基于深度确定性策略梯度的MPTCP数据调度算法  

韩佳龙 滕建霖  

西南民族大学计算机与人工智能学院，四川成都，610225；  

摘要：多路径TCP（MPTCP）是由互联网工程任务组设计的多路径传输协议，允许设备使用多个路径并行传输数据。数据调度算法负责按照调度规则将数据分配给不同路径传输。研究证明，数据调度算法对MPTCP的传输性能有很大影响。现有调度算法在动态、异构网络环境下存在一定的局限性，没有解决乱序数据包数量问题，且大多算法只能提高MPTCP的一种传输性能。针对上述问题，通过将深度确定性策略梯度引入数据调度问题，使算法适应复杂的网络环境，并通过多目标奖励函数提升多个传输性能。实验证明，改进后的算法在乱序数据包数量、吞吐量和往返时延等方面皆优于对比调度算法。  

关键词：MPTCP；数据调度算法；深度确定性策略梯度  

参考文献

[1]C. Paasch, S. Ferlin, O. Alay, and O. Bonaventure, “Experimental evaluation of multipath tcp schedulers,” in Proceedings of the 2014 ACM SIGCOMM workshop on Capacity sharing workshop, 2014, pp. 27–32.

[2]S. Ferlin, ¨O. Alay, O. Mehani, and R. Boreli, “Blest: Blocking estimation-based mptcp scheduler for heterogeneous networks,” in 2016 IFIP networking conference (IFIP networking) and workshops. IEEE,

[3]H. Wu, O. Alay, A. Brunstrom, S. Ferlin, and G. Caso, “Peekaboo: Learning-based multipath scheduling for dynamic heterogeneous environments,” IEEE J. Sel. Areas Commun., vol. 38, no. 10, pp. 2295–2310, Oct. 2021.

[4]Kumar, P.S., Saxena, P., Alay, Ö. (2024). DEAR: DRL Empowered Actor-Critic Scheduler for Multipath QUIC Under 5G/B5G Hybrid Networks. In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2024. Lecture Notes on Data Engineering and Communications Technologies, vol 199. Springer, Cham.