Aleksandar Stankovic
Santa Clara University, CA·Engineering
Engineers who run large systems such as interconnected power grids face a basic trade-off. Detailed models predict accurately but are hard to understand, while simple models are easy to interpret but less precise.
- Fields
Engineering
Mathematics & Statistics
Computer Science
- Topics
cyber-physical systems
energy systems
power grids
- Grants
- 1 known grant, through May 2027
What they work on
- Develop techniques combining manifold learning, which finds simple structure in complex data, with information-geometry model reduction to build physically interpretable models that still make quantitative predictions.
- Pair qualitatively correct but quantitatively inaccurate reduced physical models with learned data-driven transformations, mapping them onto measured data from cyber-physical systems.
- Apply these hybrid modeling tools to key operational challenges in interconnected energy networks and release them as open-source software.
More about the research
Machine learning can build accurate predictive models from data, but these act as black boxes and may not carry over to new situations. The project asks how to get both: models simple enough for humans making key decisions yet precise enough to make quantitative predictions.
Why it matters
Power grid operators and engineers managing critical infrastructure could gain models that are both interpretable and quantitatively accurate, aiding operational decisions in interconnected energy networks. The methods and open-source software are intended to apply to modeling other complex cyber-physical systems as well.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Kaijian Liu
Stevens Institute of Technology, NJ·Engineering·Early-career
Develop a learning framework that estimates the conditions of people and infrastructure, across space and time, from sparse and uncertain observations, as a basis for modeling disaster disruptions.
Qinghua Li
University of Arkansas, AR·Computer Science
Develop methods to assess the risk of security vulnerabilities in energy system operational technology and choose the most effective ways to mitigate them, including lowering the cost and risk of patching.
David Reeping
University of Cincinnati, OH·Education Research
Reach expert consensus on the fundamental concepts needed to master cyber-physical systems through a Delphi study, structured rounds of surveys of academic and industry experts.
The school
Santa Clara University: 8 labs on PI Pages, $8M a year on research, 24 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.