Congestion Control Scheme Performance Analysis Based on Nonlinear RED

Congestion control has become a research focus with the development of network communication technology. Random early detection (RED) for queue management techniques is the most effective method. However, RED is particularly sensitive to the traffic load and the parameters of the scheme itself. When the traffic load is low, the bandwidth is underutilized, whereas when the traffic load is high, the delay is large. This paper presents a minimal adjustment to RED called three-section random early detection (TRED) based on nonlinear RED, in which the packet dropping probability function is divided into three sections to distinguish between light, moderate, and high loads to achieve a tradeoff in the delay and the throughput between low and high traffic loads. The NS2 simulation results show that TRED effectively improves the insufficiencies of RED to achieve better congestion control.

System Architecture
Project Overview : This paper presents a minimal adjustment to RED called three-section random early detection (TRED) based on nonlinear RED, in which the packet dropping probability function is divided into three sections to distinguish between light, moderate, and high loads to achieve a tradeoff in the delay and the throughput between low and high traffic loads.

System Requirements
Hardware Requirement
Main processor : Pentium IV processor 1.13 GHz
Hard disk capacity : 40GB
Cache memory : 512 MB
Monitor : LG Digital Color Monitor
Keyboard : Samsung
Mouse : Logitech

Software Requirement
Operating system : Fedora 8 (linux)
Scripting language : Network Simulator 2.33
Protocol developed : C++
Scripting : Tool Command Language