Multi-Step Controlled Islanding of Transmission Power Systems Using Constrained Spectral Clustering and Deep Learning Assistance
Bibliographic record
Abstract
This paper presents a multi-step controlled islanding (CI) approach for transmission power systems, utilizing spectral clustering techniques enhanced by deep learning assistance.The methodology aims to proactively divide the power grid into stable islands in response to severe faults, thereby preventing widespread outages.The approach commences with monitoring the power system based on voltage and frequency data, adhering to North American Electric Reliability Corporation (NERC) standards to detect critical system instability.Upon detecting a severe system state, coherency analysis is performed to identify coherent generator groups, which then is used in a constrained spectral clustering (CSC) algorithm to generate initial islanding solutions.To expand further potential solutions, a boundary space expansion (BSE) technique is applied.For each generated split option, relevant islanding indicators, including rate of change of frequency (ROCOF), normalized directed power imbalance (NDPI), inter-cluster voltage angle indicator (ICVAI), and root mean square error (RMSE) indicators, are calculated.A deep learning model, trained on historical simulations and the relationship between these indicators and an overall system stability score, is then employed to predict the optimal cut set, facilitating informed decision-making by system operators.The proposed approach has been validated through RMS simulations on the IEEE 9-Bus and IEEE 39-Bus systems, demonstrating its capability to accurately detect system instability, identify coherent generator groups, and effectively rank potential islanding solutions.The generic nature of the trained deep learning model suggests its potential applicability to diverse power system models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".