The Airlift Planning Problem
Name
Airlift Planning problem.pdf
Description
Accepted version
Size
880.11 KB
Format
Adobe PDF
Checksum (MD5)
bd23afdb625cb94c0eaf74faaa9bb332
Author(s)
Bertsimas, Dimitris J
Chang, Allison
Mundru, Nishanth.
Date Issued
May 2019
Journal
Transportation Science
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Citation
Bertsimas, Dimitris et al. “The Airlift Planning Problem.” Transportation Science, 53, 3 (May 2019): 623-916 © 2019 The Author(s)
Version
Author's final manuscript
Abstract
The U.S. Transportation Command (USTRANSCOM) is responsible for planning and executing the transportation of U.S. military personnel and cargo by air, land, and sea. The airlift planning problem faced by the air component of USTRANSCOM is to decide how requirements (passengers and cargo) will be assigned to the available aircraft fleet and the sequence of pickups and drop-offs that each aircraft will perform to ensure that the requirements are delivered with minimal delay and with maximum utilization of the available aircraft. This problem is of significant interest to USTRANSCOM because of the highly time-sensitive nature of the requirements that are typically designated for delivery by airlift, as well as the very high cost of airlift operations. At the same time, the airlift planning problem is extremely difficult to solve because of the combinatorial nature of the problem and the numerous constraints present in the problem (such as weight restrictions and crew rest requirements). In this paper, we propose an approach for solving the airlift planning problem faced by USTRANSCOM based on modern, large-scale optimization. Our approach relies on solving a large-scale mixed-integer programming model that disentangles the assignment decision (which aircraft will pickup and deliver which requirement) from the sequencing decision (in what order the aircraft will pickup and deliver its assigned requirements), using a combination of heuristics and column generation. Through computational experiments with both a simulated data set and a planning data set provided by USTRANSCOM, we show that our approach leads to highquality solutions for realistic instances (e.g., 100 aircraft and 100 requirements) within operationally feasible time frames. Compared with a baseline approach that emulates current practice at USTRANSCOM, our approach leads to reductions in total delay and aircraft time of 8%-12% in simulated data instances and 16%-40% in USTRANSCOM's planning instances.
MIT Department
Sloan School of Management
Lincoln Laboratory
Massachusetts Institute of Technology. Operations Research Center
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1287/TRSC.2018.0847
