Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Shimiao, Tuor, Aaron, Vrabie, Draguna, Pileggi, Larry, Drgona, Jan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.11677
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909903338078208
author Li, Shimiao
Tuor, Aaron
Vrabie, Draguna
Pileggi, Larry
Drgona, Jan
author_facet Li, Shimiao
Tuor, Aaron
Vrabie, Draguna
Pileggi, Larry
Drgona, Jan
contents Learning to optimize (L2O) parametric approximations of AC optimal power flow (AC-OPF) solutions offers the potential for fast, reusable decision-making in real-time power system operations. However, the inherent nonconvexity of AC-OPF results in challenging optimization landscapes, and standard learning approaches often fail to converge to feasible, high-quality solutions. This work introduces a \textit{homotopy-guided self-supervised L2O method} for parametric AC-OPF problems. The key idea is to construct a continuous deformation of the objective and constraints during training, beginning from a relaxed problem with a broad basin of attraction and gradually transforming it toward the original problem. The resulting learning process improves convergence stability and promotes feasibility without requiring labeled optimal solutions or external solvers. We evaluate the proposed method on standard IEEE AC-OPF benchmarks and show that homotopy-guided L2O significantly increases feasibility rates compared to non-homotopy baselines, while achieving objective values comparable to full OPF solvers. These findings demonstrate the promise of homotopy-based heuristics for scalable, constraint-aware L2O in power system optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Homotopy-Guided Self-Supervised Learning of Parametric Solutions for AC Optimal Power Flow
Li, Shimiao
Tuor, Aaron
Vrabie, Draguna
Pileggi, Larry
Drgona, Jan
Machine Learning
Learning to optimize (L2O) parametric approximations of AC optimal power flow (AC-OPF) solutions offers the potential for fast, reusable decision-making in real-time power system operations. However, the inherent nonconvexity of AC-OPF results in challenging optimization landscapes, and standard learning approaches often fail to converge to feasible, high-quality solutions. This work introduces a \textit{homotopy-guided self-supervised L2O method} for parametric AC-OPF problems. The key idea is to construct a continuous deformation of the objective and constraints during training, beginning from a relaxed problem with a broad basin of attraction and gradually transforming it toward the original problem. The resulting learning process improves convergence stability and promotes feasibility without requiring labeled optimal solutions or external solvers. We evaluate the proposed method on standard IEEE AC-OPF benchmarks and show that homotopy-guided L2O significantly increases feasibility rates compared to non-homotopy baselines, while achieving objective values comparable to full OPF solvers. These findings demonstrate the promise of homotopy-based heuristics for scalable, constraint-aware L2O in power system optimization.
title Homotopy-Guided Self-Supervised Learning of Parametric Solutions for AC Optimal Power Flow
topic Machine Learning
url https://arxiv.org/abs/2511.11677