A bandwidth delay product based modified Veno for high-speed networks: BDP-Veno

Abstract

In recent years, we have seen a significant enhancement in the performance of standard Transmission Control Protocol (TCP) congestion control algorithms. The number of packet drops and high round-trip time (RTT) are indications of network congestion. Many congestion control mechanisms have been proposed to overcome the challenge of achieving increased throughput and reduced latency. We have reviewed many TCP congestion control algorithms which are discussed in the literature. The limitation of the existing work is a trade-off between throughput, loss ratio, and delay. It is not possible for any algorithm to outperform the existing algorithm in terms of all the performance measures. We attempt to achieve the best performance while our proposed algorithm competes with CUBIC and Bottleneck Bandwidth and Round-trip propagation time (BBR). According to the observed results in the literature, TCP Veno dominates among other existing algorithms. We have proposed a bandwidth-delay product (BDP) based TCP (BDP-Veno) congestion control algorithm by modifying Veno to incorporate the information of BDP of the bottleneck. The proposed algorithm is implemented using ns-2. Moreover, we have analyzed the performances of standard TCP congestion control algorithms by considering different network scenarios. Our proposed algorithm performs better compared to other existing TCP congestion control schemes such as Reno, Newreno, BIC, CUBIC, Vegas, Veno, and Compound TCP in terms of average throughput in most of the scenarios. In Scenario 1, our proposed algorithm enhances the throughput with respect to Veno by 57%. Further, we have also compared the throughput with BBR using ns3 where we receive comparable throughput with BBR.