Speaker: Rahman Khorramfar
Title: “Power-Gas Infrastructure Planning under Weather-induced Uncertainty”
Date: 7th February, 2025 (Friday)
Time: 16:00 -17:00
This is an online seminar. To request event details please send a message to department.
Abstract:
Achieving economy-wide decarbonization via variable renewable energy (VRE) expansion and electrification of end-uses requires new approaches for energy infrastructure planning that consider, among other factors, weather-driven uncertainty in demand and VRE supply. A planning model that fails to account for these uncertainties can hinder the intended transition efforts and increase the risk of disruptions in energy supply, especially during extreme weather conditions. In this talk, I will present two modeling approaches resulted from our recent attempt to incorporate weather-driven uncertainty in energy planning models. The first approach is based on the distributional robust optimization (DRO) approach for the generation and transmission expansion problem (GTEP) of joint power-gas infrastructure and operations planning under the uncertainty of both demand and renewable supply. The second approach is an ML-assisted optimization framework where we rely on a deep generative learning model to obtain robust energy plans while avoiding overly conservative outcomes.
Bio:
Dr. Khorramfar is currently a postdoctoral associate at MIT Energy Initiative and LIDS, developing advanced optimization and machine learning tools for design, planning, and operations of climate-resilient energy systems. He received PhD in Industrial and Systems Engineering from NC State University where he primarily worked on hierarchical decision-making and optimization under uncertainty and their applications in production planning, supply chain, and capacity expansion problems.