- By Joe Whitwell
- Technology Reporter
image source, Asif Rehan
Asif Rehan was one of the millions of Texans affected by power outages in 2021.
Amid rising demand for electricity, artificial intelligence (AI) is now being used to help prevent power outages.
“I would wake up in the middle of the night very, very cold,” recalls Asif Rehan. “I took out my military sleeping bag, and slept in it overnight for warmth.
“In the morning I found out that the electricity was definitely not on.”
Mr. Rehan describes the scene in February 2021 when he was stationed in San Antonio, Texas while serving in the US Air Force.
The winter storm Uri wreaked havoc in the state this month. As temperatures plunged to -19C, Texas scrambled to keep warm, sending electricity demand skyrocketing.
At the same time, Texas’ power grid began to unravel. Wind turbines froze, solar panels covered in snow, and a nuclear reactor had to be taken offline as a precaution.
More than 4.5 million homes and businesses were without power for hours, then days, because there wasn’t enough power to go around.
“Without electricity, the heating system didn’t work at all. And you couldn’t use an electric stove or a microwave to cook,” Mr Rehan recalls.
It took more than two weeks for the Texan power grid to finally return to normal.
image source, Getty Images
In February 2021, Texan power firms were scrambling to repair facilities and lines damaged by extreme cold weather.
The storm exposed the fragility of the systems we take for granted to provide round-the-clock electricity.
And while not all countries experience winters as severe as those in North America, worldwide demand for electricity continues to rise. From charging electric cars, to air conditioning more and more homes, we are using more and more power in our daily lives.
It comes at a time when countries are increasingly moving towards renewable energy sources, which are more variable in the amount of energy they produce. If the wind doesn’t blow, and the sun doesn’t shine, the power output is reduced.
All this led UK Energy Secretary Claire Coutinho to warn last month that the country could face blackouts in the future without new gas-fired power stations as “backup”.
Another way to make the energy system more flexible is to add large batteries to the grid.
The idea is that the batteries can charge when power is spare, and then release power later when power is in high demand.
This is an approach taken in Texas.
“We’ve added more than five gigawatts of battery storage capacity in Texas in the three years since the hurricane, which is really an incredible pace,” says Dr. Michael Weber, professor of energy resources at the University of Texas at Austin. That’s about as much energy as “four large nuclear power plants,” he says.
image source, Getty Images
Power firms in Texas and other US states are building energy storage facilities filled with rows and rows of batteries.
However, for such batteries to be truly useful, they need to know the best time to charge, and the best time to discharge. This means making complex predictions about how much electricity will be needed in the future.
“The main thing that makes the biggest difference is weather and power demand,” says Gavin McCormick, founder of tech startup WattTime.
His Oakland, California-based company makes AI software that predicts electricity supply and demand in a given area or region. This information can then tell the batteries when to charge and discharge.
The same information can be used in homes to help people use mains electricity more efficiently.
“So if you’ve got an electric vehicle that you need to get ready in eight hours, but it only takes two or three hours to charge, what it can do is run it for five minutes throughout the night. “Can find where there is surplus energy, or perhaps clean energy,” says Mr McCormick.
“It will charge a little faster at all the best times and still be ready by morning.”
AI can make these predictions by analyzing weather patterns, vacation dates, work schedules, and even when football is being played. “Everybody gets up and makes a cup of tea at half-time,” says Mr McCormick.
Another company using AI to forecast electricity demand is Danish firm ElectricityMaps. It focuses its AI on forecasting weather patterns such as cloud cover, wind strength, temperature and rainfall.
This information is used to better understand how much electricity will be produced from wind turbines or solar panels.
“If you can accurately predict in advance how much air is going into your system, you can plan ahead.” says company founder Oliver Corradi.
“One example is Google, where we’re giving them a forecast of how clean the grid is going to be in the next few hours. They can use that to change the time they use electricity in their data centers. have been.”
AI is now also being used to protect the physical infrastructure that delivers electricity to our homes.
One company, Buzz Solutions, uses AI to scan through images of power lines, pylons and substations, identifying signs of damage such as broken parts or rust.
The system also indicates when trees and other vegetation are growing too close to power lines.
Not only can this prevent power outages from damaged lines, but it can also reduce the risk of wildfires, which can occur when power lines come into contact with trees, as in recent years in California. I was the wind.
The tech can also spot and automatically report another major cause of power outages — wildlife — to power firm staff.
“Many times surprisingly, animals like squirrels and rats enter the substation, and they get electrocuted,” says Wakhayat Chaudhry, co-founder of Buzz Solutions.
“Their electric current sometimes causes a big explosion at the substation. Our AI that is deployed at the substations, one of the things they are detecting is animal interference, including raccoons and squirrels. Included.”