Proactive URLLC Adaptation for Connected Vehicles Through ML-Based Channel Prediction
For connected vehicle URLLC systems, this work demonstrates that ML prediction can enhance service reliability and robustness, but it is an incremental application of existing methods to a specific vehicular scenario.
This paper investigates ML-based channel prediction for proactive URLLC adaptation in connected vehicles, showing that DNN and LSTM models significantly outperform past-measurement-based approaches and approach ideal perfect-knowledge performance in realistic urban simulations.
Connected and automated vehicles (CAVs) are expected to increasingly rely on 5G and future 6G ultra-reliable and low-latency communication (URLLC) services to support safety-critical and time-sensitive applications. Since wireless link conditions can vary rapidly in urban vehicular environments, proactively adapting service parameters based on future channel conditions is essential to maintain service continuity and reliability. In this paper, we investigate the use of machine learning (ML) techniques for channel quality prediction in vehicular URLLC scenarios. Specifically, we evaluate deep neural network (DNN) and long short-term memory (LSTM) models to forecast future channel conditions and enable proactive service adaptation with minimized performance degradation. The analysis is conducted using realistic simulations combining the SUMO traffic simulator and the Sionna-RT ray-tracing framework in a real urban environment reconstructed from OpenStreetMap data. Results show that ML-based prediction significantly outperforms approaches relying solely on past channel measurements and achieves performance close to the ideal case in which future channel conditions are perfectly known in advance. These findings demonstrate the potential of ML-driven prediction techniques to enhance the reliability and robustness of URLLC services for connected vehicular systems.