Multiplex Community Detection for Resilient Electrical Segmentation Enabling Management of an Increasingly Complex Power Grid
Abstract
The integration of renewable energy into the power grid presents a significant challenge for Transmission System Operators (TSOs). This context brings increasingly complex flow to manage, and the development of new tools becomes necessary. One promising solution to reduce complexity management of the grid consists of electrical segmentation, which aims to construct coherent electrical zones to help TSO’s operators focus on reduced areas independently. Electrical segmentation is based on electrical influence and allows for constructing zones with strong intra-zone mutual influence and low extra-zone influence between structures. However, electrical segmentation on a single situation may not adequately represent the constantly changing grid over time. This paper presents a new modeling approach for resilient segmentation based on multiplex graphs, which take advantage of different layers exhibiting grid variations. The resilient segmentation is computed by clustering the multiplex graph using a flattening process to compute a unified representation. The proposed model is evaluated in a real application, showing clearly its computation gain.
Cite
Text
Henka et al. "Multiplex Community Detection for Resilient Electrical Segmentation Enabling Management of an Increasingly Complex Power Grid." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2024. doi:10.1007/978-3-031-70381-2_16Markdown
[Henka et al. "Multiplex Community Detection for Resilient Electrical Segmentation Enabling Management of an Increasingly Complex Power Grid." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2024.](https://mlanthology.org/ecmlpkdd/2024/henka2024ecmlpkdd-multiplex/) doi:10.1007/978-3-031-70381-2_16BibTeX
@inproceedings{henka2024ecmlpkdd-multiplex,
title = {{Multiplex Community Detection for Resilient Electrical Segmentation Enabling Management of an Increasingly Complex Power Grid}},
author = {Henka, Noureddine and Tazi, Sami and Assaad, Mohamad},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2024},
pages = {247-262},
doi = {10.1007/978-3-031-70381-2_16},
url = {https://mlanthology.org/ecmlpkdd/2024/henka2024ecmlpkdd-multiplex/}
}