Time: Friday, February 25 from 1:00 PM - 1:50 PM EST

Location: Via ZOOM ,  download calendar file

Presenter: Dr. Abhishek Dubey, Vanderbilt University

Title: Optimizing the Scale up of Electrification of Public Transit

Abstract: Public bus transit services in the U.S. are responsible for at least 19.7 million metric tons of CO2 emission annually. Electric vehicles (EVs) can have a much lower environmental impact than comparable internal combustion engine vehicles (ICEVs), especially in urban areas. Unfortunately, EVs are also much more expensive than ICEVs. As a result, many public transit agencies can afford only mixed fleets of transit vehicles, consisting of EVs, hybrids (HEVs), and ICEVs. Transit agencies that operate such mixed fleets of vehicles face a set of challenging optimization questions: (a) can principled decisions that allocate different vehicle models to trips achieve better fuel efficiency than random vehicle assignments; (b) is there a principled schedule that can reduce the overall cost of vehicle charging and reduce potential grid impacts, which have to be considered in particular as the transportation electrification is increasing in general. Our solution to these problems, developed in collaboration with our partners at Chattanooga Area Regional Transportation Agency (Mr. Philip Pugliese), University of Houston (Prof. Aron Laszka) and Pacific National Northwest Lab (Dr. Malini Ghosal) demonstrates a data-driven approach where we collect, merge and analyze large volumes of high-resolution real-world telemetry data to build machine learning models that be used to understand and predict the energy operations. Our approach is novel because we have demonstrated that it is possible to transfer the machine learning models we have developed in this project to other teams and cities by using inductive transfer learning. We also showed that the performance of the macro energy prediction models could be improved using a multi-task learning approach where the learning parameters are shared between the models being developed for different vehicle types. Finally, we have developed trip and vehicle assignment and scheduling algorithms that use the energy prediction models and produce a trip to vehicle type (diesel, electric, hybrid) assignment for the whole operation to reduce overall emissions and cost.

Bio:  Dr. Abhishek Dubey is an Assistant Professor of Electrical Engineering and Computer Science at Vanderbilt University, Senior Research Scientist at the Institute for Software-Integrated Systems. Abhishek directs the SCOPE lab  (https://scopelab.org/) at the Institute for Software Integrated Systems and is the co-lead of Vanderbilt Initiative for Smart Cities Operation and Research (VISOR). His broad research interest is in the design and operation of decision procedures for smart and connected communities with a focus on transportation and energy networks. In particular, he focuses on design and operation of Cyber-physical Systems (CPS) with Artificial Intelligence (AI) based components (AI-CPS) with a focus on  public transit systems, emergency response systems and power grid. For these systems his lab investigates principled design, operation and optimization methods that not only consider the system operations, but also consider resilience, performance and assurance. Some of his key research results include the design of hierarchical decision procedures for responding to motor vehicle crashes, the design of energy-efficient transit operation procedures, and the design of transactive energy systems. His recent publications can be obtained from his lab’s publication page. His work has been funded by NSF, NASA, DOE, ARPA-E. AFRL, DARPA, Siemens, Cisco, and IBM. Abhishek completed his Ph.D. in Electrical Engineering from Vanderbilt University in 2009. He received his M.S. in Electrical Engineering from Vanderbilt University in August 2005 and completed his undergraduate studies in Electrical Engineering from the Indian Institute of Technology, Banaras Hindu University, India in May 2001.

Watch the recorded seminar

Upcoming CURENT Power and Energy Seminars

March 4 - Micron Technology Tech Talk

March 11 - Jingjing Sun & Min Lin, University of Tennessee - GaN-based T-type rectifer / High insulation voltage APS

March 18 - Spring Break, no seminar

March 25 - Fei Lu - High Efficiency Solid State Circuit Breaker for MVDC System Applications

April 1 - Timothy Fritch, TVA - Solar Overview

April 8 - Le Xie, Texas A&M - An Open-access Cross-domain Approach to Analyzing the Impact of Extreme Events on the Electricity Sector: What We Learned from COVID-19 and 2021 Texas Winter Outage

April 15 - Spring Break, no class

April 22 - Agasthya Ayachit, Mercedes Benz - eDrive Platforms and Power Electronics

April 29 - Natt Praisuwanna & Pay Kritprajun, University of Tennessee - Fault detection in inverter based grids / reactive power allocation among PV inverters

May 6 - Rupy Sawhney, University of Tennessee - People-Centric Operational Excellence Model

May 10 - Joe Zhou, Kettering University - Energy Storage Systems