Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow

Ilgiz Murzakhanov, Andreas Venzke, George S. Misyris, Spyros Chatzivasileiadis

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

94 Downloads (Pure)

Abstract

This paper introduces a framework to capture previously intractable optimization constraints and transform them to a mixed-integer linear program, through the use of neural networks. We encode the feasible space of optimization problems characterized by both tractable and intractable constraints, e.g. differential equations, to a neural network. Leveraging an exact mixed-integer reformulation of neural networks, we solve mixed-integer linear programs that accurately approximate solutions to the originally intractable non-linear optimization problem. We apply our methods to the AC optimal power flow problem (AC-OPF), where directly including dynamic security constraints renders the AC-OPF intractable. Our proposed approach has the potential to be significantly more scalable than traditional approaches. We demonstrate our approach for power system operation considering N-1 security and small-signal stability, showing how it can efficiently obtain cost-optimal solutions which at the same time satisfy both static and dynamic security constraints.
Original languageEnglish
Title of host publicationProceedings of 11th Bulk Power Systems Dynamics and Control Sympositum 2022
Number of pages8
Publication date2022
Publication statusPublished - 2022
Event11th Bulk Power Systems Dynamics and Control Symposium - Banff, Canada
Duration: 25 Jul 202230 Jul 2022
Conference number: 11

Conference

Conference11th Bulk Power Systems Dynamics and Control Symposium
Number11
Country/TerritoryCanada
CityBanff
Period25/07/202230/07/2022

Keywords

  • Neural networks
  • Mixed-integer linear programming
  • Optimal power flow
  • Power system security

Fingerprint

Dive into the research topics of 'Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow'. Together they form a unique fingerprint.

Cite this