Skip to content
Open access

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

Oct 2026 · International Journal of Research Publication and Reviews · 0 citations

TL;DR

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.

Abstract

Voltage stability indices (VSIs) are widely used to flag the transmission line most likely to trigger voltage collapse, yet published indices are usually validated at a handful of loading snapshots along a single trajectory. This paper audits twelve line VSIs on the IEEE 14bus system using continuation power flow (CPF) over 30 scenarios (a base case, 19 successful single-line outages and 10 randomized loading directions), each traced to its collapse point and yielding 31,660 line-step samples. Indices are scored on saturation, trend correlation with the loading factor, and single-line bias. We show analytically, and verify on 30,693 in-service samples, that three pairs of published formulas (BVSI/Lp, Lij/Lmn and VQILine/FVSI) are identical, and that the R-multiplied pair BVSI/Lp is structurally blind to the five zero-resistance transformer branches, including the heavily loaded branch 5–6. The Novel Voltage Stability Index (NVSI) is the most reliable index (trend correlation 0.99, 0.4% saturation) and supplies a severity label, while a consensus vote across all twelve indices supplies a critical-line label. A Gradient Boosting classifier trained on 14 raw electrical measurements, with no index as input, reaches F1 = 0.824, recall 0.901 and ROCAUC 0.987 on scenario-disjoint test data, and a Random Forest regressor reproduces NVSI with R^{2} = 0.999. We also observe that the weakest line migrates with loading (5–6, 7–8, 2–3, then 5–6 again in the base case) and that residual errors arise almost entirely among the lines that trade the critical label. A Streamlit application serves both models.

Read PDF

Similar papers

Open access Sep 2026

Accelerated state estimation and voltage-magnitude monitoring in transmission networks using multi-output regressor chains

The results demonstrate the potential of the RF–RC model for accurate voltage-magnitude estimation in standard transmission systems, however, the proposed model is dependency-aware rather than topology-aware, and its scalability has been evaluated only on standard IEEE test systems.

Z. Almajali · 0 citations
Open access Oct 2026

Early Multi-Bus Transient-Voltage Stability Margin Assessment and Warning in Hybrid AC/DC Grids

The secure operation of a hybrid AC/DC grid requires not only a stable/unstable decision but also the voltage recovery margins of vulnerable buses. This paper presents a cascaded dual-criterion assessment and severity warning framework using a 0.75 p.u./1 s low-voltage-duration check and a 0.8 p.u./10 s recovery check....

Yong Wang, Yu-Xin Dai, Bing-Chen Li et al. · 0 citations
Open access Oct 2026

Fast Identification of Static Voltage Weak Nodes in Large-Scale Power Grids Using GATv2-JK

Rapid identification of static voltage weak buses in large-scale power grids is hindered by the computational burden of bus-by-bus continuation power flow (CPF) verification. This study proposes a GATv2–Jumping Knowledge (GATv2-JK) framework that screens operating conditions by system voltage stability margin and uses...

Zhen-Cheng Liang, Si-Ying Wang, Jun-Hui Liu et al. · 0 citations
Oct 2026

Simulation-based multihorizon LSTM-transformer prediction for live-line crossing platform stability

Live-line crossing platforms are exposed to coupled wind, operational, and impact loads while electrical clearance must be maintained. This paper presents a multi-scale LSTM-Transformer for forecasting the continuous overturning stability margin of an insulated telescopic-boom platform at 5s and 30s horizons. Because f...

Li Gong, Jiu-Qi Wang, Wen-Zhe Liu et al. · 0 citations
Preprint Nov 2026

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

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....

Pallav Kumar Bera, Samita Rani Pani, Ranjeeta Patel · 0 citations

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