Rapidity Prediction of Power Infrastructure Forced Outages: Data-Driven Approach for Resilience Planning
Bibliographic record
Abstract
Power infrastructure is essential for the operation of almost all other critical infrastructure systems, including water, transportation, and telecommunications. Recently, there has been an increase in forced power outage frequency and extent due to infrastructure aging, extreme weather events, and deliberate attacks. To combat forced power outage risks, researchers have been focusing on improving the resilience of different power infrastructure systems. A key aspect of infrastructure resilience is the rapidity, defined as the time required to return to normal operation levels following functionality disruptions. This study developed a machine learning–based framework to predict the rapidity of power infrastructure following forced outages. The framework includes classification models such as bagging, random forests, and artificial neural networks to accommodate the categorical nature of typical power infrastructure component outage features. The framework also includes a genetic algorithm for optimized selection of such features in order to facilitate the model’s best prediction performance. The utility of the developed framework was demonstrated using actual transmission line forced outages data. Within the demonstration application, rapidity was split into two classes indicating short and extended outages, and the random forest classification model had the best rapidity prediction performance. In addition, the influence of key features on outage classification was explored using partial dependence analysis. Finally, insights for resilience-guided asset management were presented. The developed framework enables infrastructure stakeholders to predict forced outage rapidity classes soon after the occurrence of the former—subsequently enabling rapid identification of appropriate resources needed to promptly restore infrastructure functionality and thus ensuring infrastructure resilience.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".