In large bandwidth delay product networks, traditional TCP have the under-utilization problem. And in fixed bandwidth networks, Additive Increase Multiplicative Decrease (AIMD) algorithm causes unnecessary packet losses and retransmissions from conges...
In large bandwidth delay product networks, traditional TCP have the under-utilization problem. And in fixed bandwidth networks, Additive Increase Multiplicative Decrease (AIMD) algorithm causes unnecessary packet losses and retransmissions from congestion window increment for available bandwidth verification. Because current TCP congestion control algorithm was designed for relatively narrowband network environments, and thus its performance is inefficient for traffic transport in broadband or fixed networks. In this paper, we propose an improved TCP congestion control method that can sufficiently utilize the large available bandwidth in broadband networks and algorithm which provides stable throughput and transmission rate regardless of buffer size by limiting the TCP congestion window in fixed bandwidth networks. The proposed algorithm measures the available bandwidth by using ACK information and RTT variation, and prevents large packet losses by adjusting congestion window size appropriately. This algorithm uses not only linear method but also rapid growth phase in the congestion window. Also, it can rapidly utilize the large available bandwidth by enhancing the legacy TCP algorithm in congestion avoidance phase. In order to evaluate the performance of the proposed algorithm, we use the ns-2 simulator. The simulation results show that the proposed algorithm improves not only the utilization of the available bandwidth but also RTT fairness and the fairness between contending TCP flows better than the HSTCP in high bandwidth delay product network environment. The proposed methods maintain a TCP-compatibility property in small BDP networks, so it can use HBDP and small BDP networks without buffer and window control process.