CLTCP: An Adaptive TCP Congestion Control Algorithm Based on Congestion Level

The Transmission Control Protocol (TCP) has been profusely used by diverse applications such as FTP, email, and HTTP. In recent decades, numerous TCP variants have been developed to fit the fast increasing of network capacities and improve the performance of TCP algorithms in various scenarios, particularly in the high-bandwidth-delay-product (high-BDP) and lossy networks. Although the performance improvements are different for different TCP under different networking conditions, implementing a new congestion control algorithm that is suitable for a wide range of network conditions is still a challenge. In this letter, we propose a novel scheme, i.e., the congestion-level-based TCP (CLTCP), which could perform effectively in both high-BDP and lossy networks. Different from the TCP-FIT, the CLTCP does not use the delay variation but the congestion level as a signal to control the number of virtual parallel flows in a TCP connection. This could avoid the influence of the delay measurement error in the TCP-FIT. Extensive experiments in NS-2 show that the performance of the CLTCP is significantly improved, as compared to other state-of-the-art algorithms, while maintaining good fairness.