Abstract:For the problem that the active queue managements(AQM’s) parameters configuration is difficult, especially in
the dynamic network, an adaptive AQM algorithm (called NFL) is proposed, which is composed of two main parts: the fuzzy AQM and the active-flow estimation strategy. Considering the tradeoff among each performance indicators, a set of fuzzy rules are built for NFL to adapt to the dynamic network situation. Furthermore, an optimization method is raised, which reduces the computational complexity of fuzzy AQM. Then, a stateless active-flow estimation strategy baesd on Bloom filter is introduced to capture network congestion status. According to this, an output gain compensator for fuzzy AQM in accordance with active-flow-number parameter is proposed. Simulation results show that NFL is adaptive to dynamic network with fast convergence rate and stable steady-state queue control performance, and the comprehensive performance of NFL is more excellent than other AQM algorithms.