Knowledge transfer for long-term voltage stability assessment between power grids based on deep domain adaptation networks

Huaxiang Cai, David J. Hill

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

1 Citation (Scopus)

Abstract

For machine learning techniques, it is difficult to transfer knowledge between different domains due to the system discrepancy and limited training data. In this paper, we implement a knowledge transfer system (KTS) for long-term voltage stability assessment between power grids. First, system behaviours are converted to heatmaps with a more general method to avoid negative transfer. Then, a deep domain adaptation network (DDAN) is introduced to learn domain-invariant representations with strong semantic separations by adding a maximum-mean-discrepancy calculator. The KTS based on DDAN is performed to transfer knowledge from IEEE 39-bus system to IEEE 14-bus system. Case studies are also given to show its potential under those scenarios of data shortage.

Original languageEnglish
Title of host publication2020 12th IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC 2020)
EditorsFeng Wu, Ming Ni
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1345-1349
Number of pages5
ISBN (Electronic)9781728157481
ISBN (Print)9781728157498
DOIs
Publication statusPublished - 2020
Externally publishedYes
EventIEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) 2020 - Nanjing, China
Duration: 20 Sept 202023 Sept 2020
Conference number: 12th
https://ieeexplore.ieee.org/xpl/conhome/9212309/proceeding (Proceedings)

Publication series

NameAsia-Pacific Power and Energy Engineering Conference, APPEEC
PublisherIEEE, Institute of Electrical and Electronics Engineers
Volume2020-September
ISSN (Print)2157-4839
ISSN (Electronic)2157-4847

Conference

ConferenceIEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) 2020
Abbreviated titleAPPEEC 2020
Country/TerritoryChina
CityNanjing
Period20/09/2023/09/20
Internet address

Keywords

  • convolutional neural networks
  • deep domain adaptation
  • knowledge transfer
  • voltage stability

Cite this