Cooperation between container transport service providers can increase efficiency in the logistics sector significantly. However, cooperation between competitors requires co-planning methods that not only give the cooperating partners an advantage towards external competition but also protect the partners from losing information, clients and autonomy to one another. Furthermore, modern freight transport requires real-time methods that react to new information and situations. We propose a real-time, co-planning method called departure learning based on model predictive control where a barge operator considers the joint cost of themselves and a truck operator when deciding barge departures. At regular time-intervals, the barge operator uses previous information to propose a number of departure schedules for which the truck operator discloses their corresponding expected operational costs. Co-planning thus only requires limited exchange of aggregate data. The impact of using departure learning on the transport system’s performance and the method’s learning quality are thoroughly investigated numerically on an illustrative, simulated, realistic hinterland network. With as little as six schedules being exchanged per timestep, departure learning outperforms decentralized benchmark methods significantly in terms of operational costs. It is found that using knowledge about the performance of related schedules is important for the exploration of opportunities, but if this is relied upon too much, the realized solution becomes more costly. It is also found that departure learning is a reliable and realistic co-planning method that especially performs well when peaks in the demand make departure times highly correlated to the cost of operating the transport system, such as in hinterland areas of ports which receive large container ships.

@en

This paper considers a decentralized container transport system in which two decision-makers are involved in getting a container from its origin to its destination: a logistics service provider (LSP) and a flexible service operator (FSO). While the LSP receives shipment requests from shippers and controls the movement of containers over a multimodal network by booking scheduled (e.g., barges and trains) and flexible services (e.g., trucks) from service operators, the FSO manages a fleet of vehicles (e.g., trucks) that have flexible routes and departure times to fulfill the transport requests proposed by the LSP. In the literature, most of the studies focus on either container routing, by assuming all services have fixed routes and trucks are unlimited, or vehicle routing in a road network. This paper investigates the integrated problems of routing containers and vehicles through a multimodal network from a decentralized perspective considering the decision authorities of the LSP and the FSO. A synchromodal framework is designed to control the decision process which enables to utilize the benefits of real-time mode and route changes. To investigate the impact of communication, we develop a co-planning method under the synchromodal framework to coordinate the transport plans between the LSP and the FSO in real-time. The co-planning method considers a realistic level of information exchange and adheres to no changes in their responsibilities and authorities compared to current practice. The performance of the co-planning method is evaluated under various scenarios. The experimental results show that co-planning, using expected transport request fulfillment as feedback, reduces the total costs of container transportation and decreases the distance traveled by flexible vehicles under most of the scenarios.

@en

Container transport is an essential part of the well-functioning, highly specialized, and global production chains society currently relies on. To improve the utilization of resources, it is important to ensure all processes are as efficient as possible. Synchromodal transport is a recent transport paradigm which seeks to increase the efficiency of freight transport by letting transport providers change the mode of transport of goods in real-time. This new flexibility alleviates some of the obstacles to using sustainable transport modes, e.g., barges and trains, as it simplifies the process of changing transport plans if something unpredicted happens, such as delays, cancellations or if shipping requests that were announced later makes different routing smarter. Furthermore, synchromodal transport can improve the utilization of the transport vehicles, as the freight can be routed using up-to-date information about vehicle availability....@en

Container transport requires real-time control and a high degree of cooperation to alleviate disturbances and perform smoothly without unnecessary environmental impact and monetary losses. The involved operators are, however, often reluctant to cooperate as they fear loosing valuable information and autonomy, eventually leading their clients to choose another (cooperating) operator. In this paper we propose a real-time co-planning method, called Secure Departure Learning that in real-time lets several truck operators indicate to a barge operator what departure schedules they prefer without revealing any sensitive information. The method uses Paillier encryption and a learning method inspired by Bayesian Optimization in a model predictive control framework. At frequent time intervals a number of potential barge schedules are communicated to the co-planning truck operators. They evaluate their operation cost for each schedule and communicate it to the barge operator encrypted using several public keys. The barge operator computes the encrypted total cost for each schedules, which hereafter is decrypted by several truck operators. The first action of the schedule that results in the lowest total cost is implemented in a model predictive control fashion. Simulated experiments on a realistic, Dutch transport network illustrate that Secure Departure Learning is a good alternative for replacing the current method in practice, where barge departures are scheduled ahead of time and only mode-decisions can be updated in real time. Secure Departure Learning offers a new perspective on cooperation at the operational level in freight transport where co-planning and information protection can go hand in hand.

@en

It is desirable to improve the efficiency of container transport both from an economical and an environmental point of view, as increased efficiency decreases costs and emissions per transported container. Modern transport schemes, such as synchromodal transport, use a-modal bookings to increase the flexibility of the transport providers where the mode choice can be postponed until all demand for a planning period is known. We show in this paper the impact of planning the routes of containers, and thus the mode choice, together with truck routing. The developed integrated container and truck routing model is compared to a two-stage model that represents current practice, where the route of the containers are decided upon assuming an unlimited amount of trucks are always available. The two models are compared on several simulated, hinterland scenarios. In all scenarios, integrated routing performs at least as well as the two-stage model in terms of cost and the benefits of integration are more evident when there is a limited amount of trucks available. Integration of the routing increases the utilization rate of trucks and, often, a smaller truck fleet is needed. The presented model, therefore, demonstrates a proof-of-concept with promising improvements towards efficiency and environmental sustainability.@en

Transport of containers on a-modal bookings enables transport suppliers to route the containers in accordance with the current state of the synchromodal transport network. At the same time, it enables the transport providers to route their vehicles in real time based on the current need for transportation. The interdependency of the routes of containers and of vehicles has not yet been discussed explicitly in the synchromodal literature. This paper presents a model predictive controller that determines which combination of trucks, trains, and ships to use for transporting the containers and what routes empty and full trucks should use as one integrated problem. The impacts of this integrated problem as opposed to only considering the routes of the containers are shown with experiments on a simulated synchromodal hinterland network performed with both the proposed method and with a method that solely routes the containers. The results indicate an improved vehicle utilization. Furthermore, the integrated problem approach allows for more realistic constraints and costs.

@en

Controlling systems with both continuous and discrete actuators using model predictive control is often impractical, since mixed-integer optimization problems are too complex to solve sufficiently fast. This paper proposes a parallelizable method to control both the continuous input and the discrete switching signal for linear switched systems. The method uses ideas from Bayesian optimization to limit the computation to a predefined number of convex optimization problems. The recursive feasibility and stability of the method is guaranteed for initially feasible solutions. Results from simulated experiments show promising performances and computation times.

@en

When barges are scheduled before the demand for container transport is known, the scheduled departures may match poorly with the realised demands’ due dates and with the truck utilization. Synchromodal transport enables simultaneous planning of container, truck and barge routes at the operational level. Often these decisions are taken by multiple stakeholders who wants cooperation, but are reluctant to share information. We propose a novel co-planning framework, called departure learning, where a barge operator learns what departure times perform better based on indications from the other operator. The framework is suitable for real time implementation and thus handles uncertainties by replanning. Simulated experiment results show that co-planning has a big impact on vehicle utilization and that departure learning is a promising tool for co-planning.

@en

When containers are transported on a-modal bookings, the transport supplier can decide which combination of trucks, trains, ships, etc. to use. This gives the flexibility to transport suppliers to route the containers in accordance with the current state of the synchromodal transport network. At the same time, it enables the transport providers to route their vehicles in real time based on the current need for transportation. The interdependency of the routes of containers and of vehicles has not yet been discussed explicitly in the synchromodal literature. The aim of this paper is thus to illustrate the effect of planning the routes of containers and trucks as one integrated problem. This is addressed with a model predictive control planning method. Simulation experiments of a synchromodal hinterland network are used to illustrate the method's potential.

@en