This paper studied a tactical liner shipping schedule design issue under sail and port time uncertainties,
which is the determination of the planned arrival time at each port call as well as the punctuality rate and number
of assigned ship on the route. A number of studies have tried to introduce the operational speed adjustment
measure into this tactical schedule design issue, to alleviate the discrepancies between designed schedule and
maritime practice. On the one hand, weather conditions can lead to speed loss phenomenon of ships, which may
result in the failure of ships’ punctual arrivals. On the other hand, improving the ability of speed adjustment
can decrease the late-arrival compensation, but increase the fuel consumption cost. Then, we formulated a
machine learning-based liner shipping schedule design model aiming at above-mentioned two limitations on speed
adjustment measure. And a machine learning-based approach has been designed, where the speed adjustment
simulation, the neural network training and the reinforcement learning were included. Numerical experiments were
conducted to validate our results and derive managerial insights, and then the applicability of machine learning
method in shipping optimization issue has been confirmed.
DU Jian1∗ (杜 剑), ZHAO Xu2 (赵 旭), GUO Liming2 (郭力铭), WANG Jun2 (王 军)
. Machine Learning-Based Approach to
Liner Shipping Schedule Design[J]. Journal of Shanghai Jiaotong University(Science), 2022
, 27(3)
: 411
-423
.
DOI: 10.1007/s12204-021-2338-9
[1] VERNIMMEN B, DULLAERT W, ENGELEN S. Schedule unreliability in liner shipping: Origins and consequences for the hinterland supply chain [J]. Maritime Economics & Logistics, 2007, 9: 193-213.
[2] NOTTEBOOM T E. The time factor in liner shipping services [J]. Maritime Economics & Logistics, 2006, 8(1): 19-39.
[3] W ANG S A, MENG Q. Liner ship route schedule design with sea contingency time and port time uncertainty [J]. Transportation Research Part B: Methodological, 2012, 46(5): 615-633.
[4] W ANG S A, MENG Q. Robust schedule design for liner shipping services [J]. Transportation Research Part E: Logistics and Transportation Review, 2012, 48(6): 1093-1106.
[5] LEE C Y, LEE H L, ZHANG J H. The impact of slow ocean steaming on delivery reliability and fuel consumption [J]. Transportation Research Part E: Logistics and Transportation Review, 2015, 76: 176-190.
[6] DU J, ZHAO X, W ANG J. Container feeder liner shipping service optimal design model [J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(3): 178-183 (in Chinese).
[7] ALIBEYG A, CONTRERAS I, FERN áNDEZ E. Exact solution of hub network design problems with profits [J]. European Journal of Operational Research, 2018, 266(1): 57-71.
[8] DU J, ZHAO X, JI M J. Planning model of feeder shipping network for container liners under considering shipper preference [J]. Journal of Traffic and Transportation Engineering, 2017, 17(3): 131-140 (in Chinese).
[9] TRAN N K, HAASIS H D. Literature survey of network optimization in container liner shipping [J]. Flexible Services and Manufacturing Journal, 2015, 27(2/3): 139-179.
[10] W ANG S A, MENG Q. Reversing port rotation directions in a container liner shipping network [J]. Transportation Research Part B: Methodological, 2013, 50: 61-73.
[11] PLUM C E M, PISINGER D, SALAZAR-GONZ áLEZ J J, et al. Single liner shipping service design [J]. Computers & Operations Research, 2014, 45: 1 - 6 .
[12] KARIMI H, SETAK M. A bi-objective incomplete hub location-routing problem with flow shipment scheduling [J]. Applied Mathematical Modelling, 2018, 57: 406-431.
[13] SUN Z, ZHENG J F. Finding potential hub locations for liner shipping [J]. Transportation Research Part B: Methodological, 2016, 93: 750-761.
[14] LIN D Y, HUANG C C, NG M W. The coopetition game in international liner shipping [J]. Maritime Policy & Management, 2017, 44(4): 474-495.
[15] RAU P, SPINLER S. Alliance formation in a cooperative container shipping game: Performance of a real options investment approach [J]. Transportation Research Part E: Logistics and Transportation Review, 2017, 101: 155-175.
[16] KOZA D F. Liner shipping service scheduling and cargo allocation [J]. European Journal of Operational Research, 2019, 275(3): 897-915.
[17] W ANG S A, MENG Q, LIU Z Y. Containership scheduling with transit-time-sensitive container shipment demand [J]. Transportation Research Part B: Methodological, 2013, 54: 68-83.
[18] W ANG S A, ALHARBI A, DA VY P. Liner ship route schedule design with port time windows [J]. Transportation Research Part C : Emerging Technologies, 2014, 41: 1-17.
[19] ALHARBI A, W ANG S A, DA VY P. Schedule design for sustainable container supply chain networks with port time windows [J]. Advanced Engineering Informatics, 2015, 29(3): 322-331.
[20] T A N Z J , W A N G Y D , M E N G Q , e t a l . J o i n t s h i p schedule design and sailing speed optimization for a single inland shipping service with uncertain dam transit time [J]. Transportation Science, 2018, 52(6): 15701588.
[21] JIANG X, MAO H J, W ANG Y D, et al. Liner shipping schedule design for near-sea routes considering big customers’ preferences on ship arrival time [J]. Sustainability, 2020, 12(18): 7828.
[22] BELL M G H, LIU X, ANGELOUDIS P, et al. A frequency-based maritime container assignment model [J]. Transportation Research Part B: Methodological, 2011, 45(8): 1152-1161.
[23] QI X T, SONG D P. Minimizing fuel emissions by optimizing vessel schedules in liner shipping with uncertain port times [J]. Transportation Research Part E: Logistics and Transportation Review, 2012, 48(4): 863-880.
[24] BROUER B D, DIRKSEN J, PISINGER D, et al. The Vessel Schedule Recovery Problem (VSRP): A MIP model for handling disruptions in liner shipping [J]. European Journal of Operational Research, 2013, 224(2): 362-374.
[25] LI C, QI X T, LEE C Y. Disruption recovery for a vessel in liner shipping [J]. Transportation Science, 2015, 49(4): 900-921.
[26] LI C, QI X T, SONG D P. Real-time schedule recovery in liner shipping service with regular uncertainties and disruption events [J]. Transportation Research Part B: Methodological, 2016, 93: 762-788.
[27] CHERAGHCHI F, ABUALHAOL I, F ALCON R, et al. Modeling the speed-based vessel schedule recovery problem using evolutionary multiobjective optimization [J]. Information Sciences, 2018, 448/449: 53-74.
