Adaptive Informed Deep Neural Networks for Power Flow Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kaseb, Zeynab, Orfanoudakis, Stavros, Vergara, Pedro P., Palensky, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918281992994816
author Kaseb, Zeynab
Orfanoudakis, Stavros
Vergara, Pedro P.
Palensky, Peter
author_facet Kaseb, Zeynab
Orfanoudakis, Stavros
Vergara, Pedro P.
Palensky, Peter
contents This study introduces PINN4PF, an end-to-end deep learning architecture for power flow (PF) analysis that effectively captures the nonlinear dynamics of large-scale modern power systems. The proposed neural network (NN) architecture consists of two important advancements in the training pipeline: (A) a double-head feed-forward NN that aligns with PF analysis, including an activation function that adjusts to the net active and reactive power injections patterns, and (B) a physics-based loss function that partially incorporates power system topology information through a novel hidden function. The effectiveness of the proposed architecture is illustrated through 4-bus, 15-bus, 290-bus, and 2224-bus test systems and is evaluated against two baselines: a linear regression model (LR) and a black-box NN (MLP). The comparison is based on (i) generalization ability, (ii) robustness, (iii) impact of training dataset size on generalization ability, (iv) accuracy in approximating derived PF quantities (specifically line current, line active power, and line reactive power), and (v) scalability. Results demonstrate that PINN4PF outperforms both baselines across all test systems by up to two orders of magnitude not only in terms of direct criteria, e.g., generalization ability, but also in terms of approximating derived physical quantities.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02659
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Informed Deep Neural Networks for Power Flow Analysis
Kaseb, Zeynab
Orfanoudakis, Stavros
Vergara, Pedro P.
Palensky, Peter
Systems and Control
Artificial Intelligence
Signal Processing
This study introduces PINN4PF, an end-to-end deep learning architecture for power flow (PF) analysis that effectively captures the nonlinear dynamics of large-scale modern power systems. The proposed neural network (NN) architecture consists of two important advancements in the training pipeline: (A) a double-head feed-forward NN that aligns with PF analysis, including an activation function that adjusts to the net active and reactive power injections patterns, and (B) a physics-based loss function that partially incorporates power system topology information through a novel hidden function. The effectiveness of the proposed architecture is illustrated through 4-bus, 15-bus, 290-bus, and 2224-bus test systems and is evaluated against two baselines: a linear regression model (LR) and a black-box NN (MLP). The comparison is based on (i) generalization ability, (ii) robustness, (iii) impact of training dataset size on generalization ability, (iv) accuracy in approximating derived PF quantities (specifically line current, line active power, and line reactive power), and (v) scalability. Results demonstrate that PINN4PF outperforms both baselines across all test systems by up to two orders of magnitude not only in terms of direct criteria, e.g., generalization ability, but also in terms of approximating derived physical quantities.
title Adaptive Informed Deep Neural Networks for Power Flow Analysis
topic Systems and Control
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2412.02659