Project information

  • Category: Data Science
  • Data: NDW mixed traffic data and OSM POI data
  • Project: Work of MSc student - Mingjia
  • Methods: Optimization, Data Fusion
  • Technologies: Python, pandas, geatpy, networkx
  • Conference/Journal: IEEE ITSC Conference 2023
  • URL: Proceedings needs to be published

Project details

This study introduces a data-driven framework for planning fast-charging facilities for freight electric vehicles, using highway traffic data to analyze and compare spatial and temporal flow patterns of general and freight traffic. Employing graph theory-based methods, we identify key traffic nodes within the highway network ideal for charging infrastructure. A selection method pinpoints potential locations for charging stations and to-go chargers, leading to a bi-objective optimization model aiming to minimize costs and maximize demand coverage. The Amsterdam highway network case study illustrates the realistic charging demand scenarios derived from existing traffic data, and how it's integrated within our optimization framework for facility planning. The research highlights how early investments can significantly improve charging demand coverage.