Scalable monitoring and kernel learning for energy grids

Vassilis Kekatos
Department of Electrical and Computer Engineering
University of Minnesota

12:00pm-1:00pm, Thursday, 13 March 2014, ITE 325b, UMBC

The smart grid vision urges for enhanced situational awareness, sustainability, and economics over our energy systems. While meters are being installed throughout the grid, algorithms that can effectively process this big data deluge are now demanded. Aligned to that end, this talk focuses first on scalable grid monitoring. Albeit control centers monitor their local grids independently, deregulation and renewables call for power system state estimation (PSSE) at the interconnection level. To address the complexity and communication challenges involved, a decentralized PSSE framework based on the alternating direction method of multipliers has been developed. Beyond conventional least-squares, our framework can identify outliers and circuit breaker statuses as verified on IEEE grids having thousands of nodes. Electricity market inference is the second theme of this talk. We will first demonstrate how grid topologies can be revealed using only publicly available real-time energy prices. This becomes feasible after recognizing that the price matrix can be factorized as the product of the grid Laplacian times a low-rank and sparse matrix. Leveraging the link between energy markets and the underlying physical grids, we will then cast day-ahead price forecasting as a kernel learning task. Through a novel nuclear norm-based regularization, kernels across pricing nodes and hours are systematically selected. Numerical tests using real data from the Midwest ISO market corroborate the interpretative merits of our schemes.

Dr. Vassilis Kekatos is currently a postdoctoral associate with the ECE Dept. of the University of Minnesota, Minneapolis. He obtained his Ph.D. in Computer Engineering and Science from the University of Patras, Greece, in 2007. In 2009, he received a Marie Curie fellowship. During the summer of 2012, he worked as a consultant for Windlogics Inc. His current interests lie in the areas of signal processing, optimization, and statistical learning towards modernizing our energy systems.

Host: Tulay Adali

Scalable monitoring and kernel learning for energy grids

Vassilis Kekatos
Department of Electrical and Computer Engineering
University of Minnesota

12:00pm-1:00pm, Thursday, 13 March 2014, ITE 325b, UMBC

The smart grid vision urges for enhanced situational awareness, sustainability, and economics over our energy systems. While meters are being installed throughout the grid, algorithms that can effectively process this big data deluge are now demanded. Aligned to that end, this talk focuses first on scalable grid monitoring. Albeit control centers monitor their local grids independently, deregulation and renewables call for power system state estimation (PSSE) at the interconnection level. To address the complexity and communication challenges involved, a decentralized PSSE framework based on the alternating direction method of multipliers has been developed. Beyond conventional least-squares, our framework can identify outliers and circuit breaker statuses as verified on IEEE grids having thousands of nodes. Electricity market inference is the second theme of this talk. We will first demonstrate how grid topologies can be revealed using only publicly available real-time energy prices. This becomes feasible after recognizing that the price matrix can be factorized as the product of the grid Laplacian times a low-rank and sparse matrix. Leveraging the link between energy markets and the underlying physical grids, we will then cast day-ahead price forecasting as a kernel learning task. Through a novel nuclear norm-based regularization, kernels across pricing nodes and hours are systematically selected. Numerical tests using real data from the Midwest ISO market corroborate the interpretative merits of our schemes.

Dr. Vassilis Kekatos is currently a postdoctoral associate with the ECE Dept. of the University of Minnesota, Minneapolis. He obtained his Ph.D. in Computer Engineering and Science from the University of Patras, Greece, in 2007. In 2009, he received a Marie Curie fellowship. During the summer of 2012, he worked as a consultant for Windlogics Inc. His current interests lie in the areas of signal processing, optimization, and statistical learning towards modernizing our energy systems.

Host: Tulay Adali

CSEE professor Marie desJardins was interviewed for a story, Education Key Theme for International Women’s Day, by the Voice of America on International Women’s Day (March 8).

“If you look at the statistics, well over half of all STEM jobs in the next 10 to 15 years are in computing … yet when people talk about STEM, they tend to think about biology, physics,” said University of Maryland Baltimore County Professor Marie Desjardins who teaches computer science and engineering. “Those are great areas, but those are not where the big job growth is going to be.”

DesJardins also says exposing kids at an early age is key to getting them interested in STEM.

“Let your girls try things that are not typically girly,” she said. “Make sure your kids are getting that from an early age so they think of themselves as creators of technology and new ideas not just following the rules.”

DesJardins says she emphasizes that computer science is really about helping make the world a better place.

Here is the video that accompanied the VIA story.

CSEE professor Marie desJardins was interviewed for a story, Education Key Theme for International Women’s Day, by the Voice of America on International Women’s Day (March 8).

“If you look at the statistics, well over half of all STEM jobs in the next 10 to 15 years are in computing … yet when people talk about STEM, they tend to think about biology, physics,” said University of Maryland Baltimore County Professor Marie Desjardins who teaches computer science and engineering. “Those are great areas, but those are not where the big job growth is going to be.”

DesJardins also says exposing kids at an early age is key to getting them interested in STEM.

“Let your girls try things that are not typically girly,” she said. “Make sure your kids are getting that from an early age so they think of themselves as creators of technology and new ideas not just following the rules.”

DesJardins says she emphasizes that computer science is really about helping make the world a better place.

Here is the video that accompanied the VIA story.

Check out UMBC Honors College Faculty Fellow Dr. Susan Hoban, and Honors College students Kabish Shah and Allie O'Malley, featured on UMBC BreakingGround for their work conducting STEM professional development for K-12 teachers and informal educators and training future engineers in Howard and Anne Arundel County.  Together with UMBC’s “NASA’s BEST” team, (BEST stands for “Beginning Engineering, Science, and Technology,”) they helped middle schoolers design and construct small robots to serve as “seeing-eye robots” for NASA’s Curiosity rover on Mars.  Read more...

More than 80,000 new voters in Washington, D.C. have registered since 2010, and rapid changes in the city’s demographics are being studied as experts analyze the upcoming Democratic primary in the race for D.C. mayor.

George Derek Musgrove ’97, history, assistant professor of history, was interviewed for a front page story published in The Washington Post on March 9. The article, titled “D.C.’s complexion is changing. Will the next mayor reflect that?“, examines how the upcoming mayoral election could reshape power and politics in the nation’s capital.

“The identity of the city since the ’60s has been ‘Chocolate City,’ ” Musgrove said. “The last thing keeping that identity intact is the mayoralty.” Musgrove, who lives in Washington and is currently writing a book on race and politics in the District, provided insight and historical context on changing political attitudes among residents in the nation’s capital.

“The passing of the civil rights-home rule generation brought us the children of that generation, including [former council members] Kwame Brown, Michael Brown and Tommy Thomas,” Musgrove said, and those sons of prominent civil rights-era political figures in the city, now disgraced former council members, “were miserable — and not just because they were caught stealing, but because they never had a vision for the city.”

In the article, Musgrove also pointed to a younger generation of voters and council members who are focusing more on economic diversity than racial identity. Young voters, too, “have very different notions of politics and race than the older generations did,” Musgrove said. “Young black professionals are willing to give Tommy Wells a fair shake.”

You can read the full article in The Washington Post here.