Saved in:
Bibliographic Details
Main Authors: Wu, Jiaqi, Yuan, Jingyi, Weng, Yang, Wang, Guangwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918191349891072
author Wu, Jiaqi
Yuan, Jingyi
Weng, Yang
Wang, Guangwen
author_facet Wu, Jiaqi
Yuan, Jingyi
Weng, Yang
Wang, Guangwen
contents Power system voltage regulation is crucial to maintain power quality while integrating intermittent renewable resources in distribution grids. However, the system model on the grid edge is often unknown, making it difficult to model physical equations for optimal control. Therefore, previous work proposes structured data-driven methods like input convex neural networks (ICNN) for "optimal" control without relying on a physical model. While ICNNs offer theoretical guarantees based on restrictive assumptions of non-negative neural network parameters, can one improve the approximation power with an extra step on negative duplication of inputs? We show that such added mirroring step fails to improve accuracy, as a linear combination of the original input and duplicated input is equivalent to a linear operation of ICNN's input without duplication. While this design can not improve performance, we propose a unified approach to embed the non-negativity constraint as a regularized optimization of the neural network, contrary to the existing methods, which added a loosely integrated second step for post-processing on parameter negation. Our integration directly ties back-propagation to simultaneously minimizing the approximation error while enforcing the convexity constraints. Numerical experiments validate the issues of the mirroring method and show that our integrated objective can avoid problems such as unstable training and non-convergence existing in other methods for optimal control. (preprint)
format Preprint
id arxiv_https___arxiv_org_abs_2503_12380
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Unified Approach to Enforce Non-Negativity Constraint in Neural Network Approximation for Optimal Voltage Regulation
Wu, Jiaqi
Yuan, Jingyi
Weng, Yang
Wang, Guangwen
Systems and Control
Power system voltage regulation is crucial to maintain power quality while integrating intermittent renewable resources in distribution grids. However, the system model on the grid edge is often unknown, making it difficult to model physical equations for optimal control. Therefore, previous work proposes structured data-driven methods like input convex neural networks (ICNN) for "optimal" control without relying on a physical model. While ICNNs offer theoretical guarantees based on restrictive assumptions of non-negative neural network parameters, can one improve the approximation power with an extra step on negative duplication of inputs? We show that such added mirroring step fails to improve accuracy, as a linear combination of the original input and duplicated input is equivalent to a linear operation of ICNN's input without duplication. While this design can not improve performance, we propose a unified approach to embed the non-negativity constraint as a regularized optimization of the neural network, contrary to the existing methods, which added a loosely integrated second step for post-processing on parameter negation. Our integration directly ties back-propagation to simultaneously minimizing the approximation error while enforcing the convexity constraints. Numerical experiments validate the issues of the mirroring method and show that our integrated objective can avoid problems such as unstable training and non-convergence existing in other methods for optimal control. (preprint)
title A Unified Approach to Enforce Non-Negativity Constraint in Neural Network Approximation for Optimal Voltage Regulation
topic Systems and Control
url https://arxiv.org/abs/2503.12380