Protecting privacy in microgrids using federated learning and deep reinforcement learning

Wenzhi Chen, Hongjian Sun*, Jing Jiang, Minglei You, William J.S. Piper

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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%.
Original languageEnglish
Title of host publication12th IET International Conference on Advances in Power System Control, Operation and Management (APSCOM)
Subtitle of host publicationEnabling high performance & resilience power grid: decarbonization, digitalization, automation, and beyond
Place of PublicationStevenage
Number of pages6
Publication statusAccepted/In press - 1 Oct 2022
Event12th IET International Conference on Advances in Power System Control, Operation and Management (APSCOM): Enabling high performance & resilience power grid: decarbonization, digitalization, automation, and beyond - Hyatt Regency Tsim Sha Tsui, Hong Kong, Hong Kong
Duration: 7 Nov 20229 Nov 2022
https://www.apscom.org/

Conference

Conference12th IET International Conference on Advances in Power System Control, Operation and Management (APSCOM)
Abbreviated titleAPSCOM 2022
Country/TerritoryHong Kong
CityHong Kong
Period7/11/229/11/22
Internet address

Fingerprint

Dive into the research topics of 'Protecting privacy in microgrids using federated learning and deep reinforcement learning'. Together they form a unique fingerprint.

Cite this