Vehicular Ad Hoc Networks (VANETs) play a pivotal role in advancing Intelligent Transportation Systems (ITS), facilitating real-time communication among vehicles and infrastructure. However, VANETs face challenges arising from high mobility, dynamic topologies, and significant interference levels. This study proposes a novel cross-layer framework incorporating channel prediction and adaptive resource management to address these challenges. By leveraging a Software-Defined Radio (SDR) platform, the framework is evaluated under diverse mobility and interference conditions. Key contributions include an analysis of multi-code and multi-modulation schemes, identification of critical trade-offs in receiver diversity, and the introduction of mechanisms to optimize Quality of Service (QoS). Simulation results demonstrate significant improvements in throughput, packet delivery ratio, and network resilience, highlighting the framework’s potential for real-world applications such as autonomous vehicles and smart city communication networks. The study concludes with actionable recommendations for future research, emphasizing scalability, real-time adaptation, and hardware implementation to further enhance VANET performance.

VANET, Cross-Layer Design, Channel Prediction, QoS Optimization, Interference Management, Mobility Models