Tech
3 Questions: How AI could optimize the power grid
Artificial intelligence has captured headlines recently for its rapidly growing energy demands, and particularly the surging electricity usage of data centers that enable the training and deployment of the latest generative AI models. But it’s not all bad news — some AI tools have the potential to reduce some forms of energy consumption and enable cleaner grids.
One of the most promising applications is using AI to optimize the power grid, which would improve efficiency, increase resilience to extreme weather, and enable the integration of more renewable energy. To learn more, MIT News spoke with Priya Donti, the Silverman Family Career Development Professor in the MIT Department of Electrical Engineering and Computer Science (EECS) and a principal investigator at the Laboratory for Information and Decision Systems (LIDS), whose work focuses on applying machine learning to optimize the power grid.
Q: Why does the power grid need to be optimized in the first place?
A: We need to maintain an exact balance between the amount of power that is put into the grid and the amount that comes out at every moment in time. But on the demand side, we have some uncertainty. Power companies don’t ask customers to pre-register the amount of energy they are going to use ahead of time, so some estimation and prediction must be done.
Then, on the supply side, there is typically some variation in costs and fuel availability that grid managers need to be responsive to. That has become an even bigger issue because of the integration of energy from time-varying renewable sources, like solar and wind, where uncertainty in the weather can have a major impact on how much power is available. Then, at the same time, depending on how power is flowing in the grid, there is some power lost through resistive heat on the power lines. So, as a grid operator, how do you make sure all that is working all the time? That is where optimization comes in.
Q: How can AI be most useful in power grid optimization?
A: One way AI can be helpful is to use a combination of historical and real-time data to make more precise predictions about how much renewable energy will be available at a certain time. This could lead to a cleaner power grid by allowing us to handle and better utilize these resources.
AI could also help tackle the complex optimization problems that power grid operators must solve to balance supply and demand in a way that also reduces costs. These optimization problems are used to determine which power generators should produce power, how much they should produce, and when they should produce it, as well as when batteries should be charged and discharged, and whether we can leverage flexibility in power loads. These optimization problems are so computationally expensive that operators use approximations so they can solve them in a feasible amount of time. But these approximations are often wrong, and when we integrate more renewable energy into the grid, they are thrown off even farther. AI can help by providing more accurate approximations in a faster manner, which can be deployed in real-time to help grid operators responsively and proactively manage the grid.
AI could also be useful in the planning of next-generation power grids. Planning for power grids requires one to use huge simulation models, so AI can play a big role in running those models more efficiently. The technology can also help with predictive maintenance by detecting where anomalous behavior on the grid is likely to happen, reducing inefficiencies that come from outages. More broadly, AI could also be applied to accelerate experimentation aimed at creating better batteries, which would allow the integration of more energy from renewable sources into the grid.
Q: How should we think about the pros and cons of AI, from an energy sector perspective?
A: One important thing to remember is that AI refers to a heterogeneous set of technologies. There are different types and sizes of models that are used, and different ways that models are used. If you are using a model that is trained on a smaller amount of data with a smaller number of parameters, that is going to consume much less energy than a large, general-purpose model.
In the context of the energy sector, there are a lot of places where, if you use these application-specific AI models for the applications they are intended for, the cost-benefit tradeoff works out in your favor. In these cases, the applications are enabling benefits from a sustainability perspective — like incorporating more renewables into the grid and supporting decarbonization strategies.
Overall, it’s important to think about whether the types of investments we are making into AI are actually matched with the benefits we want from AI. On a societal level, I think the answer to that question right now is “no.” There is a lot of development and expansion of a particular subset of AI technologies, and these are not the technologies that will have the biggest benefits across energy and climate applications. I’m not saying these technologies are useless, but they are incredibly resource-intensive, while also not being responsible for the lion’s share of the benefits that could be felt in the energy sector.
I’m excited to develop AI algorithms that respect the physical constraints of the power grid so that we can credibly deploy them. This is a hard problem to solve. If an LLM says something that is slightly incorrect, as humans, we can usually correct for that in our heads. But if you make the same magnitude of a mistake when you are optimizing a power grid, that can cause a large-scale blackout. We need to build models differently, but this also provides an opportunity to benefit from our knowledge of how the physics of the power grid works.
And more broadly, I think it’s critical that those of us in the technical community put our efforts toward fostering a more democratized system of AI development and deployment, and that it’s done in a way that is aligned with the needs of on-the-ground applications.
Tech
Thinking Machines Cofounder’s Office Relationship Preceded His Termination
Leaders at Mira Murati’s Thinking Machines Lab confronted the startup’s cofounder and former CTO, Barret Zoph, over an alleged relationship with another employee last summer, WIRED has learned.
That relationship was likely the alleged “misconduct” that has been mentioned in prior reporting, including by WIRED.
To protect the privacy of the individuals involved, WIRED is not naming the employee in question. The individual, who worked in a different department than Zoph and was in a leadership role, is no longer at the lab.
Murati approached Zoph to discuss the relationship, sources say. The cofounders’ working relationship broke down in the months following that conversation, according to multiple sources, and Zoph started speaking to competitors about other opportunities.
Before Zoph left the company, he was in conversation with leaders from Meta Superintelligence Labs, according to a source familiar with the matter. Zoph was ultimately hired by OpenAI. OpenAI’s CEO of applications, Fidji Simo, said the hiring had been in the works for weeks. Simo also noted that she did not share Thinking Machines’ concerns over Zoph’s ethics.
Zoph and OpenAI declined to comment for this story.
This week, a third Thinking Machines cofounder, Luke Metz, and at least three other researchers from Murati’s startup also departed for OpenAI. In October, the startup’s cofounder Andrew Tulloch left for Meta.
While tensions between Murati and Zoph came to a head in recent days, they do not entirely explain the broader exodus of Thinking Machines employees.
WIRED previously reported that there was misalignment within Thinking Machines about what the startup should build.
In November, Murati’s startup was reportedly looking to raise capital at a $50 billion valuation, up from its current valuation of $12 billion.
Thinking Machines Lab declined to comment for this story.
Tech
This Jackery Power Station Can Save You in an Emergency, and It’s on Sale for $199
Here in the Pacific Northwest, we’re heading into the cold and windy season, which generally means power outages. One of the best ways to stay prepared for those cold and dark days is a portable power station like the Jackery Explorer 300 Plus, which is currently marked down by $100 at Best Buy and by the same amount at B&H. It’s compact enough to tuck away in a cabinet for a rainy day, but still has enough juice to power small and medium sized devices.
I actually picked up one of these a few weeks ago ahead of a big windstorm, and although I fortunately didn’t have to use it, I did run some quick tests on it to make sure everything was in working order. Every device I connected to the Jackery started charging at its fastest rate instantly, and I plugged my router in as well, which happily ran off the outlet with no issue. While I didn’t get a chance to drain the battery, it has a 288-watt-hour capacity that’s excellent for many charges of smaller devices like phones and tablets, or hours of use keeping your small appliances awake.
It has a raft of ports for charging and powering your various devices. There’s a regular USB-A port with a 15W max for incidentals, plus two USB-C ports with a 100W max, one of which is also used as the input to charge the power station. There’s a traditional American 120V outlet too, with a 300W limit, in case the lower wattage USB ports don’t quite fit the bill for your most demanding equipment. There’s even a charger of the style you find in cars, in case you have accessories that need it.
If you’re worried the Explorer 300 Plus won’t have enough juice to get you through a long outage, or you’re a frequent road tripper, I also spotted several Jackery solar panels marked down at Best Buy. The smaller 40W solar panel is marked down to $79 from $130, and the larger 100W version is discounted down to $198 from $299. While this smaller model is great for individuals and occasional use, make sure to check out our other favorite portable power stations for bigger batteries.
Tech
Former USDS Leaders Launch Tech Reform Project to Fix What DOGE Broke
The past year has been traumatic for many of the volunteer tech warriors of what was once called the United States Digital Service (USDS). The team’s former coders, designers, and UX experts have watched in horror as Donald Trump rebranded the service as DOGE, effectively forced out its staff, and employed a strike force of young and reckless engineers to dismantle government agencies under the guise of eliminating fraud. But one aspect of the Trump initiative triggered envy in tech reformers: the Trump administration’s fearlessness in upending generations of cruft and inertia in government services. What if government leaders actually used that decisiveness and clout in service of the people instead of following the murky agendas of Donald Trump or DOGE maestro Elon Musk?
A small though influential team is proposing to answer that exact question, working on a solution they hope to deploy during the next Democratic administration. The initiative is called Tech Viaduct, and its goal is to create a complete plan to reboot how the US delivers services to citizens. The Viaduct cadre of experienced federal tech officials is in the process of cooking up specifics on how to remake the government, aiming to produce initial recommendations by the spring. By 2029, if a Democrat wins, it hopes to have its plan adopted by the White House.
Tech Viaduct’s advisory panel includes former Obama chief of staff and Biden’s secretary of Veterans Affairs Denis McDonough; Biden’s deputy CTO Alexander Macgillivray; Marina Nitze, former CTO of the VA; and Hillary Clinton campaign manager Robby Mook. But most attention-grabbing is its senior adviser and spiritual leader, Mikey Dickerson, the crusty former Google engineer who was the first leader of USDS. His hands-on ethic and unfiltered distaste for bureaucracy embodied the spirit of Obama’s tech surge. No one is more familiar with how government tech services fail American citizens than Dickerson. And no one is more disgusted with the various ways they have fallen short.
Dickerson himself unwittingly put the Viaduct project in motion last April. He was packing up the contents of his DC-area condo to move as far away as possible from the political scrum (to an abandoned sky observatory in a remote corner of Arizona) when McDonough suggested he meet with Mook. When the two got together, they bemoaned the DOGE initiative but agreed that the impulse to shred the dysfunctional system and start over was a good one. “The basic idea is that it’s too hard to get things done,” says Dickerson. “They’re not wrong about that.” He admits that Democrats had blown a big opportunity “For 10 years we’ve had tiny wins here and there but never terraformed the whole ecosystem,” Dickerson says. “What would that look like?”
Dickerson was surprised a few months later when Mook called him to say he found funding from Searchlight Institute, a liberal think tank devoted to novel policy initiatives, to get the idea off the ground. (A Searchlight spokesperson says that the think tank is budgeting $1 million for the project.) Dickerson, like Al Pacino in Godfather III, was pulled back in. Ironically, it was Trump’s reckless-abandon approach to government that convinced him that change was possible. “When I was there, we were severely outgunned, 200 people running around trying to improve websites,” he says. “Trump has knocked over all the beehives—the beltway bandits, the contractor industrial complex, the union industrial complex.”
Tech Viaduct has two aims. The first is to produce a master plan to remake government services—establishing an unbiased procurement process, creating a merit-based hiring process, and assuring oversight to make sure things don’t go awry. (Welcome back, inspector generals!) The idea is to design signature-ready executive orders and legislative drafts that will guide the recruiting strategy for a revitalized civil service. In the next few months, the group plans to devise and test a framework that could be executed immediately in 2029, without any momentum-killing consensus building. In Viaduct’s vision that consensus will be achieved before the election. “Thinking up bright ideas is going to be the easy part,“ Dickerson says. “As hard as we’re going to work in the next three to six months, we’re going to have to spend another two to three years, through a primary season and through an election, advocating as if we were a lobbying group.”
-
Tech4 days agoNew Proposed Legislation Would Let Self-Driving Cars Operate in New York State
-
Sports6 days agoClock is ticking for Frank at Spurs, with dwindling evidence he deserves extra time
-
Sports7 days ago
Commanders go young, promote David Blough to be offensive coordinator
-
Fashion6 days agoSouth India cotton yarn gains but market unease over US tariff fears
-
Fashion6 days agoChina’s central bank conducts $157-bn outright reverse repo operation
-
Entertainment3 days agoX (formerly Twitter) recovers after brief global outage affects thousands
-
Business7 days agoSoftBank reduces Ola Electric stake to 13.5% from 15.6% – The Times of India
-
Sports6 days agoUS figure skating power couple makes history with record breaking seventh national championship
