Jul 2026· International Journal of Energy and Smart Grid· 0 citations· 12 references
TL;DR
The findings of this research underscore the potential of data-driven techniques in improving the robustness and flexibility of AC protection systems in contemporary microgrids.
Abstract
This paper presents a simulation-based analysis of fault detection in alternating current microgrids through data-driven methods. A detailed simulation-based microgrid model is created for conducting the fault analysis, including single phase ground fault, line fault, two phase fault and three phase fault situations. Simulations were carried out under different loading conditions and fault impedance values to obtain an extensive set of data containing voltage, current, and signal characteristics. This data was used to test the performance of various machine learning techniques for fault classification. The results show that the ensemble methods perform better than standalone models, with Random Forest (RF) demonstrating the highest classification performance. This findings of this research underscore the potential of data-driven techniques in improving the robustness and flexibility of AC protection systems in contemporary microgrids. Future work will focus on extending the analysis to more complex fault conditions and validating the proposed approach through real-time implementation.
The dataset is designed for training, fine-tuning, and benchmarking machine learning models by providing synchronized point-on-wave voltage and current measurements across a diverse set of topologies and voltage levels.
Georg Kordowich, Jonathan Loebel, Julian Oelhaf et al.· 0 citations
The results indicate that phase-angle information provides supplementary and class dependent discriminative value, but does not consistently improve all fault classes, whereas conventional voltage and current measurements alone represent a simpler and more stable alternative, whereas phase-angle measurements may be incorporated when synchronized phasor information is already available.
Zeynep Bala Duranay, İsmail Anıl Avcı, Mohammed Bushra Mohammed et al.· Symmetry· 0 citations
The reliable operation of smart distribution grids depends heavily on the timely detection and accurate classification of faults. Traditional fault detection methods, such as impedance and threshold-based analysis, provide essential diagnostic insights but are limited under noisy and dynamic operating conditions. This study proposes a hybrid framework combining MATLAB/Simulink-based modeling with Artificial Intelligence (AI) to enhance fault detection and classification in smart distribution grids. Fault scenarios including single line-to-ground (SL_G), line-to-line (L_L), double line-to-ground (LL_G), three-phase (LLL), and no-fault conditions were simulated to generate a labeled dataset of 9201 samples. The dataset was then used to train two AI models: a Multilayer Perceptron (MLP) and an Extreme Gradient Boosting (XGBoost) classifier. The MLP achieved the highest classification accuracy of 96.3%, while XGBoost reached 95.5% with reduced training complexity and faster execution. Comparative analysis demonstrated that AI-based approaches significantly outperform traditional methods in accuracy, adaptability, and computational efficiency. These results highlight the potential of integrating AI into modern power system protection schemes to achieve rapid, accurate, and cost-effective fault detection.
Nizar Jabar Faqishafyee, Halbast Rashid Ismael, A. Hasan· Academic Journal of Internat...· 0 citations
A robust Machine Learning (ML)-based framework for accurately locating electrical faults in wind farm collector networks and achieves the highest accuracy, with prediction errors not exceeding 2%.
Miguel R. Fonseca, M. Davi, M. Oleskovicz· IEEE Access· 0 citations
The increasing operational complexity and fault vulnerability of Nigeria’s electrical distribution
networks demand intelligent systems capable of rapid fault detection, accurate localization, and
efficient isolation. This study develops an intelligent fault detection and location framework for
the Ayepe 34-bus Nigerian distribution network using the Adaptive Differential Evolution (ADE)
algorithm. A mathematical model for fault location and distance estimation was formulated
based on voltage and current measurements derived from the network’s impedance
characteristics. The Forward and Backward Sweep (FBS) technique was employed to determine
pre- and post-fault voltage and current profiles of the distribution buses under steady-state and
faulted conditions. The ADE algorithm was implemented to minimize the fault location distance
error and optimize fault clearing time, enabling improved coordination of network protection
devices. Simulation was conducted in MATLAB R2023a, and the ADE performance was
compared with that of Genetic Algorithm (GA) and Political Optimization (PO) approaches.
Results show that ADE achieved faster convergence, lower fault location error, and shorter
clearing times than GA and PO. Specifically, the ADE-based model accurately identified fault
locations at buses 6, 15, 20, and 30, with an average fault clearing time of 80–92 ms and
enhanced post-fault voltage recovery of approximately 0.77 p.u. The proposed ADE framework
demonstrated superior precision, adaptability, and reliability, contributing to more efficient fault
management and improved service continuity. This research establishes ADE as a powerful
optimization-based tool for intelligent fault detection and location in Nigeria’s medium-voltage
distribution networks, enhancing overall grid stability and operational efficiency.
G. Ajenikoko· INTERNATIONAL JOURNAL OF APP...· 0 citations
Transmission line faults play a significant role in affecting power systems' reliability, stability, and security. This paper presents a fault classifying structure based on PMU, which diagnoses transmission line faults accurately through utilizing machine learning methods. The real-time measured and synchronized multiple times plan composed of phase currents, phase voltages, voltage magnitude, current magnitude, phase angles, and frequency parameters extracted from Phasor Measurement Units (PMUs). Support Vector Machine (SVM), XGBoost, and CatBoost were chosen as machine learning algorithms to classify faults. In addition, this paper develops a hybrid model based on combining these classifiers to enhance prediction performance. In conclusion, this system classifies five kinds of transmission line conditions including NF, LG, LL, LLG, and LLLG fault. Simulation results indicate that the proposed hybrid method achieved 99.98% classification accuracy and the individual classifiers obtain less than that. Besides, feature importance analysis found that voltage phase angle, current magnitude, and voltage magnitude were the most important parameters for fault diagnosis. The proposed method provides an efficient and reliable solution for smart grid monitoring, real-time fault diagnosis, and power system protection applications.
S. P, S. Shanmugam, Hariprabhu M et al.· 2026 International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
