Mobility-Aware Throughput Prediction for Adaptive Streaming in Cellular Networks

Adaptive video streaming in cellular networks faces challenges due to the dynamic nature of network conditions, particularly in environments with varying mobility patterns. This study introduces a novel multi-stage mobility-aware throughput prediction engine (MATH-P) designed to enhance the Quality of Experience (QoE) in adaptive bitrate (ABR) streaming. MATH-P integrates a classification-driven model selection mechanism that dynamically adjusts to different mobility scenarios, such as stationary, vehicular, and high-speed mobility, allowing for precise throughput predictions. By replacing the conventional throughput estimation module in existing ABR systems with MATH-P, our experiments demonstrate significant improvements across key QoE models and streaming performance metrics across different mobility scenarios. The results highlight MATH-P's ability to deliver smoother video playback, reduced interruptions, and better overall streaming quality. The comprehensive evaluation shows that MATH-P outperforms traditional estimation methods, making it a robust solution for enhancing video streaming in mobility-rich environments.