Inside Pg&e’s ‘first Of Its Kind’ Wildfire Moni…

California utility Pacific Gas and Electric Company (PG&E) recently unveiled its new Continuous Monitoring Center (CMC), described as a “first-of-its-kind” centralized hub that takes the pulse of PG&E’s electric system to detect risks and prevent wildfires.

The CMC in San Ramon combines data and machine learning from tens of thousands of sensors installed across PG&E’s electric grid with data from its smart meter network, which consists of approximately 5.5 million meters that monitor grid conditions. PG&E argues that by analyzing this data continuously, its experts can identify emerging issues, often before customers are impacted, and dispatch crews to address those issues before they escalate into wildfires or outages.

The CMC analyzes signals across PG&E’s electric system and flags abnormalities that require attention.  Machine-learning models scan for patterns that indicate potential risks. PG&E argues the CMC’s capabilities are redefining how it identifies and addresses wildfire risk, moving from reactive response to proactive detection and prevention.

PG&E pointed to several wins stemming from its continuous monitoring capabilities last year, including the interception of 17 potential ignitions in high fire-risk areas; the avoidance of 12 million minutes of unplanned customer outages; the reduction of emergency outage response time by 2,620 hours; and savings of approximately $6 million in operational costs. Building on these results, PG&E established the CMC to bring these capabilities into a single, integrated operation.

“The threat of wildfire requires more than incremental improvement; it demands a different kind of vigilance,” said Mark Quinlan, PG&E’s Senior Vice President of Wildfire, Emergency, and Operations. “With the Continuous Monitoring Center, we’re adding another layer of protection, using predictive intelligence from millions of data points across our system, to spot problems forming before they become emergencies. The results are clear: faster detection, quicker action, a safer grid, and real cost savings for the customers we serve. We are also actively sharing what we’ve learned with utilities and industry peers around the world.”

PG&E also noted a specific example of a “good catch” caught by the CMC team. PG&E’s engineers caught an issue on the Brunswick 1106 circuit in Nevada County, where the machine learning model identified a possible wiring issue. After traveling to the location, an electric troubleshooter found melted insulation at the transformer caused by degraded connections from weather-related stress. Crews replaced the transformer and other associated equipment before an ignition could occur. Had an ignition resulted, it could have led to a 17-acre wildfire, potentially damaging two or three structures and causing up to $1.4 million in losses, the utility argued. Since 2025, PG&E has recorded 1,484 “good catches.”

The CMC analyzes data from multiple technologies deployed across PG&E’s systems, including:  

• Early fault detection sensors – Radiofrequency (RF) monitoring that identifies partial discharge, arcing, and insulation breakdown across 900 circuit miles in high fire-risk areas.
• GridScope devices – Pinpoint the location and nature of issues across 1,350+ circuit miles in high fire-risk areas.
• Downed conductor detection – Enable identification of the location and cause of disturbances across 1,350+ circuit miles, supporting quicker response and targeted repairs.
• SmartDetect – Uses SmartMeter data and machine learning to monitor grid performance, identify patterns and anomalies that may indicate emerging risks.
• Distribution fault anticipation sensors – Identify small system disturbances across 8,900+ circuit miles that help enable proactive maintenance to prevent outages or risks before they occur.
• Line sensors – Detect changes in electric current patterns that help crews locate issues and determine root causes across 19,000+ circuit miles.
• Grid data analytics & technology platform – Integrates incoming sensor and outage data across PG&E’s electric grid into a single system to help identify trends, prioritize preventative work, and inform decision-making.

A Multi-Layered Approach

The CMC is the latest addition to PG&E’s multiple layers of protection and wildfire mitigation, which include undergrounding, Enhanced Powerline Safety Settings (EPSS), Public Safety Power Shutoffs (PSPS), AI-enabled wildfire cameras, and more. PG&E’s 2026-2028 Wildfire Mitigation Plan (WMP) integrates tools and solutions, including inspecting assets with drones, using artificial intelligence in an effort to improve weather forecasts, and installing sensors that can detect vibrations, sounds, and light that could indicate potential anomalies on an electric circuit that could lead to an ignition. 

PG&E’s WMP outlines layers of protection intended to work together to reduce wildfire ignition risk and strengthen PG&E’s electric grid in Northern and Central California, where risk is most severe. These measures include strengthening 570 miles of overhead power lines and poles; burying nearly 1,100 more miles of power lines; using drones to get a bird’s-eye view of electric assets; using a network of weather stations and high-definition cameras with AI; trimming trees and more. 

In 2022, PG&E paid $55 million to avoid criminal prosecution for the 2021 Dixie Fire, which scorched more than 1 million acres. PG&E acknowledged that a tree leaning into one of its power lines may have started the blaze, one of the largest in state history.

In 2020, PG&E pleaded guilty to 84 counts of manslaughter for the Camp Fire, California’s all-time deadliest and most destructive wildfire. It started in November 2018 when part of a poorly maintained transmission line in Butte County’s Feather River Canyon failed during strong winds, sparking a fire that burned for two weeks, killing 85 people and causing an estimated $16.5 billion in damages. PG&E negotiated more than $25 billion in settlements during the 17-month bankruptcy that ed.