Deep Adaptive Rate Allocation in Volatile Heterogeneous Wireless Networks

TL;DR

This paper introduces DARA, a deep reinforcement learning-based multipath scheduler that improves data transfer and streaming quality in highly volatile vehicular wireless networks by forecasting link states and dynamically allocating rates.

Contribution

It presents a novel deep adaptive rate allocation scheduler integrating Transformer-based forecasting with reinforcement learning for real-time multipath data management.

Findings

DARA outperforms existing schedulers in file transfer times.

Resolution quality in streaming is maintained across conditions.

Significant reduction in rebuffering during burst scenarios.

Abstract

Modern multi-access 5G+ networks provide mobile terminals with additional capacity, improving network stability and performance. However, in highly mobile environments such as vehicular networks, supporting multi-access connectivity remains challenging. The rapid fluctuations of wireless link quality often outpace the responsiveness of existing multipath schedulers and transport-layer protocols. This paper addresses this challenge by integrating Transformer-based path state forecasting with a new multipath splitting scheduler called Deep Adaptive Rate Allocation (DARA). The proposed scheduler employs a deep reinforcement learning engine to dynamically compute optimal congestion window fractions on available paths, determining data allocation among them. A six-component normalised reward function with weight-mediated conflict resolution drives a DQN policy that eliminates the observation-reaction lag inherent in reactive schedulers. Performance evaluation uses a Mininet-based Multipath Datagram Congestion Control Protocol testbed with traces from mobile users in vehicular environments. Experimental results demonstrate that DARA achieves better file transfer time reductions compared to learning-based schedulers under moderate-volatility traces. For buffered video streaming, resolution improvements are maintained across all tested conditions. Under controlled burst scenarios with sub-second buffer constraints, DARA achieves substantial rebuffering improvements whilst state-of-the-art schedulers exhibit near-continuous stalling.