Enhancing Congestion Avoidance Mechanism in Wired & Wireless Networks

This paper presents Neighborhood learning automata like (NLAL) mechanism for congestion avoidance in wired and wireless networks. The gateway and node detects incipient congestion by computing the average queue size. The gateway and node could notify connections of congestion by dropping packets arriving at the gateway and node. When the average queue size exceeds a preset threshold, the gateway drops or marks each arriving packet with a certain probability, where the exact probability is a function of queue size. Here Neighborhood Learning Automata Like Random Early Detection (NLALRED) is founded on the principles of the operations of existing LALRED congestion avoidance mechanisms along with a LAL philosophy. The primary objective of NLALRED is to optimize the value of the average size of the queue used for congestion avoidance and to consequently reduce the total loss of packets at the queue. The LAL scheme chooses the action that possesses the maximal ratio between the number of times the chosen action is rewarded and the number of times that it has been chosen. NLALRED minimizes the number of packet drops in wired & wireless networks. This approach helps to improve the performance of congestion avoidance & Throughput by adaptively minimizing the average queue size. Simulation results obtained using Network Simulator (NS2) establish the improved performance of NLALRED over the traditional RED methods. Simulations of a Transmission Control Protocol/Internet Protocol (TCP/IP) network are used to illustrate the performance of NLALRED gateway and nodes.