On a plot of land on the eastern shore of San Francisco Bay, startup Gridware built a full-scale electrical grid, complete with 50-foot poles, 200-foot spans of wire, and 12.5 kilovolts of power flowing through it. Once it was finished, the company then set about destroying it. Over and over and over again.
“I’ve destroyed it thousands and thousands of times,” Gridware co-founder and CEO Tim Barat told us. “I throw trees on the lines, I cut live wires, I explode transformers.”
The goal of all of this mangling is to collect data on the kinds of things that might happen to power lines in the real world. Gridware has used it to inform the sensors the company now supplies to utilities. Its product, Gridscope, mounts onto electrical poles and listens for signs of threats or problems using machine learning.
“If you [test] enough, you start to recognize the patterns associated with how the equipment will behave,” Barat said. “And then what we discovered is—and we weren’t surprised by this—it matches what happens in the real world.”
Bolstering for potential damage has become increasingly important for utilities as the country’s aging grid infrastructure faces new threats from climate-related disasters like wildfires, as well as newfound stress from ongoing electrification efforts. Without AI to interpret patterns in a flood of data, monitoring the grid can also be tricky, according to Barat.
“They have an aging infrastructure, they have a diminishing labor force, they have pressures on rates,” he said. “They have increased frequency and severity of these weather events, and they have to totally change the way they operate, and yet they don’t have any tools to be able to do that.”
Boots on the ground
Barat has had firsthand experience with some of the disaster scenarios that can face electrical grids. A high school dropout at the age of 15, he was working as a lineman in the Australian state of Victoria during the 2009 Black Saturday wildfires, a set of devastating brushfires—at least some of which were caused by faulty power lines—that killed more than 170 people.
“This was a catastrophic event for Australia, where 50 fires were ignited by power lines in one day,” Barat said. “Since then, we’ve seen many of these similar events occur.”
A few years later, he moved to California, where he went back to school and eventually earned a master’s degree from UC Berkeley in electrical engineering and computer science. He later identified a gap in how utilities were able to monitor stresses and problems in the grid, and co-founded Gridware. It was accepted into the Y Combinator incubator in 2021.
Keep up with the innovative tech transforming business
Tech Brew keeps business leaders up-to-date on the latest innovations, automation advances, policy shifts, and more, so they can make informed decisions about tech.
Barat was also able to draw on his time as a lineman when it came to that on-the-ground destruction at the test grid in the UC Berkeley-owned Richmond Field Station. The team was able to get access to the university-owned land, which hosts a number of engineering and environmental experiments, through the startup’s membership in a UC-run incubator called the Citris Foundry, according to UC Berkeley’s Engineering Department website. But the company built the test grid there itself.
“We have, as an industry historically, looked very myopically at the grid and just tried to observe the current and voltage, and when you think about state estimation of the grid, it’s all electric,” Barat said. “But to me, the grid isn’t just the circuit board. It’s a physical thing—this is a large thing that we all walk past every day. It’s hit by extreme weather. It’s hit by animals. It’s hit by a multitude of different stresses, and the environment which it was designed to operate in has fundamentally changed and is continuing to change.”
Tuned in
The Gridscope devices work by measuring the vibrations of the power lines and monitoring for anomalies like trees falling on the lines, among other potential scenarios. The devices use “cellular, satellite, and device-to-device” communication to transmit this data on the health of grid assets to utilities, according to a news release. Built-in solar panels aim to ensure the devices will remain on through outages.
Gridware ran a pilot test with PG&E last year and has since expanded to other utility customers in 10 states. The company also raised a Series A funding round of $26.4 million this month, led by Sequoia Capital.
Barat hopes the company can eventually help power companies better understand the types of demands and stresses that the grid will face as they update their infrastructure for the future.
“We have this big, long set of standards that the grid is currently built to that, in my opinion, is outdated. But we can’t even attempt to update those standards because we now have to think what’s going to happen in five years, 10 years, 50 years—some of this equipment remains in service for 100 years,” Barat said. “How can we even pretend to know what’s going to happen in 100 years when we don’t know what’s happening today? Specifically, beyond just electrical, we don’t understand the physical profile and the stress and environment that each of these components experience…So that’s why Gridware exists.”