DRLFcc: Deep Reinforcement Learning-empowered Congestion Control Mechanism for TCP Fast Recovery in High Loss Wireless Networks
Yuanlong Cao, Jinquan Nie, Yuehua Fan, Xun Shao, Gang Lei · 2023
TCP is currently the most widely used Internet transmission protocol, which is extensively applied to applications on the Internet to enable reliable data transmission. The TCP congestion control algorithm has a significant performance impact on all applications that use the TCP. However, traditional TCP congestion control algorithms rely on fixed feedback mechanisms, which can be challenging to adapt to complex and changing network environments and application scenarios, resulting in network performance bottlenecks. To address this issue, we design a congestion control windowing solution, DRLFcc, which is based on deep reinforcement learning and the TCP fast recovery mechanism. DRLFcc has demonstrated the ability to facilitate real-time adaptation of the congestion window to dynamic changes in network conditions while incorporating fast recovery mechanisms, thereby effectively enhancing network throughput and improving data transmission capacity recovery in high-loss wireless networks. The DRLFcc algorithm is validated in NS-3, and experimental results show an average improvement of 196% in effective throughput and a 22.4% reduction in round trip time. Compared to traditional TCP congestion control algorithms, the DRLFcc algorithm demonstrates superior performance and robustness.