AI-Based Analytics and Energy Modeling Frameworks for Characterizing Urban Energy Systems

Abstract:
Urban energy systems are growing in complexity as they respond to the challenges of planning location-specific energy transitions. However, current modeling approaches often fail to capture the physical, behavioral, and systemic diversity required for effective localized planning and decision-making.

In this talk, I will present integrated frameworks that combine bottom-up physics-based modeling with AI-driven analytics for characterizing urban energy systems. I will first show how the URBANopt platform has developed capabilities that enable coordinated analysis and co-design across buildings, DERs, and the grid. I will then discuss an AI-driven capabilities that automates input generation and supports dynamic scenario exploration.

These capabilities transform urban energy system planning by reducing the labor required for model generation, scaling scenario exploration, and improving accuracy for localized analysis. Together, they form a scalable and adaptable framework that provides stakeholders with actionable insights for planning reliable and efficient energy transitions.

Biography:
Dr. Rawad El Kontar is a Senior Research Engineer at the U.S. Department of Energy’s National Laboratory of the Rockies (NLR). He is the lead developer of URBANopt, DOE’s open-source urban energy modeling platform, and the creator of the Urban Systems Generator, an AI-driven framework that automates building-level data completion and scenario generation for city-scale energy modeling. With a multidisciplinary background spanning architecture, building science, and data science, Rawad develops analytics and software platforms that integrate machine learning, AI, and energy simulation to accelerate the co-design and optimization of buildings, distributed energy resources (DERs), and grid systems. His work supports stakeholders in advancing reliable and efficient energy.