Learning to Optimize meets Neural-ODE: Real-Time, Stability-Constrained AC OPF

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Di Vito, Vincenzo, Mohammadian, Mostafa, Baker, Kyri, Fioretto, Ferdinando
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909364636352512
author Di Vito, Vincenzo
Mohammadian, Mostafa
Baker, Kyri
Fioretto, Ferdinando
author_facet Di Vito, Vincenzo
Mohammadian, Mostafa
Baker, Kyri
Fioretto, Ferdinando
contents Recent developments in applying machine learning to address Alternating Current Optimal Power Flow (AC OPF) problems have demonstrated significant potential in providing close to optimal solutions for generator dispatch in near real-time. While these learning to optimize methods have demonstrated remarkable performance on steady-state operations, practical applications often demand compliance with dynamic constraints when used for fast-timescale optimization. This paper addresses this gap and develops a real-time stability-constrained OPF model (DynOPF-Net) that simultaneously addresses both optimality and dynamical stability within learning-assisted grid operations. The model is a unique integration of learning to optimize that learns a mapping from load conditions to OPF solutions, capturing the OPF's physical and engineering constraints, with Neural Ordinary Differential Equations, capturing generator dynamics, enabling the inclusion of a subset of stability constraints. Numerical results on the WSCC 9-bus and IEEE 57-bus benchmark systems demonstrate that DynOPF-Net can produce highly accurate AC-OPF solutions while also ensuring system stability, contrasting the unstable results obtained by state-of-the-art LtO methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19157
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Optimize meets Neural-ODE: Real-Time, Stability-Constrained AC OPF
Di Vito, Vincenzo
Mohammadian, Mostafa
Baker, Kyri
Fioretto, Ferdinando
Systems and Control
Recent developments in applying machine learning to address Alternating Current Optimal Power Flow (AC OPF) problems have demonstrated significant potential in providing close to optimal solutions for generator dispatch in near real-time. While these learning to optimize methods have demonstrated remarkable performance on steady-state operations, practical applications often demand compliance with dynamic constraints when used for fast-timescale optimization. This paper addresses this gap and develops a real-time stability-constrained OPF model (DynOPF-Net) that simultaneously addresses both optimality and dynamical stability within learning-assisted grid operations. The model is a unique integration of learning to optimize that learns a mapping from load conditions to OPF solutions, capturing the OPF's physical and engineering constraints, with Neural Ordinary Differential Equations, capturing generator dynamics, enabling the inclusion of a subset of stability constraints. Numerical results on the WSCC 9-bus and IEEE 57-bus benchmark systems demonstrate that DynOPF-Net can produce highly accurate AC-OPF solutions while also ensuring system stability, contrasting the unstable results obtained by state-of-the-art LtO methods.
title Learning to Optimize meets Neural-ODE: Real-Time, Stability-Constrained AC OPF
topic Systems and Control
url https://arxiv.org/abs/2410.19157