Open Source in an Age of Transformation for the Energy Industry
summary
Google describes concrete results: 35 GW of new clean energy procured since 2010 (12 GW in 2024), AI weather models boost forecast resolution ~5× to ~10 km and add solar irradiance, cutting large forecast errors by ~21% and imbalance penalties ~15%. An AI AC OPF solver finds near-optimal solutions within 0.06% of optimal at 28,000× faster than traditional solvers and ships its training dataset open source. Edge architecture prototypes use Kubernetes with Open DSO/Open Field Message Bus; a Westinghouse pilot claims ~25% cost and ~50% time reductions.
AI-written summary · about
chapters (8)
- 0:00Introduction and speakers
- 1:48Energy challenges and goals
- 7:25AI weather forecasting breakthroughs
- 12:35Optimal power flow with AI
- 17:47Distributed grid edge computing
- 20:12AI for nuclear plant efficiency
- 21:38Open source energy tools
- 22:50Q&A session
related talks
13mHow Open Source Is Helping Fight Climate Change
25mThe Value of Open Source Short-term Energy Forecasting Demo...
30mOSS = Open Source ... Strategy!? Google Is Doubling Down on K8s in the AI Era, and You Should Too!
46mPanel: Expanding the OpenSynth Ecosystem: Open Source Data and AI for Power Systems Modelling
06mThe AI Compute Crisis & Web3 Opportunity
22mThe Imperative for Open Source AI - The Path Forward to Take Down the AI Oligarchs
18mAI Owes its Rebirth to Open Source and the Cloud
11mKeynote: Open Source Stack Empowers the AI Era