PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

A faster problem-solving tool that guarantees feasibility

The FSNet system, developed at MIT, could help power grid operators rapidly find feasible solutions for optimizing the flow of electricity

2025-11-03
(Press-News.org) Cambridge, MA – Managing a power grid is like trying to solve an enormous puzzle.

Grid operators must ensure the proper amount of power is flowing to the right areas at the exact time when it is needed, and they must do this in a way that minimizes costs without overloading physical infrastructure. Even more, they must solve this complicated problem repeatedly, as rapidly as possible, to meet constantly changing demand.

To help crack this consistent conundrum, MIT researchers developed a problem-solving tool that finds the optimal solution much faster than traditional approaches while ensuring the solution doesn’t violate any of the system’s constraints. In a power grid, constraints could be things like generator and line capacity.

This new tool incorporates a feasibility-seeking step into a powerful machine-learning model trained to solve the problem. The feasibility-seeking step uses the model’s prediction as a starting point, iteratively refining the solution until it finds the best achievable answer.

The MIT system can unravel complex problems several times faster than traditional solvers, while providing strong guarantees of success. For some extremely complex problems, it could find better solutions than tried-and-true tools. The technique also outperformed pure machine learning approaches, which are fast but can’t always find feasible solutions.

In addition to helping schedule power production in an electric grid, this new tool could be applied to many types of complicated problems, such as designing new products, managing investment portfolios, or planning production to meet consumer demand.

“Solving these especially thorny problems well requires us to combine tools from machine learning, optimization, and electrical engineering to develop methods that hit the right tradeoffs in terms of providing value to the domain, while also meeting its requirements. You have to look at the needs of the application and design methods in a way that actually fulfills those needs,” says Priya Donti, the Silverman Family Career Development Professor in the Department of Electrical Engineering and Computer Science (EECS) and a principal investigator at the Laboratory for Information and Decision Systems (LIDS).

Donti, senior author of an open-access paper on this new tool, called FSNet, is joined by lead author Hoang Nguyen, an EECS graduate student. The paper will be presented at the Conference on Neural Information Processing Systems.

Combining approaches

Ensuring optimal power flow in an electric grid is an extremely hard problem that is becoming more difficult for operators to solve quickly.

“As we try to integrate more renewables into the grid, operators must deal with the fact that the amount of power generation is going to vary moment to moment. At the same time, there are many more distributed devices to coordinate,” Donti explains.

Grid operators often rely on traditional solvers, which provide mathematical guarantees that the optimal solution doesn’t violate any problem constraints. But these tools can take hours or even days to arrive at that solution if the problem is especially convoluted.

On the other hand, deep-learning models can solve even very hard problems in a fraction of the time, but the solution might ignore some important constraints. For a power grid operator, this could result in issues like unsafe voltage levels or even grid outages.

“Machine-learning models struggle to satisfy all the constraints due to the many errors that occur during the training process,” Nguyen explains.

For FSNet, the researchers combined the best of both approaches into a two-step problem-solving framework.

Focusing on feasibility

In the first step, a neural network predicts a solution to the optimization problem. Very loosely inspired by neurons in the human brain, neural networks are deep learning models that excel at recognizing patterns in data.

Next, a traditional solver that has been incorporated into FSNet performs a feasibility-seeking step. This optimization algorithm iteratively refines the initial prediction while ensuring the solution does not violate any constraints.

Because the feasibility-seeking step is based on a mathematical model of the problem, it can guarantee the solution is deployable.

“This step is very important. In FSNet, we can have the rigorous guarantees that we need in practice,” Hoang says.

The researchers designed FSNet to address both main types of constraints (equality and inequality) at the same time. This makes it easier to use than other approaches that may require customizing the neural network or solving for each type of constraint separately.

“Here, you can just plug and play with different optimization solvers,” Donti says.

By thinking differently about how the neural network solves complex optimization problems, the researchers were able to unlock a new technique that works better, she adds.

They compared FSNet to traditional solvers and pure machine-learning approaches on a range of challenging problems, including power grid optimization. Their system cut solving times by orders of magnitude compared to the baseline approaches, while respecting all problem constraints.

FSNet also found better solutions to some of the trickiest problems.

“While this was surprising to us, it does make sense. Our neural network can figure out by itself some additional structure in the data that the original optimization solver was not designed to exploit,” Donti explains.

In the future, the researchers want to make FSNet less memory-intensive, incorporate more efficient optimization algorithms, and scale it up to tackle more realistic problems.

END


ELSE PRESS RELEASES FROM THIS DATE:

Smartphones can monitor patients with neuromuscular diseases

2025-11-03
Because researchers have made such striking progress in developing drugs to treat neuromuscular diseases, Scott Delp, PhD, was surprised to learn that scientists conducting clinical trials were still relying on a decidedly low-tech tool to track whether those treatments were working: a stopwatch. In a study published in the New England Journal of Medicine, Delp, a professor of bioengineering, and his collaborators showed that a smartphone could do the job as well or better. With two smartphone cameras and a free app, they ...

Biomaterial vaccines to make implanted orthopedic devices safer

2025-11-03
By Benjamin Boettner (BOSTON) — Patients with implanted medical devices like orthopedic joint replacements, pacemakers, and artificial heart valves run a small but significant risk that these devices get infected with bacterial pathogens. This starts them on a burdensome path requiring “redo” (revision) surgeries, prolonged antibiotic treatments, or in severe cases amputation. If the infections spread in patients’ bodies, they can even become fatal. “In the U.S. alone, about ...

Semaglutide, tirzepatide, and dulaglutide have similar gastrointestinal safety profiles in clinical settings

2025-11-03
Embargoed for release until 5:00 p.m. ET on Monday 3 November 2025    Follow @Annalsofim on X, Facebook, Instagram, Bluesky, and Linkedin              Below please find summaries of new articles that will be published in the next issue of Annals of Internal Medicine. The summaries are not intended to substitute for the full articles as a source of information. This information is under strict embargo and by taking it into possession, media representatives are committing to the terms of the embargo not only on their own behalf, but also on behalf of the organization they represent.    ----------------------------     1. ...

Neural implant smaller than salt grain wirelessly tracks brain

2025-11-03
ITHACA, N.Y. – Cornell University researchers and collaborators have developed a neural implant so small that it can rest on a grain of salt, yet it can wirelessly transmit brain activity data in a living animal for more than a year. The breakthrough, detailed Nov. 3 in Nature Electronics, demonstrates that microelectronic systems can function at an unprecedentedly small scale, opening new possibilities for neural monitoring, bio-integrated sensing and other applications. Development of the device, called a microscale optoelectronic tetherless electrode, or MOTE, was co-led ...

Large brains require warm bodies and big offspring

2025-11-03
Vertebrates have extremely different brain sizes: even with the same body size, brain size can vary a hundredfold. As a rule, mammals and birds have the largest brains in relation to their body size, followed by sharks and reptiles. Amphibians and most fish, on the other hand, have the smallest brains of all vertebrates. Why is this the case? In some animal groups, species that live in groups have larger brains than solitary species. They have to cope with rapidly changing social situations and therefore need ...

Team’s biosensor technology may lead to breath test for lung cancer

2025-11-03
University of Texas at Dallas researchers have developed biosensor technology that when combined with artificial intelligence (AI) shows promise for detecting lung cancer through breath analysis. The electrochemical biosensor identifies eight volatile organic compounds (VOCs) that are potential biomarkers for thoracic cancers, which include lung and esophageal cancers. AI then analyzes the biochemical characteristics of the compounds to determine whether they are a match to those linked to various thoracic cancers. “We built a screening tool that could allow physicians to catch the disease ...

Remote patient monitoring boosts primary care revenue and care capacity

2025-11-03
Remote physiologic monitoring (RPM)—digital tools that track patients’ health data between visits—shows promise for improving chronic disease management and reshaping primary care delivery, according to a new study at Columbia University Mailman School of Public Health. While prior studies have examined how RPM affects patients who use the technology, this is the first study to quantify the impact of RPM on practices, including its effects on practice revenue, care delivery, and ...

Protein plays unexpected dual role in protecting brain from oxidative stress damage

2025-11-03
New research from Johns Hopkins Medicine shows that the enzyme biliverdin reductase A (BVRA) plays a direct protective role against oxidative stress in neurons, independent of its role producing the yellow pigment bilirubin. In this study of genetically engineered mice, the scientists say BVRA protected brain cells from oxidative stress, an imbalance between oxidants and antioxidants that protect cells, by modulating another key protein, NRF2, which regulates the levels of protective proteins and antioxidants in cells. Oxidative stress is a hallmark of neurodegenerative diseases, including Alzheimer’s disease.   A report describing the research, funded by the ...

Fermentation waste used to make natural fabric

2025-11-03
UNIVERSITY PARK, Pa. — A fermentation byproduct might help to solve two major global challenges: world hunger and the environmental impact of fast fashion. The leftover yeast from brewing beer, wine or even to make some pharmaceuticals can be repurposed to produce high-performance fibers stronger than natural fibers with significantly less environmental impact, according to a new study led by researchers at Penn State and published today (Nov 3) in the Proceedings of the National Academy of Sciences.  The yeast biomass — ...

When speaking out feels risky

2025-11-03
In an era when social media blurs the line between public and private speech, how do people decide whether to speak their minds or stay silent? A new study from researchers at Arizona State University and the University of Michigan, published in the Proceedings of the National Academy of Sciences, or PNAS, offers a groundbreaking look at the strategic trade-offs individuals make when facing the threat of punishment for dissent. The work, co-authored by Professor Stephanie Forrest and Assistant Professor Joshua J. Daymude in the School of Computing and Augmented Intelligence, part of the ...

LAST 30 PRESS RELEASES:

Aortic hemiarch reconstruction safely matches complex aortic arch reconstruction for acute dissection in older adults

Destination Earth digital twin to improve AI climate and weather predictions

Late-breaking study finds comparable long-term survival between two leading multi-arterial CABG strategies

Lymph node examination should be expanded to accurately assess cancer spread in patients with lung cancer

Study examines prediction of surgical risk in growing population of adults with congenital heart disease

Novel radiation therapy QA method: Monte Carlo simulation meets deep learning for fast, accurate epid transmission dose generation

A 100-fold leap into the unknown: a new search for muonium conversion into antimuonium

A new approach to chiral α-amino acid synthesis - photo-driven nitrogen heterocyclic carbene catalyzed highly enantioselective radical α-amino esterification

Physics-defying discovery sheds new light on how cells move

Institute for Data Science in Oncology announces new focus-area lead for advancing data science to reduce public cancer burden

Mapping the urban breath

Waste neem seeds become high-performance heat batteries for clean energy storage

Scientists map the “physical genome” of biochar to guide next generation carbon materials

Mobile ‘endoscopy on wheels’ brings lifesaving GI care to rural South Africa

Taming tumor chaos: Brown University Health researchers uncover key to improving glioblastoma treatment

Researchers enable microorganisms to build molecules with light

Laws to keep guns away from distressed individuals reduce suicides

Study shows how local business benefits from city services

RNA therapy may be a solution for infant hydrocephalus

Global Virus Network statement on Nipah virus outbreak

A new molecular atlas of tau enables precision diagnostics and drug targeting across neurodegenerative diseases

Trends in US live births by race and ethnicity, 2016-2024

Sex and all-cause mortality in the US, 1999 to 2019

Nasal vaccine combats bird flu infection in rodents

Sepsis study IDs simple ways to save lives in Africa

“Go Red. Shop with Heart.” to save women’s lives and support heart health this February

Korea University College of Medicine successfully concludes the 2025 Lee Jong-Wook Fellowship on Infectious Disease Specialists Program

Girls are happiest at school – for good reasons

Researchers from the University of Maryland School of Medicine discover genetic ancestry is a critical component of assessing head and neck cancerous tumors

Can desert sand be used to build houses and roads?

[Press-News.org] A faster problem-solving tool that guarantees feasibility
The FSNet system, developed at MIT, could help power grid operators rapidly find feasible solutions for optimizing the flow of electricity