Development of an AI-supported control model for an intelligent charging strategy for battery buses

Background

Freiburger Verkehrsbetriebe (VAG) operates a steadily growing fleet of growing fleet of electric buses and are faced with the challenge of organizing the charging processes efficiently and reliably. As the number of battery buses increases, so do the demands on the charging infrastructure, energy planning and vehicle scheduling. Key influencing factors are the different battery generations with their respective charging and discharging characteristics, network utilization, operational cycles and the charging infrastructure. In addition, the use of artificial intelligence methods is becoming increasingly important, especially for forecasting energy requirements and optimizing dynamic charging decisions. In this master's thesis, a data-based control model for an intelligent charging strategy for battery buses is to be developed in a real operational environment, taking into account both technical and economic aspects.

The master's thesis is a collaboration between the KIT and VAG.

Objectives

• Analysis of the ideal charging time for buses over the course of the day, taking into account routes, battery type and depot logistics

• Evaluation of the charging performance, service life and efficiency of different battery types and their influence on the charging strategy

• Development of an AI-supported control model for automated charging decisions

• Application and evaluation of the model using real VAG data

• Documentation of the work and presentation of the results on site.

Prerequisites

• Interest in electromobility and public transport processes

• Basic knowledge of battery technology, AI methods and machine learning processes

• Experience in data analysis or modeling

• Structured way of working

Benefits

Gaining relevant practical experience, opportunity to travel regularly to Freiburg, state-of-the-art AI methods and machine learning processes in application