Review on deep learning applications in frequency analysis and control of modern power system

Yi Zhang, Xiaohan Shi, Hengxu Zhang, Yongji Cao, Vladimir Terzija

Research output: Contribution to journalReview articlepeer-review

35 Citations (Scopus)

Abstract

The penetration of renewable energy resources (RES) generation and the interconnection of regional power grids in wide area and large scale have led the modern power system to exhibit more and more complex dynamic features, such as time-varying nonlinearity, uncertainty, data diversity, and local observability. The increasing complexity of power system's dynamic characteristics makes the traditional analysis and control methods inefficient, even invalid. As a new technology path of Machine Learning, Deep learning (DL) has distinct advantages in solving complex problems such as power system frequency analysis and control due to its powerful ability of data analysis, prediction, and classification. This paper reviews the history, state of art and the future of the DL's application in power system frequency analysis and control. Firstly, the basic principle and research progress of DL, the training methods, typical structures, and application peculiarity of DL were introduced. Secondly, the application status of DL in frequency situation awareness, frequency security and stability assessment, and frequency regulation and control were summarized, and the adaptability of DL application to each kind of issue was discussed. Finally, the development trend of DL and its application in power system frequency were prospected.

Original languageEnglish
Article number107744
JournalInternational Journal of Electrical Power and Energy Systems
Volume136
DOIs
Publication statusPublished - Mar 2022

Keywords

  • Artificial intelligence
  • Deep learning
  • Frequency analysis
  • Power system
  • Renewable energy
  • Smart grid

Fingerprint

Dive into the research topics of 'Review on deep learning applications in frequency analysis and control of modern power system'. Together they form a unique fingerprint.

Cite this