Smart Grid Stability Prediction Using Machine Learning

DOI

10.2991/978-94-6239-668-5_37How to use a DOI?

Keywords

Smart grid stability; machine learning; feature selection

Abstract

The increasing integration of renewable energy sources and prosumer-driven energy exchange has made smart grid stability a critical challenge for modern power systems. This study presents a comparative machine learning framework for predicting grid stability using a synthetic dataset derived from a four-node Decentralized Smart Grid Control (DSGC) model. Five complementary training approaches—standard learning, correlation-based feature selection, k-means–assisted enrichment, mutual-information–driven selection, and principal component analysis (PCA)—were systematically evaluated using a broad range of classifiers. Tree-based models demonstrated consistently superior performance, with XGBoost and LightGBM achieving up to 98.9% accuracy under PCA- and mutual-information–enhanced pipelines. These findings highlight the strong discriminative potential of machine learning for stability assessment and demonstrate that data-driven approaches can serve as efficient, interpretable, and computationally scalable tools for supporting reliable energy management in next-generation smart grids.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Berna Gurler Ari
AU  - Omer Faruk Alcin
PY  - 2026
DA  - 2026/05/14
TI  - Smart Grid Stability Prediction Using Machine Learning
BT  - Proceedings of the International Conference on Current Problems in Engineering and Applied Sciences (ICCPEAS 2025)
PB  - Atlantis Press
SP  - 338
EP  - 346
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-668-5_37
DO  - 10.2991/978-94-6239-668-5_37
ID  - Ari2026
ER  -