UT Arlington Faculty: Jay Rosenberger, Victoria Chen
Collaborators: Ellis Johnson, Barry Smith
Ph.D. Students: Dirk Günther (Georgia Tech 1998), Venkata Pilla (2006), Sheela Siddappa (2006), Narakorn Engsuwan (2013)
Topics: Network simulation (SimAir), Fleet assignment, revenue management
Description: Airlines contend with complex decision problems in continually difficult economic times, leading to the need to optimize their decisions whenever possible. The major areas of airline optimization are fleet assignment, crew scheduling, aircraft recovery, and revenue management. The primary sources of uncertainty are weather conditions, passenger demand, mechanical failures, congestion at airports, etc. The fleet assignment and crew scheduling tasks assign aircraft and personnel, respectively, to specific flights. The initial fleet assignment decision must be made far in advance (e.g., 60-90 days) of the departure of flights, when little is known about demand. However, assignments can be “adjusted” closer to departure by swapping crew-compatible aircraft of different capacities to enable the capture of more demand. Aircraft recovery must handle the re-routing of aircraft, crew, and passengers in the event of disruptions in the schedule. These disruptions occur often enough to require special methods. Finally, the revenue management task seeks to control the sale of seats, so as to maximize revenue. COSMOS researchers and collaborators have developed simulation and stochastic optimization methods to improve decision-making. These include a comprehensive discrete-event simulation model called SimAir that assists airlines in evaluating assignments and recovery policies, a statistics based approach for solving the two-stage stochastic programming formulation for fleet assignment using demand driven dispatch, and a statistics based approach for solving the Markov decision problem formulation for network revenue management.
- Shih, D. T., S. B. Kim, V. C. P. Chen, J. M. Rosenberger, and V. L. Pilla (2014). “Efficient Computer Experiment-Based Optimization through Variable Selection.” Annals of Operations Research, Special Issue on Data Mining and Informatics, 216, pp. 287–305. COSMOS Technical Report 07-02.
- Pilla, V. L., J. M. Rosenberger, V. C. P. Chen, N. Engsuwan, and S. Siddappa (2012). “A Multivariate Adaptive Regression Splines Cutting Plane Approach for Solving a Two-Stage Stochastic Programming Fleet Assignment Model.” European Journal of Operational Research, 216, pp. 162–171. COSMOS Technical Report 10-06.
- Pilla, V. L., J. M. Rosenberger, V. C. P. Chen, and B. C. Smith (2008). “A Statistical Computer Experiments Approach to Airline Fleet Assignment.” IIE Transactions, 40(5), pp. 524–537. COSMOS Technical Report 05-03. The University of Texas at Arlington. Arlington, TX.
- Siddappa, S., J. M. Rosenberger, and V. C. P. Chen (2008). “Optimizing Airline Overbooking Using a Hybrid Gradient Approach and Statistical Modeling.” Journal of Pricing and Revenue Management, 7(2), pp. 207–218. COSMOS Technical Report 06-07.
- Siddappa, S., D. Günther, J. M. Rosenberger, and V. C. P. Chen (2007). “Refined Experimental Design and Regression Splines Method for Network Revenue Management.” Journal of Pricing and Revenue Management, 6(3), pp. 188–199. COSMOS Technical Report 06-04.
- Chen, V. C. P., D. Günther, and E. L. Johnson (2003). “Solving for an Optimal Airline Yield Management Policy via Statistical Learning.” Journal of the Royal Statistical Society, Series C, 52 Part 1, pp. 1–12.
- Rosenberger, J. M., E. L. Johnson, G. L. Nemhauser (2004). “A robust fleet assignment model with hub isolation and short cycles.” Transportation Science, 38(3), pp. 357–368.
- Rosenberger, J. M., E. L. Johnson, G. L. Nemhauser (2003). “Rerouting Aircraft for Airline Recovery.” Transportation Science, 37(4), pp. 408–421.
- Rosenberger, J. M., A. J. Schaefer, D. Goldsman, E. L. Johnson, A. J. Kleywegt, G. L. Nemhauser (2002). “A Stochastic Model of Airline Operations.” Transportation Science, 36(4), pp. 357–377.
