Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

Andreas Venzke, Guannan Qu, Steven Low, Spyros Chatzivasileiadis

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

Abstract

This paper introduces for the first time a framework to obtain provable worst-case guarantees for neural network performance, using learning for optimal power flow (OPF) problems as a guiding example. Neural networks have the potential to substantially reduce the computing time of OPF solutions. However, the lack of guarantees for their worst-case performance remains a major barrier for their adoption in practice. This work aims to remove this barrier. We formulate mixed-integer linear programs to obtain worst-case guarantees for neural network predictions related to (i) maximum constraint violations, (ii) maximum distances between predicted and optimal decision variables, and (iii) maximum sub-optimality. We demonstrate our methods on a range of PGLib-OPF networks up to 300 buses. We show that the worst-case guarantees can be up to one order of magnitude larger than the empirical lower bounds calculated with conventional methods. More importantly, we show that the worst-case predictions appear at the boundaries of the training input domain, and we demonstrate how we can systematically reduce the worst-case guarantees by training on a larger input domain than the domain they are evaluated on.
Original languageEnglish
Title of host publicationProceedings of 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids
Number of pages7
PublisherIEEE
Publication date2020
ISBN (Print)9781728161266
DOIs
Publication statusPublished - 2020
Event2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids - Tempe, United States
Duration: 11 Nov 202013 Nov 2020
https://ieeexplore.ieee.org/xpl/conhome/9302911/proceeding

Conference

Conference2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids
Country/TerritoryUnited States
CityTempe
Period11/11/202013/11/2020
Internet address

Fingerprint

Dive into the research topics of 'Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks'. Together they form a unique fingerprint.

Cite this