Facilitating the Integration of Quantum Computing Solutions in Smart Grid Infrastructure
summary
A joint E.ON–Fraunhofer project trains quantum models and extracts classical surrogates to deploy on edge devices, claiming training-time quantum benefit while keeping inference classical. A 9-qubit prototype and a 4-qubit noisy-device run (IBM) produce a surrogate that reconstructs outputs with MSE 0.0013 from ~1,000 data points, shrinking memory needs from terabytes to a tiny fraction and yielding a linear-scaling pipeline suitable for per‑node Raspberry Pi–class deployment.
AI-written summary · about
chapters (7)
- 0:00Quantum computing in smart grids
- 3:56Classical vs quantum ML for power flow
- 5:45Quantum ML landscape and challenges
- 8:59Quantum circuit periodicity
- 13:15Optimizing classical surrogates
- 15:209-qubit model pipeline demo
- 17:26Deployment and validation
related talks
15mThe Fraunhofer Quantum Computing Ecosystem: Present Achievements und Developments
17mFrom Quantum Awareness to Quantum Readiness
22mSchrödinger’s Cat in Industry: Real Life Quantum Software Engineering
20mHow to Benefit from Quantum Computing
18mIntegrating Quantum Computers in High-Performance Computing Environments
21mSoftware for Quantum Computing- Easing Solutions for Complex
53mThe quantum computers are coming
47mUnboxing Quantum Computing