Available Master's Projects

Projects on applying algorithms to real-world problems

Many exciting Master's projects can be defined by applying state-of-the-art planning, scheduling, optimization and game theoretical algorithms to real-world problems. The prerequisite for all projects is that you are doing your master's in computer science including at least the course on Advanced Algorithms and preferably the one on Algorithms for Planning and Scheduling. Below is a sample of problems and their source (typically industry or a scientific collaborator).




Optimizing the heat network at the TU Delft campus

Dr. Keviczky (3ME)

De Weerdt

Scheduling Flexible Charging of Electrical Vehicles

possible internship at Jedlix (Eneco)

De Weerdt/Spaan

Multi-party multi-issue negotiation versus matching

C. Jonker  (Interactive Intelligence)

De Weerdt

Voting with incomplete preferences

University of Southampton

De Weerdt

Scheduling for the PowerMatcher toolkit


De Weerdt/Spaan

Planning heat pumps and heat storage for households

possible internship at TNO, cooperate with De Nijs

De Weerdt

Improving energy use in a district of greenhouses with heat exchange

possible internship at Eneco / AgroEnergy

De Weerdt

Algorithms for the Green Village

Green Village

De Weerdt/Spaan

Heatweb – Operations of a smart thermal grid

possible internship with E.On

De Weerdt/Spaan

Portfolio hedging – Optimizing forward market positions

possible internship with E.On

De Weerdt/Spaan

Power to Heat – Optimize use of industrial electric boiler

possible internship with E.On

De Weerdt/Spaan

Multi-objective Mechanism Design

CWI - Peter Bosman

De Weerdt

Algorithms for real-time dynamic routing for taxis -- dial-a-ride

possible internship with Transvision

De Weerdt

Long-term / short-term optimization or investment decisions versus operational optimization of warm and cold water distribution

possible internship with Mijnwater (Heerlen)

De Weerdt

Auctions and tenders with uncertainty

possible internship with Grontmij

De Weerdt

Airline operation optimization with uncertainty

Aerospace Engineering


Traffic flow optimization

Transport, Infrastructure, and Logistics


Analyzing and optimizing energy use at TU Delft buildings (e.g. Learning Center)

with Erwin Mlecnik (OTB)

De Weerdt

combined work and study on decision support at KLM

at KLM

De Weerdt

experimental comparison of algorithms for (temporal) planning

with Leon Planken

De Weerdt

parallel algorithms for simple temporal planning

with Leon Planken

De Weerdt

Reducing traffic congestion through coordination

possible cooperation with Southampton university

De Weerdt

multi-objective maintenance planning

possible internship with NedTrain

De Weerdt/Witteveen

Decision support for large-scale trip planning

Kees is a planner at a company that moves vehicles around the Netherlands. Each day, the company’s customers inform him about jobs that need to be performed the next day. A job might be to pick up a vehicle between 9:00 and 10:00 in Amsterdam and deliver it to Breda before noon. The company has drivers in many locations at its disposal and Kees has to decide to which driver each job should be allocated. As jobs typically don’t take the whole day, Kees usually assigns trips consisting of multiple jobs to a driver. Drivers use public transport to get from the dropoff location of one job to the pickup location of the next one. What’s important to Kees is to minimize the total cost of executing all jobs on a day, taking into account the hourly wages of the drivers as well as their public transport expenses. How can we create a planning algorithm for this problem to base a decision support system for Kees on?

Contact: Matthijs Spaan

Agent-based Airport Surface Traffic Planning Under Uncertainty

The amount of traffic at airports increases with every passing year. One of the major challenges which airports face is how to manage ground movements of aircraft in an effective and efficient way.  Traditionally, to address the challenge of optimal airport surface traffic planning, approaches from the area of Operations Research have been used. However, such approaches have scalability issues with handling realistic amounts of traffic at large modern airports.  In this project, agent-based planning approaches will be attempted to address the scalability issue. In contrast to traditional OR techniques, in multi-agent systems planning is performed by a large number of agents, which possess local information about the system and are able to communicate with each other.

The aim of the project is to develop an agent-based airport surface traffic planning algorithm in the context of a case study at a real airport (e.g., Schiphol).  The algorithm should be able to deal with uncertainties, in particular in input parameters such as the expected landing time of aircraft and the expected pushback time of aircraft. The planning should ensure the scheduled runway arrival times for each departing aircraft.

This project is a collaboration with Aerospace Engineering. Contact: Matthijs Spaan

Altruistic road users and optimization of sustainable traffic flows

Managing motorized traffic flows is an important issue in every major metropolitan area. Traffic management aims to reduce these problems, but it cannot normally influence routes chosen by individual vehicles. We propose an approach where individual route planning and navigation systems on the one hand and collective considerations on the other are not completely independent and sometimes counteractive processes. In contrast, route planning and navigation systems should be able to take into account multiple, collective objectives concerning congestion and pollution on various roads in the complete road network, and help in balancing traffic over the network in a highly effective way.

A crucial question in this regard is then: under what conditions will road users agree to contribute to such optimal and sustainable traffic conditions, at the cost of personal travel time losses? Some road users may be willing to contribute to the greater societal good, whereas others are more inclined to ‘free-ride’ and profit from the altruism of their fellow travellers. This research will employ discrete choice theory and stated choice experiments to empirically infer the trade-offs road users make in the context of a routing scheme that asks them to be altruistic for the benefit of system level gains in travel time and pollution reduction.

In collaboration with TPM. Contact: Matthijs Spaan

Planning under uncertainty

Planning under uncertainty is a technique for enabling agents to successfully plan their decisions in domains with stochastic transitions and partial observability, e.g., because of noisy sensors. In the Artificial Intelligence community the Partially Observable Markov Decision Process (POMDP) and related multiagent models have become popular choices to address these hard planning problems. In the Algorithmics group a considerable body of expertise, algorithms and software is present regarding these methods. This allows for defining challenging projects focused on improving state-of-the-art algorithms with a high potential for publications.

Contact: Matthijs Spaan

Matching uncertain demand and supply in smart electricity networks

Integration of renewable energy in power systems is a potential source of uncertainty, because renewable generation is variable and may depend on changing and highly uncertain weather conditions. An example is power generated by wind turbines. Although renewable wind energy is clean and cheap, it may be intermittent and its availability is uncertain and difficult to predict. To reduce peak power consumption and to mitigate the effects of uncertain renewable power supply, electricity usage can be deferred in time such that demand and supply are balanced. An example is the charging process of an electric vehicle, which often does not have to be charged immediately, as long as the available power in the battery is sufficient to reach a destination. In our group we develop efficient planning techniques to automatically coordinate deferrable loads, such that electricity is used when renewable supply is available.

Various MSc projects can be formulated in this domain. Examples include, but are not limited to, coordination of charging electric vehicles, scheduling household appliances, electricity usage within network constraints and predicting electricity demand and supply. We also have an existing collaboration with the Electrical Sustainable Energy department of the EEMCS faculty.

Contact: Erwin Walraven, Matthijs Spaan

Reinforcement learning for transportation, traffic and logistics

Reinforcement learning is a branch of machine learning focusing on agents that are able to automatically learn how they should act in their environment, and has been applied for coordination of multiagent systems in several real-world domains. For instance, reinforcement learning has been used for intelligent control of multiple traffic lights in the urban area, as well as optimization of traffic flow on highways. Other examples in the area of transportation and logistics include air traffic management and automated unloading of ships in a harbor. Typically, a real-world problem is modeled as reinforcement learning problem and then evaluated through realistic simulations.

MSc projects may focus on the application of reinforcement learning algorithms to realistic domains, but also allow for more fundamental research related to reinforcement learning and decision making under uncertainty. In our group expertise and software are present for reinforcement learning in transportation, traffic and logistics domains. However, students may also choose their own problem domain to define an interesting thesis project.

Contact: Erwin Walraven, Matthijs Spaan

Prediction of material malfunctions in trains

Modern trains are equipped with a lot of ICT supplies. This makes it possible to obtain sensor data, which can be used for data-mining. In this masters project the goal is to find, within this sensor data, indicators for (soon to be) malfunctioning material. These indicators can then be used to give advice regarding which parts of the train should be inspected and/or repaired.

This thesis consists of two parts:

  • Construct, using patterns in the sensor data and repair history, a decision model which shows what parts of the train should be inspected.
  • Refine the constructed model in order to use it for prediction of how long it will take before a part will malfunction.

Contact: Cees Witteveen

Quality personal transport for elderly and disabled people

Currently the quality of personal transport for elderly and disabled people is very low. The main reason is the heavy competition for the three-year long contracts with governmental institutions. What if people can choose their preferred company per ride? What if people can choose between different pick-up times for their transport?

In this project you will test multiple methods for assigning transportation jobs to taxi companies, such that the preferences and quality for the end-users increases without increasing the costs for the government too much.

Contact: Mathijs de Weerdt

Planning in the harbor

In the harbor in Rotterdam, every day many barges need to visit a number of the terminals. Sometimes they need to wait a long time before they are served. What can we do to coordinate the loading and unloading of barges at the different terminals better to reduce the total time barges spend waiting for their turn?

For this project you will study the interesting field of mechanism design. To get to know more about the application, we will bring you into contact with researchers from the Erasmus university who are studying many other aspects of the process in the harbor as well.

contact: Mathijs de Weerdt

More information

The topics listed above are only a sample of possible projects; more up-to-date information can be obtained by contacting our staff members:

If you are currently not studying in Delft, but if you'd like to study here, please read and act according to the formal guidelines of Delft University of Technology.