Hourly Traffic Density Based Decomposition in Non-Centralised Railway Traffic Management

The Dutch railway network is a dense network with 7000 kilometers of railway tracks spread over only 42 000 square kilometers [1, 2]. Additionally, the railways are responsible for 1.4 million passengers every working day [1]. These factors make both the infrastructure and timetable of the Dutch railway network extremely intricate. On top of...

Learning Drivers’ Preferences in Delivery Route Planning: an Inverse Optimization Approach

Optimizing delivery routes is a well-researched topic, however, most of the classical approaches do not incorporate preferences of drivers, as those approaches focus on minimizing the time or distance of the routes. As a result, the actual driven route of an experienced driver often deviates from the proposed route since the drivers have tacit...

Shared Mobility-on-Demand Systems: Reducing service unreliability

On-demand ridesharing might be an effective solution to reduce traffic congestion and, as a result, reduce emissions to mitigate environmental issues. However, travel times are more uncertain in ridesharing services compared to non-shared transit services due to their shared nature. For example, at one moment, the users are informed that the...

Optimising quay crane operations based on data-driven cycle time prediction: A case study at APM Terminals MVII

Quay cranes on modern container terminals have the possibility to lift two 40ft. containers side by side. In order to be able to perform this type of lift, the crane must be equipped with a tandem spreader. As this type of spreader cannot be used for performing certain lifts, such as the handling of hatch covers, switches between single spreader...

An analysis of the potential locations for Modular Mobile Terminals: Case study for the ports of Rotterdam and Antwerp

Long waiting times in ports for inland vessels to load and unload containers are a serious problem. The European project NOVIMOVE researches the inefficiencies and suggests solutions. One of the solutions for reducing waiting times in ports is the placement of Modular Mobile Terminals (MMTs). The focus of the research will be on the ports of...

Design implication and performance assessment of iron fuelled ships

In order to meet climate change mitigation targets, the shipping industry must change to an alternative fuel. From a ship design perspective, the switch to an alternative fuel is often a downgrade with respect to the use of conventional fuels. For instance, most alternative fuels have a low energy density, rely on technology that is not fully...

From Supervised to Reinforcement Learning: an Inverse Optimization Approach

We propose a novel method combining elements of supervised- and Q-learning for the control of dynamical systems subject to unknown disturbances. By using the Inverse Optimization framework and in-hindsight information we can derive a causal parametric optimization policy that approximates a non-causal MPC expert. Furthermore, we propose a new...

Learning Parametric Integer Programming via Inverse Optimization

Inverse Learning is implemented in order to learn a control/decision policy (in the integer space) from an Expert Agent. The Learner Agent assumes that the Expert is acting minimizing an unknown cost function and tries to approximate it, through its own parametrized version of it. Learning can be performed in two different ways: offline ...

Regulations Aware Motion Planning for Autonomous Surface Vessels in Urban Canals

With a growing number of citizens and tourists, the scarce public space, roads, and public transport in Amsterdam are experiencing rising pressure. Instead of utilizing the conventional transportation routes, Autonomous Surface Vessels (ASVs) could transport goods and people via the 165 canals present in Amsterdam. <br/>However, urban canals are...

Centralized Operational Strategy for Container Transport in a Synchromodal Transport System

In time of fast globalization and urbanization, the volumes of transported containers have significantly increased in the last decades. The challenges of operating with high volumes of containers have propagated from the deep-sea terminals into the hinterland network resulting in extensive use of road transportation, long waiting times and high...

A performance indicator framework for providing data-driven services to European truckload carriers: From identification of performance indicators to framework development

The past decade has seen a rise in ability to collect, store and manage large amounts of data. With data becoming increasingly available to businesses, organizations are looking to new ways to gain insight into their activities. Acquired information can help transportation companies to cope with industry trends of expanded competition, the...

Using stochastic and dynamic routing models to improve the performance of an e-grocer’s delivery service

E-grocers are grocery markets which offer their assortment online and deliver a customer's groceries at home. For an e-grocer the quality of their delivery service is a crucial asset to create and maintain a loyal customer-base. Because the online share of the grocery market has grown rapidly over the last decade, there is an urgent need for e...

An agent-based model evaluating last-mile solutions for parcel delivery in an urban area: A case study in the zero emission zone of Rotterdam

E-commerce has grown rapidly worldwide over the past decade and thus more parcels are shipped into urban areas. The last mile delivery of these parcels into an urban area create big problems such as congestion and pollution. In order to tackle these problems new solutions have been found by either changing the operations of the system or using...

Online Convex Optimization with Predictions: Static and Dynamic Environments

In this thesis, we study Online Convex Optimization algorithms that exploit predictive and/or dynamical information about a problem instance. These features are inspired by recent developments in the Online Mirror Decent literature. When the Player's performance is compared with the best fixed decision in hindsight, we show that it is possible...

Fuel cell Systems Applied in Expedition Cruise ships: A Comparative Impact Analysis

Global endeavors to reduce emissions in the shipping industry are accelerating the interest in fuel cell systems. This paper explores the application of different fuel cell types (LT-PEMFC, HT-PEMFC and SOFC) in combination with different fuels (LH2, LNG,MeOH and NH3) in expedition cruise ships. An impact model is developed for the first design...

Game and Choice Based Simulation: The design of a methodological framework using the case of the Physical Internet inspired “Freight Transportation Game”

Serious games have the potential to be used as an innovative data collection method. Combining this with Discrete Choice Modelling (DCM) could create a methodology that provides insight into the player's behaviour and allows for creating a realistic simulation. This innovative Game and Choice Based Simulation (GCBS) methodology has been...

A predictive model for parcel classification in the context of last-mile delivery

Last-mile delivery for shipments in the B2B (business-to-business) market make use of two types of last-mile delivery mode, van and truck, as the number of shipments per consignee is various in size, weight, and volume. A parcel classification task exists to make an optimum classification of the parcel, toward which last-mile delivery mode. The...

Improving Dynamic Route Optimisation by making use of Historical Data

In thedynamic world we live in, the transportation of people and goods in a reliable,efficient and timely manner has grown to be more important than ever. Roads andcities are becoming more congested and the impact of greenhouse gasses canalready be observed. The need for controlling transportation systems, andspecifically fleets of vehicles,...