CaltechAUTHORS
  A Caltech Library Service

DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibility

Zhao, Tianyu and Pan, Xiang and Chen, Minghua and Venzke, Andreas and Low, Steven H. (2020) DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibility. In: 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm). IEEE , Piscataway, NJ. ISBN 9781728161273. https://resolver.caltech.edu/CaltechAUTHORS:20210113-163505726

[img] PDF - Submitted Version
See Usage Policy.

429Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210113-163505726

Abstract

Deep Neural Networks approaches for the Optimal Power Flow (OPF) problem received considerable attention recently. A key challenge of these approaches lies in ensuring the feasibility of the predicted solutions to physical system constraints. Due to the inherent approximation errors, the solutions predicted by Deep Neural Networks (DNNs) may violate the operating constraints, e.g., the transmission line capacities, limiting their applicability in practice. To address this challenge, we develop DeepOPF+ as a DNN approach based on the so-called "preventive" framework. Specifically, we calibrate the generation and transmission line limits used in the DNN training, thereby anticipating approximation errors and ensuring that the resulting predicted solutions remain feasible. We theoretically characterize the calibration magnitude necessary for ensuring universal feasibility. Our DeepOPF+ approach improves over existing DNN-based schemes in that it ensures feasibility and achieves a consistent speed up performance in both light-load and heavy-load regimes. Detailed simulation results on a range of test instances show that the proposed DeepOPF+ generates 100% feasible solutions with minor optimality loss. Meanwhile, it achieves a computational speedup of two orders of magnitude compared to state-of-the-art solvers.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/smartgridcomm47815.2020.9303017DOIArticle
https://arxiv.org/abs/2009.03147arXivDiscussion Paper
ORCID:
AuthorORCID
Pan, Xiang0000-0002-6565-2339
Venzke, Andreas0000-0002-6101-6001
Low, Steven H.0000-0001-6476-3048
Additional Information:© 2020 IEEE.
Record Number:CaltechAUTHORS:20210113-163505726
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210113-163505726
Official Citation:T. Zhao, X. Pan, M. Chen, A. Venzke and S. H. Low, "DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibility," 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Tempe, AZ, USA, 2020, pp. 1-6, doi: 10.1109/SmartGridComm47815.2020.9303017
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:107471
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:14 Jan 2021 18:19
Last Modified:04 Feb 2021 00:13

Repository Staff Only: item control page