Global synchromodal shipment matching problem with dynamic and stochastic travel times: a reinforcement learning approach
نویسندگان
چکیده
Global synchromodal transportation involves the movement of container shipments between inland terminals located in different continents using ships, barges, trains, trucks, or any combination among them through integrated planning at a network level. One challenges faced by global operators is matching accepted with services an transport dynamic and stochastic travel times. The times are unknown revealed dynamically during execution plans, but information assumed available. Matching decisions can be updated before arrive their destination terminals. objective problem to maximize total profits that expressed terms revenues, costs, transfer storage delay carbon tax over given horizon. We propose sequential decision process model describe problem. In order address curse dimensionality, we develop reinforcement learning approach learn value shipment service simulations. Specifically, adopt Q-learning algorithm update function estimations use $$\epsilon $$ -greedy strategy balance exploitation exploration. Online created based on estimated functions. performance evaluated comparison myopic does not consider uncertainties sets chance constraints feasible transshipment under rolling horizon framework.
منابع مشابه
A multiple objective approach for joint ordering and pricing planning problem with stochastic lead times
The integration of marketing and demand with logistics and inventories (supply side of companies) may cause multiple improvements; it can revolutionize the management of the revenue of rental companies, hotels, and airlines. In this paper, we develop a multi-objective pricing-inventory model for a retailer. Maximizing the retailer's profit and the service level are the objectives, and shorta...
متن کاملEfficient Dynamic Programming Solution to a Platoon Coordination Merge Problem With Stochastic Travel Times
The problem of maximizing the probability of two trucks being coordinated to merge into a platoon on a highway is considered. Truck platooning is a promising technology that allows heavy vehicles to save fuel by driving with small automatically controlled intervehicle distances. In order to leverage the full potential of platooning, platoons can be formed dynamically en route by small adjustmen...
متن کاملA hybrid meta-heuristic algorithm for the vehicle routing problem with stochastic travel times considering the driver's satisfaction
A vehicle routing problem is a significant problem that has attracted great attention from researchers in recent years. The main objectives of the vehicle routing problem are to minimize the traveled distance, total traveling time, number of vehicles and cost function of transportation. Reducing these variables leads to decreasing the total cost and increasing the driver's satisfaction level. O...
متن کاملVehicle routing with dynamic travel times: A queueing approach
Transportation is an important component of supply chain competitiveness since it plays a major role in the inbound, inter-facility, and outbound logistics. In this context, assigning and scheduling vehicle routes is a crucial management problem. In this paper, a vehicle routing problem with dynamic travel times due to potential traffic congestion is considered. The approach developed introduce...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Annals of Operations Research
سال: 2022
ISSN: ['1572-9338', '0254-5330']
DOI: https://doi.org/10.1007/s10479-021-04489-z