A High-Resolution Dataset for Machine Learning-Based Link Adaptation in Urban NLOS Vehicular Networks

The advancement of machine learning (ML)-driven link adaptation (LA) in Vehicular Ad HocNetworks (VANETs) is fundamentally constrained by the absence of high-fidelity, publicly available datasetscontaining synchronized physical-layer (PHY) and mobility measurements. While existing VANET datasetspredominantly capture application layer or macroscopic traffic metrics, they critically lack the per-packetchannel state information (CSI), signal-to-noise ratio (SNR), Doppler dynamics, and interferencecharacteristics essential for training robust, real-time LA models. To bridge this gap, we present VANETLA,a novel high-resolution dataset explicitly engineered for ML-based link adaptation research in urban nonline-of-sight (NLOS) scenarios. The dataset is generated through a physics-informed methodology alignedwith IEEE 802.11p standards, accurately capturing dominant impairments including time-varying Dopplerspread (0–1500 Hz), multipath delay dispersion (0–1 μs), inter-carrier interference (ICI), and outage-constrainedfading while enforcing conservative, mobility-aware modulation and coding scheme (MCS)selection under hysteresis and effective bandwidth constraints reflective of real-world congestion control.The resulting dataset comprises 320 balanced samples spanning nine critical features (bandwidth, SNR,Doppler shift, delay spread, MCS index, modulation order, code rate, PER, and throughput), with deliberateclass balancing to eliminate representation bias inherent in raw simulation outputs. Rigorous validationconfirms the dataset's physical credibility through consistent relationships between channel impairments andlink performance metrics under diverse urban NLOS mobility conditions. By providing synchronized, fine-grainedPHY-layer measurements with explicit mobility context, VANET-LA establishes a reproduciblefoundation for developing, benchmarking, and deploying data-driven LA strategies that enhance reliabilityand spectral efficiency in safety-critical vehicular communications.