Efficient Creation of Datasets for Data-Driven Power System Applications

Research output: Contribution to journalConference articleResearchpeer-review

34 Downloads (Pure)

Abstract

Advances in data-driven methods have sparked renewed interest for applications in power systems. Creating datasets for successful application of these methods has proven to be very challenging, especially when considering power system security. This paper proposes a computationally efficient method to create datasets of secure and insecure operating points. We propose an infeasibility certificate based on separating hyperplanes that can a-priori characterize large parts of the input space as insecure, thus significantly reducing both computation time and problem size. Our method can handle an order of magnitude more control variables and creates balanced datasets of secure and insecure operating points, which is essential for data-driven applications. While we focus on N-1 security and uncertainty, our method can extend to dynamic security. For PGLib-OPF networks up to 500 buses and up to 125 control variables, we demonstrate drastic reductions in unclassified input space volumes and computation time, create balanced datasets, and evaluate an illustrative data-driven application.
Original languageEnglish
Article number106614
JournalElectric Power Systems Research
Volume190
Number of pages9
ISSN0378-7796
DOIs
Publication statusPublished - 2021
EventXXI Power Systems Computation Conference - ONLINE EVENT, Porto, Portugal
Duration: 29 Jun 20203 Jul 2020
Conference number: 21
https://pscc2020.pt/

Conference

ConferenceXXI Power Systems Computation Conference
Number21
LocationONLINE EVENT
CountryPortugal
CityPorto
Period29/06/202003/07/2020
Internet address

Keywords

  • Convex relaxation
  • Data-driven
  • Machine learning
  • Optimal power flow
  • Power system operation

Cite this