evidoria

← Back to browse

Good practice Imported

Sandia and DOE's AI-Based Protective Relay — Isolating Wildfire-Igniting Grid Faults 100 Times Faster (An Early-Stage Case)

United States of America · Albuquerque · See the United States of America profile

Top 75% 47/100 · Ask Evidence Copilot about this practice

Sandia National Laboratories and the U.S. Department of Energy are testing an AI-based protective relay that can isolate electrical faults capable of igniting wildfires roughly 100 times faster than conventional equipment, with field trials still in the planning stage.

Sandia and DOE's AI-Based Protective Relay — Isolating Wildfire-Igniting Grid Faults 100 Times Faster (An Early-Stage Case)

Details

Promoter
U.S. Department of Energy (CESER) & Sandia National Laboratories
Period
2023-2025 (ongoing pilot)
Keywords
energy, critical infrastructure, wildfire resilience, electric grid

Description

Wildfires increasingly start when faults in ageing electrical equipment — a downed line, a failing connector — arc and throw sparks into dry vegetation. The U.S. Department of Energy's Office of Cybersecurity, Energy Security, and Emergency Response (CESER) and Sandia National Laboratories are developing an AI-based protective relay designed to detect and isolate such faults before they can ignite.
Under Sandia's Wildfire Electric Grid Resilience programme, the 'Instant Arc Detection' component analyses high-speed sensor data and, according to DOE, can locate and isolate a fault approximately 100 times faster than conventional protective equipment, with detection achieved in under four milliseconds in prototype testing on a microgrid. The wider programme also includes PyroKit, a wildfire risk-mapping and Public Safety Power Shutoff planning tool now in customer discovery with utilities; SMOKEWISE, which models how wildfire smoke reduces solar generation for 30-year grid planning; and the publicly hosted Grid Event Signature Library of anonymised voltage and current data, intended to let any utility or researcher train their own fire-detection models.
Sandia names Public Service Company of New Mexico (PNM) among its utility partners, and as of the programme's August 2025 update, 'planning is currently underway to test the AI-based protective relaying solution on utility partners' electricity distribution systems' — meaning the headline performance figures come from laboratory and prototype testing, not a completed field deployment.
This is an early-stage federal research programme rather than a proven operational system, and its real-world fault-detection accuracy under actual grid conditions remains to be demonstrated; the evidence here should be read as promising bench results, not field-verified impact.

Read the full analysis: https://www.energy.gov/ceser/articles/fortifying-americas-electric-grid-against-wildfires-ai

Implementation

Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful