Utility Component Wildfire Risk Scoring for Shutoff Decisions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Utilities face a dilemma in wildfire-prone areas where disabling components to prevent outages that could cause wildfires disrupts service, while enabling these components increases fire risk, necessitating a granular and accurate risk assessment to balance service continuity and fire prevention.
Innovation Solution
A machine learning-based wildfire forecast tool that predicts catastrophic wildfire risk on a per-component basis by integrating outage risk, ignition probability, and wildfire impact simulations, providing a graphical dashboard for utility component shutoff decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If utility components are disabled to prevent wildfires, then wildfire risk is reduced, but service disruption increases
Solution Approach 1:
The system applies different risk assessments and operational decisions to different utility components based on their specific wildfire risk profiles. Instead of blanket disabling all components, the system evaluates each component's location, environmental conditions, and historical data to determine individual shutoff decisions, allowing low-risk components to remain operational while protecting high-risk areas.
Solution Approach 2:
The wildfire risk assessment is dynamic and updates in real-time based on changing environmental conditions such as weather, fuel moisture content, and wind patterns. This allows the system to adjust component operational status dynamically, maintaining service continuity when conditions are safe while quickly responding to deteriorating conditions that increase wildfire risk.
2Reliability
If existing forecasting methods are used, then general wildfire risk is identified, but granular decision-making precision is insufficient
Solution Approach 1:
The system segments the utility infrastructure into individual components (poles, transformers, lines) and assesses wildfire risk for each component separately. This granular segmentation enables precise risk measurement at the component level rather than providing only regional or general area assessments, allowing utilities to make targeted decisions about specific high-risk components.
Solution Approach 2:
The system replaces traditional mechanical or manual risk assessment methods with machine learning models that process multiple data sources (weather data, historical outage data, vegetation data, topography) to generate precise probabilistic risk scores. This substitution enables automated, high-precision risk quantification that is impossible with manual assessment methods.
Data Source
AI summary
A service inputs wind data and utility data corresponding to a utility component into a first machine learning model to determine an outage risk prediction representing a probability that the utility component will have an outage. The service determines a probability of ignition at a vicinity of the utility component, and determines a set of wildfire impact measurements by simulating a wildfire in the vicinity of the utility component. The service inputs the outage risk prediction, the probability of ignition, and the set of wildfire impact measurements into a second machine learning model, and receives as output from the second machine learning model, a catastrophic wildfire risk score corresponding to the utility component. The service outputs a graphical representation on a dashboard representing the catastrophic wildfire risk score.