An improvement over RED algorithm by using particle swarm optimization

One of the most challenging issues in Random Early Detection (RED) algorithm is how to set its parameters to achieve high performance for the dynamic conditions of the network. While original RED uses fixed values for its parameters, this paper proposes a novel algorithm, in which particle swarm optimization (PSO) technique is used to dynamic tuning of RED's parameters. For this purpose, we formulate the active queue management issue as an optimization problem to be solved by PSO algorithm. Then, we employ PSO technique to direct the system to its optimum point. Simulation results show that the proposed algorithm behaves remarkably better than RED in terms of queue size, number of dropped packets, bottleneck utilization and global stability.