Yang Weng
Arizona State University Campus Immersion, AZ·Engineering·Early-career
The electric grid is changing fast. Artificial intelligence and cloud computing drive huge new data centers.
- Fields
Engineering
Computer Science
- Topics
power systems
electric grid
grid stability
- Grants
- 2 known grants, through Sep 2029
What they work on
- Develop reduced-order models of data-center power electronics showing how converters, control loops and energy storage shape the load and impedance seen by the electric grid.
- Build statistical (stochastic) models of AI and cloud computing workloads that capture bursty, time-linked and scheduler-driven power demand, then use them to analyze and control grid stability.
- Design deep neural network power flow equations for distribution grids that obey physics, can be simplified, and are convex in the layer that represents physics, for grids with limited observation.
- Create a physics-informed generative adversarial network to reconstruct power flow from limited or bad data, and derive methods to invert the neural model for real-time analysis.
More about the research
Homes add solar panels and electric vehicles. Wind and solar power rise and fall unpredictably. All of this makes it harder to keep power flowing reliably. Weng's grants build mathematical and machine-learning models that help grid operators understand and stabilize these new kinds of demand and supply. One project covers large data centers. The other covers local distribution grids that grid operators cannot fully observe.
Why it matters
Fast-growing AI data centers and rooftop solar, wind and electric vehicles strain grid reliability, risking outages and equipment damage. Better models of data-center loads could help utilities and grid planners keep power stable as computing demand grows. Physics-informed AI for distribution grids may lower the cost of managing customer-side energy resources and help utilities run more resilient grids.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Javad Khazaei
Lehigh University, PA·Engineering·Early-career
Learn low-dimensional manifolds from time-series measurements of distributed energy resources and use them for real-time predictive control of voltage, frequency and power sharing in microgrids.
Yue Cao
Oregon State University, OR·Engineering·Early-career
Develop a universal electrical model of real and virtual energy storage, based on a multi-timescale equivalent impedance network, to select storage that matches the power needs at each timescale.
Sara Eftekharnejad
Syracuse University, NY·Engineering·Early-career
Build a scalable framework to quantify interdependent power grid uncertainties from renewable generation and component outages, combining cascading failure modeling with machine learning and statistics for near-real-time analysis.
The school
Arizona State University Campus Immersion: 36 labs on PI Pages, $1.0B a year on research, 625 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.