A Unified Approach to Enforce Non-Negativity Constraint in Neural Network Approximation for Optimal Voltage Regulation

Simple item page
dc.contributor.authorWu, Jiaqi
dc.contributor.authorYuan, Jingyi
dc.contributor.authorWeng, Yang
dc.contributor.authorWang, Guangwen
dc.date.accessioned2024-12-26T21:06:52Z
dc.date.available2024-12-26T21:06:52Z
dc.date.issued2025-01-07
dc.description.abstractPower 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 (NN) 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 NN, 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.
dc.format.extent10
dc.identifier.doi10.24251/HICSS.2025.364
dc.identifier.isbn978-0-9981331-8-8
dc.identifier.other6e03c189-d0a6-479d-9bd4-d42e978800df
dc.identifier.urihttps://hdl.handle.net/10125/109206
dc.relation.ispartofProceedings of the 58th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectMonitoring, Control, and Protection
dc.subjectback-propagation, constraint integration, input convex neural network, input duplication, power system voltage regulation
dc.titleA Unified Approach to Enforce Non-Negativity Constraint in Neural Network Approximation for Optimal Voltage Regulation
dc.typeConference Paper
dc.type.dcmiText
prism.startingpage3014

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0295.pdf
Size:
749.67 KB
Format:
Adobe Portable Document Format
Download

Collections

Monitoring, Control, and Protection