Discrete TCP: Differentiating Slow Start and Congestion Avoidance

Abstract

Deployment of wireless links (terrestrial and satellite) along with wired links has made extension of the Internet even in remote places feasible. TCP/IP protocol suite is an integral part of the Internet. Congestion control of TCP plays a vital role in the performance of the Internet. TCP's unconditional flow control in case of a packet loss has always been a concern for researchers. Further, halving congestion window in such conditions without taking in to account the current network state is also considered inappropriate. The problem is compounded in wireless networks where packet losses occur often due to channel errors rather than the shortfall in the available bandwidth. In this situation, TCP's conservative behaviour underutilises the bandwidth. We therefore, propose a scheme to address the issue of underutilization of network resources. The proposed approach, Discrete TCP (DTCP), differentiates slow start and congestion avoidance phases while tuning data flow over a transport connection. DTCP evaluates ssthresh and cwnd before setting up parameters, based on the existing network condition to enhance the performance. The proposed scheme is compared and analyzed with various existing schemes with the help of extensive simulations using ns2. Results of simulation based experiments indicate significant performance improvement of DTCP on erroneous links and in heterogeneous networks and confirm its suitability.

A Survey of End-to-End Solutions for Reliable Low-Latency Communications in 5G Networks

“…Google LLC [85] presents a congestion control algorithm (TCP bottleneck bandwidth and round-trip propagation time) that responds to the actual congestion rather than the packet loss and thus improves the throughput, latency and quality of experience. Gambhava et al [86] present a discrete TCP (DTCP), an enhancement that differentiates slow start and congestion avoidance phases while tuning the data flow over a transport connection, resulting in an improvement in TCP performance in heterogeneous networks. Zhu et al [87] present a TCP optimization using radio awareness which yields a significant gain in both latency and throughput setting parameters of the TCP layer and modifying the TCP congestion control mechanism according to the cross-layer information.…”

“…Additionally, there are research efforts on congestion and rate control enhancements: SCReAM [93] is a windowbased and byte-oriented congestion control protocol for RTP streams that achieves improvements in both video latency and throughput in real-time communications thanks to its adaptation ability, whereas Mittal et al [94] propose a framework for rate control with the similar objective of improving the throughput and latency. Finally, there exists a work aiming to [80] DP Mgmt: Retransmission TCP-ROME [81] Scheduling: Paths TCP VEGAS* [82] DP Mgmt: Congestion Control TCP 5G mmWave Networks [83] Ctxt Awa: Cross-layer DP Mgmt: Retransmission Advanced 5G-TCP [84] DP Mgmt: Congestion Control TCP BBR [85] DP Mgmt: Congestion Control Gambhava et al [86] DP Mgmt: Congestion Control Zhu et al [87] Ctxt Awa: Cross-layer DP Mgmt: Congestion Control Luo et al [88] DP Mgmt: Congestion Control ASAP [89] Ctxt Awa: Cross-layer STRP [90] DP Mgmt: Retransmission…”