Leveraging Artificial Intelligence for Enhancing Power Grid Resilience to Extreme Weather Events: Applications and Challenges
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The increasing frequency and magnitude of weather-related extreme events in recent years have severely impacted power grids. Examples of these extreme events include wildfires, heat waves, hurricanes, tornadoes, storms, flooding, etc. Extreme weather disturbances have rendered this critical infrastructure susceptible to disruption, risking essential services from health care to transportation. An important objective for many power utilities is to improve resilience and avoid widespread outages when faced with extreme events. The resilience goal of utility companies is to minimize the duration and magnitude of power outages and enable the rapid recovery of service after an outage event. For this purpose, various preventive and restorative resilience actions are required that can focus on adaptation plans as well as restoration plans that utilities can adopt to restore power to customers in an optimized fashion. However, one of the significant challenges that utilities face is to effectively handle large amounts of data from different sectors and utilize the data in an effective and optimized fashion for making resilience decisions and actions. This article discusses the data management practices required by electric power utilities to improve grid resilience and elaborates the applications of artificial intelligence (AI) for the enhanced resilience of electric power grids. The data management and AI applications are discussed from the perspective of preventive and mitigative actions on different power grid sectors, like generation, transmission, and distribution. The article concludes by summarizing the gaps in grid resilience research and technologies.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it