy. The proposed microgrid model includes energy storage systems, PV panels, loads, and the connection to the main grid. A federated multi-objective deep reinforcement learning architecture with Pareto fronts is proposed for total carbon emission and electricity bills optimization. The privacy of data is protected by federated learning, by which the original data will not be uploaded to the server. Numerical results show that compared with the traditional single Deep-Q network, using the proposed method the accumulated carbon emission decreased by 3% and the electricity bills decreased by 21%.

Citation

Chen, W., Sun, H., Jiang, J., You, M., & Piper, W. (2022). Protecting privacy in microgrids using federated learning and deep reinforcement learning. . https://doi.org/10.1049/icp.2023.0100

Conference Name	12th IET International Conference on Advances in Power System Control, Operation and Management (APSCOM 2022)
Conference Location	Hong Kong, China
Start Date	Nov 6, 2022
End Date	Nov 9, 2022
Acceptance Date	Oct 1, 2022
Publication Date	2022-11
Deposit Date	Oct 9, 2022
Publicly Available Date	Nov 30, 2022
Publisher	Institution of Engineering and Technology (IET)
Pages	205-210
DOI	https://doi.org/10.1049/icp.2023.0100
Public URL	https://durham-repository.worktribe.com/output/1135513
Additional Information	7-9 November 2022