Skip to content
Preprint

Multi-Library Feature Engineering and Statistically Validated Classification for Power Swing Detection and Stability Assessment

Nov 2026 · 0 citations · 24 references
Engineering Computer Science

Abstract

Faults occurring during power swings, and the evolution of a swing into an unstable condition, cause distance-relay maloperation and cascaded outages. This paper identifies faults, faults during power swings, and power swings, and distinguishes stable from unstable swings in a 9-bus WSCC system modeled in PSCAD/EMTDC. Three time-series feature libraries (tsfresh, TSFEL, and tsfeatures) are applied to the 3-phase relay voltages and currents, giving 3286 statistical, temporal, spectral, and fractal descriptors per event window. A two-step feature selection (Boruta all-relevant filtering followed by RFECV- and SHAP-guided minimal-optimal pruning) reduces the feature set to 18 compact, non-redundant features. 14 classifiers spanning linear, kernel/instance-based, probabilistic, neural, and tree-ensemble/boosting families are then benchmarked under repeated stratified cross-validation, with model differences assessed by a Friedman/Nemenyi omnibus-and-post-hoc test and a Nadeau--Bengio corrected paired t-test. Rotation Forest (ROF) identifies the three event types with 99.98% and SVM-RBF distinguishes stable from unstable swings with 97.97% balanced accuracy. The results show that automated, library-driven feature extraction combined with rigorous statistical model comparison achieves near-perfect discrimination while retaining feature-level interpretability through SHAP importance.

View source

Similar papers

Open access Dec 2026

Multiclass Electrical Fault Classification in Three-Phase Power Systems Using Random Forest, Support Vector Machine, and XGBoost

Electrical fault classification in three-phase power systems remains challenging because different fault conditions can exhibit similar current and voltage characteristics, limiting the diagnostic capability of conventional binary fault detection. This study aimed to compare the performance of Random Forest, Support Ve...

S. Mardiyati, Pandhu Pramarta · 0 citations
Open access Oct 2026

Sampling-Frequency-Aware Wavelet-Statistical Features for Fault Diagnostics in Inverter-Integrated Medium-Voltage Networks

Inverter-based resources (IBRs) alter fault behaviour in medium-voltage (MV) networks, while heterogeneous monitoring devices operating at different sampling rates provide different bandwidths and representations of fault transients, complicating consistent feature formulation for data-driven fault diagnostics. This st...

S. Onyedikachi, O. M. Longe · 0 citations
Sep 2026

Data-Driven Fault Location of Integrated Ship Power System

Rapid identification of a faulted node is important for maintaining the reliability of integrated ship power systems. Fault-current transients are nonstationary, making their representation relevant to data-driven diagnosis. Methods based on fixed signal bases require a predefined decomposition, while the diagnostic va...

Xin-Ke Ji, Rong-Hui Hu, Gao-Fei Pan et al. · 0 citations
Open access Oct 2026

Smart fault detection in a nanosatellite electrical power system

This simulation-based proof of concept evaluates a unified residual framework for faults affecting the photovoltaic (PV) array, maximum-power-point-tracking (MPPT) converter, regulator converter, and battery-to-ground interface of a nanosatellite electrical power system (EPS). The MATLAB R2021a implementation preserves...

A. Rezaee, Niloofar Nobahari, Ayub Taheri · 0 citations
Open access Oct 2026

Multi-Scenario Validation of Voltage Stability Indices and Machine- Learning-Based Weak Line Detection on the IEEE 14-Bus System

This paper audits twelve line VSIs on the IEEE 14bus system using continuation power flow (CPF) over 30 scenarios, finding the most reliable index, NVSI, is the most reliable and supplies a severity label, while a consensus vote across all twelve indices supplies a critical-line label.

R. Venkatesh, H. Chappa, Vempadapu Divya et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.