Open Access

ARTICLE

Fuzzy k-Means Clustering-Based Machine Learning Models for LFO Damping in Electric Power System Networks

Md Shafiullah^1,2,*

1 Control & Instrumentation Engineering Department, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia
2 Interdisciplinary Research Center for Sustainable Energy Systems, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia

* Corresponding Author: Md Shafiullah. Email:

(This article belongs to the Special Issue: Advanced Artificial Intelligence and Machine Learning Methods Applied to Energy Systems)

Computer Modeling in Engineering & Sciences 2026, 146(2), 27 https://doi.org/10.32604/cmes.2026.075269

Received 28 October 2025; Accepted 02 February 2026; Issue published 26 February 2026

Abstract

Various factors, including weak tie-lines into the electric power system (EPS) networks, can lead to low-frequency oscillations (LFOs), which are considered an instant, non-threatening situation, but slow-acting and poisonous. Considering the challenge mentioned, this article proposes a clustering-based machine learning (ML) framework to enhance the stability of EPS networks by suppressing LFOs through real-time tuning of key power system stabilizer (PSS) parameters. To validate the proposed strategy, two distinct EPS networks are selected: the single-machine infinite-bus (SMIB) with a single-stage PSS and the unified power flow controller (UPFC) coordinated SMIB with a double-stage PSS. To generate data under various loading conditions for both networks, an efficient but offline meta-heuristic algorithm, namely the grey wolf optimizer (GWO), is used, with the loading conditions as inputs and the key PSS parameters as outputs. The generated loading conditions are then clustered using the fuzzy k-means (FKM) clustering method. Finally, the group method of data handling (GMDH) and long short-term memory (LSTM) ML models are developed for clustered data to predict PSS key parameters in real time for any loading condition. A few well-known statistical performance indices (SPI) are considered for validation and robustness of the training and testing procedure of the developed FKM-GMDH and FKM-LSTM models based on the prediction of PSS parameters. The performance of the ML models is also evaluated using three stability indices (i.e., minimum damping ratio, eigenvalues, and time-domain simulations) after optimally tuned PSS with real-time estimated parameters under changing operating conditions. Besides, the outputs of the offline (GWO-based) metaheuristic model, proposed real-time (FKM-GMDH and FKM-LSTM) machine learning models, and previously reported literature models are compared. According to the results, the proposed methodology outperforms the others in enhancing the stability of the selected EPS networks by damping out the observed unwanted LFOs under various loading conditions.

---

Keywords

---