Use AI Agents to Analyze Power Grid Optimization
Key Takeaways:- Explore how AI agents can be applied to real-world data analysis problems.
- Build and analyze a synthetic power grid to understand load balancing and optimization.
- Learn how to use Zerve AI’s notebooks and agent workflows for advanced data science tasks.
Description
Balancing supply and demand in a power grid is a complex, high-stakes problem—making it an ideal use case for AI-driven analysis. By combining agentic workflows with modern data science tools, you can simulate, analyze, and optimize systems that would be difficult to manage manually.
In this code-along, Greg Michaelson and Jason Hillary, the
CPO and CTO at Zerve AI, will guide you through building and analyzing a synthetic power grid using Zerve AI’s data science notebooks and agentic workflows. You’ll explore how AI agents can assist with data analysis, optimization, and decision-making, while gaining hands-on experience with a realistic energy systems scenario. You'll generate a network of substations and transmission lines, simulate fluctuating demand, define generation costs and line capacity constraints, and optimize power flow across the network.
Presenter Bio
Greg Michaelson champions the perspective of Zerve’s users, helping ensure the platform reflects the realities of day-to-day working with data, and is an active contributor to the data science community. Previously, he was an early leader at DataRobot, serving as Chief Customer Officer after senior analytics roles at Travelers and Regions Bank. He began his career teaching statistics at the University of Alabama
Jason Hillary co-founded Zerve because he saw how much friction slowed down people working with data. With a PhD in Engineering from the University of Limerick, he’s spent years building AI systems that actually work in production, not just in theory. Before starting Zerve, Jason worked across the data and AI space, focused on making technical work less painful and more productive.