Advanced Privacy-Preserving Data Aggregation for Accurate Traffic Flow Prediction
Tyler Nicewarner, Alex Esser, Alian Yu, Ali Ataeemh Allami, Dan Lin · 2024
With advances in autonomous vehicles and Vehicular ad-hoc networks (VANETs) technology, it is envisioned that more and more vehicles will have the capability to communicate with both their peers and roadside units. This technological advance has fostered a series of research in future intelligent transportation systems with the aim to enhance travel efficiency and reduce greenhouse gas emissions. However, for any intelligent transportation system to be widely adopted in the real world, safeguarding the privacy of participating vehicles would be a critical aspect to address. In this paper, we propose an advanced and efficient privacy-preserving data aggregation protocol that facilitates the collection and aggregation of vehicle information to conduct accurate traffic flow prediction. Our experiments have demonstrated both the efficiency and effectiveness of our approach.