Multi-environment automotive QoS prediction using AI/ML
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
The evolution of wireless communications is expected to rely on machine learning (ML)-based capabilities to provide proactive management of network resources and sustain quality-of-service (QoS) and user experience. New use cases in the area of vehicular communications, including so-called vehicle-to-everything (V2X) schemes, will benefit strongly from such advances. The Berlin V2X dataset offers high-resolution wireless measurements across diverse urban environments in the city of Berlin acquired with several vehicles and mobile network operators. The captured data includes information on the vehicle location, the LTE physical layer, resource management, and quality of service. We suggest leveraging the Berlin V2X dataset to implement QoS prediction. Furthermore, we encourage the use of transfer learning and/or domain adaptation to generalize the trained algorithms across operators, vehicles, or urban areas.