Dear all,
In the next RAS webinar, Warren Powell and Clark Cheng will present
"Approximate Dynamic Programming for Strategic and Operational Planning of Locomotives at Norfolk Southern Railway: An academic/industrial partnership". This webinar is FREE and open to all but registration is required. Reserve your spot at
http://tiny.cc/raswebinar19
Date/time:
Wednesday, June 22 2022, 10:00 EDT (New York)
Abstract:
After 10 years of research and development between CASTLE Lab at Princeton University and Norfolk Southern Railway, PLASMA was put into production at Norfolk Southern to perform strategic simulations and operational planning in 2008. PLASMA (Princeton Locomotive Allocation and Shop Management System) is an optimization engine based on recently developed strategy called high-dimensional approximate dynamic programming. PLASMA was integrated within NS into a large integrated planning system called LARS (Locomotive Assignment and Routing System) developed by NS. In this talk, Warren Powell is going to review the underlying modeling and algorithmic technology and describe how a single engine was used for strategic, tactical and operational planning of locomotives for NS. Then, Clark Cheng will describe what it took to get the modeling running at NS, and then keep it running over the 14+ years since the LARS fleet sizing application was deployed.
About the speakers:
Warren B. Powell is Professor Emeritus at Princeton University, where he taught for 39 years, and is currently the Chief Analytics Officer at Optimal Dynamics. He was the founder and director of CASTLE Labs, which focused on stochastic optimization with applications to energy systems, transportation, health, e-commerce, and the laboratory sciences (see www.castlelab.princeton.edu), supported by over $50 million in funding from government and industry. He has pioneered the use of approximate dynamic programming for high-dimensional applications, and the knowledge gradient for active learning problems, work that was the foundation for his books Approximate Dynamic Programming and (with Ilya Ryzhov) Optimal Learning. He developed a universal framework for sequential decision problems which is the basis for his latest book with Wiley: Reinforcement Learning and Stochastic Optimization: A unified framework for sequential decisions. He published over 250 papers and produced 70 graduate students and post-docs. He is the 2021 recipient of the Robert Herman Lifetime Achievement Award from the Society for Transportation Science and Logistics, a fellow of Informs, and the recipient of numerous other awards.
Dr. Xingang Clark Cheng is a RAS distinguished member. He has been working in the rail industry for nearly 3 decades. Clark leads the Operations Research group at Norfolk Southern. His area of responsibility is to develop OR tools and provide analytical services to business partners. The OR tools at Norfolk Southern cover many areas such as network optimization, train scheduling, fleet sizing, capacity planning, locomotive routing, railcar distribution, crew optimization, and supply/demand forecast.
------------------------------
Andrea Arias
Sr. Operations Research Scientist II
BNSF Railway
Fort Worth TX
------------------------------