The Key to Keeping the Lights On: Artificial Intelligence – The Wall Street Journal
After Hurricane Irma tore through South Florida in 2017 and cut power to more than six million people, it took 10 days for Florida Power & Light —the state’s largest electrical utility—to get the lights back on.
That was a big improvement from 2005, when recovery from Hurricane Wilma took 18 days. Investments in technology paid off. Now, FPL is looking to reduce recovery time further, by harnessing artificial intelligence, sensors and drones to better pinpoint outages and decide how best to fix them.
“After a storm, we want data,” says Michael Putt, the company’s smart grid and innovation director. “How quickly can I get imagery and information back?” These new tools help optimize decision-making in the first 12 to 24 hours after a storm, he says, helping get a read on damage in areas that otherwise could take days to access.
Innovation is sweeping across the world’s electricity grids, as utilities and power-transmission companies turn to tech to respond to outages and save money. They are also preparing for an increasingly complex electrical future as homeowners and businesses install solar panels and wind turbines and other renewables that produce power intermittently and may also send it back to the grid.
The old model of power plants that feed electrical lines on one-way trips to people’s homes is crumbling. Power companies increasingly need AI and software to predict when and where power will be available—and automation to make sure power gets to where it’s needed, when it’s needed, without overloading the system.
“We’re finding that there are needs for artificial intelligence and opportunities for artificial intelligence to improve the three pillars of the electric power grid system—operations, planning, and preparing for and reacting to disruptions,” says Mark Petri, the director of the electric power grid program at Argonne National Laboratory in Illinois.
In grid operations, he says, AI could take data from existing electrical equipment to make it run more efficiently. Argonne is also working with power-system operators to use AI fed with grid data to plan how much electricity to buy from power plants, thus saving money.
Share Your Thoughts
What improvements would you make to power grids to ensure service and minimize interruptions? Join the conversation below.
Even more AI will likely be necessary in the future as grids become harder to manage. When a larger percentage of people own electric cars, for example, evening charge cycles when people get home from work will cause a shift in usage that grids will have to adapt to. Keeping grid equipment from breaking down becomes an even more complex task when solar is feeding power back into the system.
“You’ve got to generate enough power to support ongoing demand, but then as renewables come on and offline it gets more complex, and it becomes much more critical to have software that can manage all these renewables,” says Pat Byrne, chief executive of General Electric’s digital business. The company sells analytics software to help manage such shifts, as well as something called “digital twins”—or simulations that help predict how equipment would behave in different conditions. With such tools, power system operators can dynamically control power-generating wind and gas-fired turbines, making sure no individual turbine runs too hot when electricity demand goes up, thus preventing wear and tear.
Batteries, which can store energy from wind and solar, are another area where AI could play a role in the power grids of the future. One company, Stem Inc. of Millbrae, Calif., helps corporations in the U.S. source battery systems, and then uses software called Athena that learns companies’ consumption patterns and autonomously decides when to use battery power to avoid consumption when prices are the highest—in the middle of a hot day, for example.
As markets for electricity become more open, such software could make money for battery owners through a form of arbitrage, charging up when electricity is cheap and disbursing it to the grid when it’s more expensive.
Stem has more than 1,000 battery systems deployed across the U.S.—just a fraction of what’s possible if battery prices fall, as predicted in a 2019 analysis by the National Renewable Energy Laboratory at the U.S. Department of Energy.
Of course, building a better, more reliable grid is a challenge for utilities, which have historically been slow to adopt new technologies or hire data scientists and coders.
FPL is attempting to show technological investments can pay dividends, for example by installing analytics tools that take in historical data and use it to narrow down the sources of outages to smaller stretches of lines where problems are most likely, saving time and money.
Florida Power & Light uses artificial intelligence with its fleet of drones. The equipment pictured here was purposely disconnected to help the software learn to recognize when something is not working.
So-called smart switches take outage response a step further, automatically shutting down whole neighborhoods when there’s a problem—lightning striking a telephone pole, for example—then rerouting power to isolate the outage and turning the lights back on where possible. FPL estimates that those auto-healing switches prevented 546,000 outages during Hurricane Irma, and is planning to install more of them in the future.
Today, FPL has more than 40 drones to handle outages and can scale up the number, using contractors, after large storms. The utility is also piloting tilt sensors and other technologies that detect whether each of its 1.2 million poles is damaged.
Solving the equation of keeping the grid reliable and efficient in the age of renewables and electric cars is likely to require even more tech, Mr. Putt says.
“That’s the kind of disruption the utilities are looking for,” he says. “Putting more renewables on the grid is the goal, but it’s more difficult to host those, and communications, sensors and data are going to help us accommodate more renewables in the future.”
More in The Future of Everything | Energy
Explore what’s next for energy and climate.
Fusion Startups Step in to Realize Decades-Old Clean Power Dream
Governments have spent billions of dollars studying the emissions-free energy source. Now, private ventures are building smaller, faster, cheaper reactors.
A Sci-fi Author’s Boldest Vision of Climate Change: Surviving It
Kim Stanley Robinson’s novels imagine environmental collapse in arresting precision—and humanity finding a way forward
Read the full report.
Write to Asa Fitch at email@example.com
Copyright ©2019 Dow Jones & Company, Inc. All Rights Reserved. 87990cbe856818d5eddac44c7b1cdeb8