Analysis of the increase and decrease algorithms for congestion avoidance in computer networks
Computer Networks and ISDN Systems
Scalable TCP: improving performance in highspeed wide area networks
ACM SIGCOMM Computer Communication Review
TCP-Illinois: A loss- and delay-based congestion control algorithm for high-speed networks
Performance Evaluation
Performance of competing high-speed TCP flows
NETWORKING'06 Proceedings of the 5th international IFIP-TC6 conference on Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile and Wireless Communications Systems
| Hi-index | 0.00 |
TCP provides communication service however the network congestion is one of the core issues, it occurs when a link carry so much data, and effects on delay, packet loss rate and fairness. When the available bandwidth becomes very high, TCP, as tuned today, does not perform well. Several high-speed variants of TCP have been implemented to resolve the congestion issue , such as High-Speed TCP (HSTCP), Reno and New Reno TCP, Scalable TCP (STCP), Binary Increase Congestion Control TCP (BIC TCP), CUBIC TCP, Hamilton TCP (HTCP), Compound TCP and TCP Illinois. In this research a new Quick Transport Control Protocol (QTCP) has been designed to overcome the congestion issue. This is a new congestion control mechanism based on the modifications in the slow start phase of HSTCP and AIMD. QTCP performance evaluated by the experiment and compares the QTCP average throughput ratio, bandwidth link utilization and packet loss rate in inter and intra RTTs with inter protocols. We evaluated how the link can be fairly shared and achieve end-to-end throughput for each flow. Therefore a series of experiments conducted for the evaluation of multiple high-speed flows in different configurations. The results based on NS-2 simulator shows that QTCP provides better performance compared to other transport control protocols.