PDAA3C: An A3C-Based Multi-Path Data Scheduling Algorithm

Abstract

In this letter, a path dynamics assessment asynchronous advantage actor-critic scheduling algorithm (PDAA3C) is proposed to solve the MPTCP scheduling problem by using deep reinforcement learning Actor-Critic framework. The algorithm picks out the optimal transmitting path faster by multi-core asynchronous updating and also guarantee the network fairness. Compared with the existing algorithms, the proposed algorithm achieves 8.6% throughput gain over RLDS algorithm, and approaches the theoretic upper bound in the NS3 simulation.

PDASTSGAT: An STSGAT-Based Multipath Data Scheduling Algorithm

“…Therefore, MPTCP-PDASTSGAT achieves higher throughput. We utilize the Jain fairness index to compare the fairness of the links [12]. Figure 4…”

“…We evaluated the proposed PDASTSGAT algorithm through simulations. The results demonstrate that when there are significant performance differences among links, PDASTSGAT outperforms scheduling algorithms such as round-robin, Average-RTT, Fast-RTT, and PDAA3C [12] in terms of transmission performance. It achieves throughput improvements ranging from 8% to 14% compared to PDAA3C.…”

“…Therefore, MPTCP-PDASTSGAT achieves higher throughput. We utilize the Jain fairness index to compare the fairness of the links[12]. Figure4presents a comparison of subflow fairness values among MPTCP-RLDS, MPTCP-round-robin, MPTCP-Fastest-RTT, MPTCP-PDAA3C, and MPTCP-PDASTSGAT.…”