Informs 2015

451 / 552

INFORMS Philadelphia – 2015
449
WC66
66-Room 113C, CC
Airline Operations
Sponsor: Aviation Applications
Sponsored Session
Chair: Cheng-lung Wu, Senior Lecturer, UNSW Australia, School of
Aviation, UNSW Australia, Kensington, NS, 2052, Australia,
1 - Enhanced Delay Propagation Tree Model with Bayesian Network
for Modelling Flight Delay Propagation
Cheng-lung Wu, Senior Lecturer, UNSW Australia, School of
Aviation, UNSW Australia, Kensington, NS, 2052, Australia,
, Weiwei Wu
This paper developed an enhanced Delay Propagation Tree model with Bayesian
Network (DPT-BN) to model delay propagation and interdependencies between
flights. Results showed that flights have non-homogeneous delay propagation
with non-IID delay profiles. The DPT-BN model was used to infer posterior delay
profiles with different delay scenarios. We also demonstrated how robust airline
scheduling methodologies can benefit from this probability-based delay model.
2 - Integer Programming Based Pairing Generation with Deviation
Penalty in Airline Crew Recovery
Hyunsuk Lee, Ph.d Student, McCombs School of Business, The
University of Texas at Austin, 2110 Speedway Stop B6500, CBA
5.202, Austin, TX, 78712, United States of America,
Douglas Fearing
In this paper, we will explore how to model airline scheduling problems
(flight/crew scheduling and recovery), and apply IP based pairing generation
technique to crew recovery with deviation penalty. In particular, we will control
IP based pairing generator by restricting the number of different flights in new
pairing. Such a study should hopefully give insights to minimizing deviations
from original schedule.
3 - U.S. Commercial Aviation Demand Forecasting with a Panel Data:
The Role of Individual Heterogeneity
Mei Liu, Economist, FAA, 6712 Tildenwood Lane, Rockville, MD,
20852, United States of America, ,
Dipasis Bhadra
Studies in aviation demand forecasting have long relied on time series
approaches, ignoring the individual heterogeneity in a panel data. Heterogeneity
is most evident in the U.S. aviation sector where network effect is prevalent. This
paper identifies the route-specific effects from 2000 through 2010 and takes it
forward to perform a 4-year-ahead forecasting. We evaluate whether the
inclusion of individual heterogeneity reduces forecast errors.
WC67
67-Room 201A, CC
Risk in Freight Transport and Logistics
Sponsor: TSL/Freight Transportation & Logistics
Sponsored Session
Chair: Choungryeol Lee, Purdue University,
United States of America,
1 - Downside Risk Analysis for Planning Intermodal
Facility Investments
Irina Benedyk, United States of America,
Hong Zheng, Yuntao Guo, Srinivas Peeta, Ananth Iyer
We apply Down Side Risk analysis to plan intermodal facility investment
decisions. The model accounts for factors such as the future global commodity
flow changes and demand uncertainty. Experiment results show that tighter
downside risk constraints lead to the inland intermodal facilities being preferred
for investment compared to the ports. They also suggest that low downside risk
values increase the total cost but reduce its variation.
2 - Procuring and Transporting Commodities: Hedging against Price,
Demand and Freight Rate Risk with Options
Arun Chockalingam, Assistant Professor, Eindhoven University of
Technology, Den Dolech 2, Eindhoven, 5612AZ, Netherlands,
Taimaz Soltani, Jan Fransoo
We consider a firm that procures and transports a commodity via ocean freight to
its production plant where the commodity is converted to a final product to meet
customer demand. Transportation of commodities via ocean freight has increased
significantly in recent years leading to increasing volatility in the cost of freight
transportation. We study how a firm can reduce its procurement and
transportation costs using options on procuring the commodity and freight space
in a newsvendor setting.
3 - Risk Management Strategies in Transportation Capacity
Decisions: An Analytical Approach
Jiho Yoon, Michigan State University, N468 North Business
Complex, Michigan State University, East Lansing, MI, 48824-
1121, United States of America, ,
Hakan Yildiz, Sri Talluri
In recent years, access to freight transportation capacity has become a constant
issue in the minds of logistics managers due to capacity shortages. In a buyer-
seller relationship, reliable, timely, and cost-effective access to transportation is
critical to the success of such partnerships. Given this, guaranteed capacity
contracts with 3PLs may be appealing to shippers to increase their access to
capacity and respond effectively to customer requirements. With this new
opportunity, 3PLs must focus on approaches that can assist them in analyzing
their options as they promise guaranteed capacity to shippers when faced with
uncertain demand and related risks in transportation. In this paper, we
analytically analyze three capacity-based risk mitigation strategies and the mixed
use of these individual strategies using industry based data to provide insights on
which strategy is preferable to the 3PL and under what conditions. We posit that
the selection of a strategy is contingent on several conditions faced by both the
shipper and the carrier. Although our approach is analytical in nature, it has a
high degree of practical utility in that a 3PL can utilize our decision models to
effectively analyze and visualize the trade-offs between the different strategies by
considering appropriate cost and demand data.
4 - Freight Option-Based Mechanism for Multiple Carrier
Collaborative Less-Than-Truckload Logistics
Choungryeol Lee, Purdue University,
United States of America, Srinivas Peeta
We propose option-based mechanisms for LTL carrier-to-carrier collaboration to
alleviate operational and financial risks resulting from stochastic demand in the
operational horizon. It aims to enhance the utilization of fleet capacity and reduce
the induced costs of handling demand variability. Numerical experiments
illustrate the feasibility and provide useful insights of implementing option-based
multiple carrier collaborative LTL logistics.
WC68
68-Room 201B, CC
Traffic Control
Sponsor: Transportation, Science and Logistics
Sponsored Session
Chair: Indrajit Chatterjee, University of Minnesota, Twin Cities, 500
Pillsbury Drive SE, Minneapolis, mn, 55455, United States of America,
1 - Computationally Efficient Algorithms for the Calibration of High-
resolution Stochastic Traffic Simulators
Chao Zhang, Massachusetts Institute of Technology, 77
Massachusetts Ave, Cambridge, MA, 02139, United States of
America Carolina Osorio, Gunnar Flütterüd
This work formulates the calibration problem as a simulation-based optimization
(SO) problem which is addressed by the metamodel approach. The metamodel
combines information from both the simulator and an analytical traffic model
that relates the calibration parameters to the simulation-based objective function.
The performance of the proposed approach has been tested on a toy network and
is currently being evaluated on a large-scale metropolitan network in Berlin,
Germany.
2 - Decentralized Traffic Assignment for Multi-level Modeling
Ehsan Jafari, University of Texas at Austin, Austin, TX,
United States of America, , Stephen Boyles
Statewide planning model is used for planning projects that will have implications
on transportation across the entire state. At the same time, medium-sized cities
have their own planning model. The process of updating these models in a way
that maintains consistency between them is laborious and time-consuming. In
this research, a decentralized bi-level modeling approach, based on the concept of
network contraction, is proposed to address these issues.
3 - A Simulation-based Optimization Algorithm for Traffic
Responsive Control
Linsen Chong, Massachusetts Institute of Technology,
Cambridge, MA, United States of America, ,
Carolina Osorio
We propose a simulation-based optimization (SO) framework to address generally
constrained urban traffic responsive control problems. We develop a tractable
dynamic traffic model that is inspired from traffic flow theory, transient queueing
theory and is parameterized by time-dependent sensor data. We illustrate the
performance of the proposed method through a large-scale urban traffic case
study.
WC68