Probabilistic grid state estimation engine for
This technology is a software framework that helps model and predict the unpredictable, complex behavior of power grids — things like fluctuating renewable energy output or sudden demand spikes. It takes messy, real-world sensor data that doesn't follow neat statistical patterns and uses machine learning to compress it into a simpler, more manageable representation. It then uses an advanced sampling technique (a hybrid Markov Chain Monte Carlo method) to estimate what's actually happening inside the grid at any given moment. The end result is a set of estimated system states that can feed directly into grid control decisions.
What you could build
A software module or analytics engine embedded in energy management systems (EMS) or SCADA platforms that provides real-time probabilistic state estimation for grids with high renewable penetration; likely buyers are grid operators, independent system operators (ISOs), and power management software vendors like GE Vernova or Siemens Energy.
Who in Virginia should care
Virginia's growing data center load and Dominion Energy's grid modernization efforts create a plausible local buyer or pilot partner for probabilistic grid state estimation tools.
Readiness: Lab validated
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Xiao Chen, Can Huang, Liang Min, Charanraj Thimmisetty, Charles Tong, Yijun Xu, Lamine Mili
- Granted
- February 27, 2024
- Status
- Granted patent
- Patent number
- 11914937
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.