PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation

Huayi Wu; Zhao Xu; Jiaqi Ruan; Xianzhuo Sun

doi:10.17775/CSEEJPES.2023.08830

PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation

Huayi Wu
, Zhao Xu
, Jiaqi Ruan
, Xianzhuo Sun

Research output: Journal article publication › Journal article › Academic research › peer-review

4 Citations (Scopus)

Abstract

A centralized framework-based data-driven framework for active distribution system state estimation (DSSE) has been widely leveraged. However, it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center. A personalized federated learning-based DSSE method (PFL-DSSE) is proposed in a decentralized training framework for DSSE. Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.

Original language	English
Pages (from-to)	2265-2270
Number of pages	6
Journal	CSEE Journal of Power and Energy Systems
Volume	10
Issue number	5
DOIs	https://doi.org/10.17775/CSEEJPES.2023.08830
Publication status	Published - Sept 2024

Keywords

Distribution system state estimation
personalized federated learning
privacy protection

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
General Energy
Electrical and Electronic Engineering

More information

10.17775/CSEEJPES.2023.08830

Cite this

@article{bdfac144ac964cd3bf021f62a99666c6,

title = "PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation",

abstract = "A centralized framework-based data-driven framework for active distribution system state estimation (DSSE) has been widely leveraged. However, it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center. A personalized federated learning-based DSSE method (PFL-DSSE) is proposed in a decentralized training framework for DSSE. Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.",

keywords = "Distribution system state estimation, personalized federated learning, privacy protection",

author = "Huayi Wu and Zhao Xu and Jiaqi Ruan and Xianzhuo Sun",

note = "Publisher Copyright: {\textcopyright} 2015 CSEE.",

year = "2024",

month = sep,

doi = "10.17775/CSEEJPES.2023.08830",

language = "English",

volume = "10",

pages = "2265--2270",

journal = "CSEE Journal of Power and Energy Systems",

issn = "2096-0042",

publisher = "China Electric Power Research Institute",

number = "5",

}

TY - JOUR

T1 - PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation

AU - Wu, Huayi

AU - Xu, Zhao

AU - Ruan, Jiaqi

AU - Sun, Xianzhuo

PY - 2024/9

Y1 - 2024/9

N2 - A centralized framework-based data-driven framework for active distribution system state estimation (DSSE) has been widely leveraged. However, it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center. A personalized federated learning-based DSSE method (PFL-DSSE) is proposed in a decentralized training framework for DSSE. Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.

AB - A centralized framework-based data-driven framework for active distribution system state estimation (DSSE) has been widely leveraged. However, it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center. A personalized federated learning-based DSSE method (PFL-DSSE) is proposed in a decentralized training framework for DSSE. Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.

KW - Distribution system state estimation

KW - personalized federated learning

KW - privacy protection

UR - https://www.scopus.com/pages/publications/85212058309

U2 - 10.17775/CSEEJPES.2023.08830

DO - 10.17775/CSEEJPES.2023.08830

M3 - Journal article

AN - SCOPUS:85212058309

SN - 2096-0042

VL - 10

SP - 2265

EP - 2270

JO - CSEE Journal of Power and Energy Systems

JF - CSEE Journal of Power and Energy Systems

IS - 5

ER -

PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this