US utility Pacific Gas & Electric (PG&E) has unveiled a monitoring hub that helped prevent 17 wildfires and over a thousand outages.

The continuous monitoring centre in San Ramon, California, brings together people, data and machine learning from tens of thousands of sensors installed across PG&E’s electric grid, combined with data from its smart meter network consisting of approximately 5.5 million meters that are scanning grid conditions. By analysing these data continuously, trained experts can identify emerging problems often before customers are impacted and dispatch crews to take action before those issues escalate into wildfires or outages.

It analyses signals across PG&E’s electric system and flags abnormalities that require attention. Machine-learning models scan for patterns that indicate potential risks, allowing PG&E to move from reacting to incidents to preventing them altogether.

In 2025, the continuous monitoring capabilities delivered measurable results for customers and communities, including intercepting 17 potential ignitions in high fire-risk areas, avoiding 12 million minutes of unplanned customer outages, reducing emergency outage response time by 2620 hours, and saving approximately $6m in operational costs.

Building on these early results, PG&E established the continuous monitoring centre to bring these capabilities into a single, integrated operation, allowing for faster analysis, stronger coordination and more proactive risk detection to enhance safety and reliability.

“The threat of wildfire requires more than incremental improvement, it demands a different kind of vigilance,” said Mark Quinlan, PG&E senior vice president. “With the continuous monitoring centre, 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.”

As an example, engineers at the centre caught an issue, which they describe as a good catch, on the Brunswick 1106 circuit in Nevada County. The machine-learning model identified a possible wiring issue and, after traveling to the location, an electric troubleshooter found melted insulation at the transformer caused by degraded connections because of severe 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 $1.4m in losses. Since 2025, PG&E has recorded 1484 good catches.

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

• Early fault detection sensors: RF monitoring identifies partial discharge, arcing and insulation breakdown across 1500 circuit kilometres in high fire-risk areas, acting like a check engine light for the grid. 
• GridScope devices: These pinpoint the location and nature of issues across 2200 circuit kilometres in high fire-risk areas allowing for quick response and remediation.
• Downed conductor detection: This enables fast identification of the location and cause of disturbances across 2200 circuit kilometres, supporting quicker response and targeted repairs.
• SmartDetect: This uses smart-meter data and machine learning to monitor grid performance, identifying patterns and anomalies that may indicate emerging risks.
• Distribution fault anticipation sensors: The sensors identify small system disturbances across 15,000 circuit kilometres that enable proactive maintenance to prevent outages or risks before they occur.
• Line sensors: These detect changes in electric current patterns that help crews locate issues faster and determine root causes for more effective repairs across 30,000 circuit kilometres.
• Grid data analytics and technology: The platform integrates incoming sensor and outage data across PG&E’s electric grid into a single system to help identify trends, prioritise preventative work and inform faster decision-making.

Together, these capabilities, anchored by the continuous monitoring centre, are redefining how PG&E identifies and addresses wildfire risk before it becomes an emergency. PG&E (pge.com) is identifying and addressing hazards earlier, faster and more precisely. It marks a shift from reactive response to proactive detection and prevention, just as the next wildfire season (pge.com/wildfiresafetyprogress) begins.