Contact Us

Use the form on the right to contact us.

You can edit the text in this area, and change where the contact form on the right submits to, by entering edit mode using the modes on the bottom right. 

1 Create Way
Singapore, 138602

Research project within TUM CREATE. Focussing on modelling and optimisation of architecture and infrastructure, urban systems simulation like traffic and power are the main research interests. Apart from that, a cognitive systems group deal with human computer interaction. 

Brain - shutterstock_130952747.jpg

Machine Learning for Mobility Pattern Prediction

Intelligent Control of Energy Storage in Smart Grids


Smart grids rely on the intelligent behavior of individual consumers and generators. In this project we are developing a system which intelligently controls how mobile or stationary energy storages are charged and discharged to support the stability of power grids. One objective of the project is to realize a technology for the integration into electric vehicles (EV) to perform smarter charging and intelligent Vehicle-to-Grid (V2G) dispatch.


You will be part of a small research team addressing different aspects of this topic. To optimally schedule the charging and discharging of an EV, the time at which the vehicle will be used for driving and the required amount of energy needs to be known. This information can be predicted from a user’s historical trip data. The objective of this thesis/internship is to develop a machine learning algorithm which is capable of making this short term mobility pattern prediction. For this purpose the following tasks should be accomplished:

  • Conceptual development and implementation of a method for mobility pattern prediction based on historical trip data and context information (e.g. current driver location collected from the user’s smartphone)
  • Validation of the learning method using synthetic and real data; quantification of prediction accuracy to determine required safety buffers
  • Integration of the method into the overall system


  • Good programming skills in any object-oriented language
  • Knowledge in linear and/or non-linear optimization
  • Team spirit and innovative thinking
  • Fluency in English


  • Financial support
  • Opportunity to work on a project with real-life relevance and commercialization perspective
  • An international and multidisciplinary working environment
  • A great experience in one of the most dynamic megacities in Asia

Availability: Approx. August 2015
ContactDominik Pelzer (dominik.pelzer [at]
PDF DownloadMachine Learning for Mobility Pattern Prediction