![]() | Only 14 pages are availabe for public view |
Abstract Today, most of the Internet applications are based on the Transmission Control Protocol (TCP). However, with the increasing number and variety of Internet applications, congestion becomes a key issue. Generally, congestion problem occurs when the traffic load increases. This problem decreases network utilization and increases traffic delay. Therefore, the stability of the internet depends on the TCP congestion control. Due to the serious effectiveness of congestion problem in the Internet performance, congestion control has the most concern in the network community. Several End-to-End mechanisms were developed to overcome this problem. However, most of the existing mechanisms adapt the sending rate at the sender, when detecting congestion, without considering the network status. This behavior degrades the Internet performance because congestion is happen. Hence, an intelligent congestion control is required to avoid the mentioned problem. This thesis presents a new intelligent control technique, called fuzzy controller or Fuzzy logic, to adjust the sending rate at the sender dynamically based on the network load. The intended controller is employed to enhance the existing TCPvarients and TCP-Vegas in order to avoid congestion. Nevertheless, the main challenge in utilizing fuzzy controller is how to choice the number of membership functions. Two different cases as considered: the first case employs 3- memberships while the second case employs 5-memberships. The performance of the proposed controller is evaluated by using the well-known Network Simulator NS-2 considering a simple network and the AT&T real network. The results are compared with the most recent protocols. The results indicate that the proposed controller increases the throughput and decreases both the packet loss and packet delay. Fathur, a greater performance is achieved with a large number of membership functions. Keywords: Congestion Control, Congestion avoidance, |