Input-Rate Based Adaptive Fuzzy Neuron PID Control for AQM

Abstract

Internet routers play an important role during network congestion. All the routers have buffers at input and output ports to hold the packets at congestion. Various congestion control algorithms have been proposed to control the congestion. Recently, some proportional-integral-derivative (PID) controller based algorithms have been proposed as Active Queue Management (AQM) schemes to address performance degradations of end-to-end TCP congestion control. However, most of the proposed PID-controllers for AQM are validated for their performance and stability via intuitive explanation and simulation studies instead of theoretic analysis and performance evaluation. But there are a few drawbacks of PID-controller based AQM algorithms leading to poor performance like causing data retention dropping and oscillation when the time delay is large, which means that the existing PID-controller can not meet the Quality of Service (QoS) requirements. To overcome the drawbacks of traditional PID, we analyze and enhance the PID-controller based AQM algorithm by regarding the TCP congestion control mechanism as an input-rate based Adaptive Fuzzy Neuron PID control algorithm (IRAFNPID) to avoid congestion in TCP/AQM networks. By means of simulations, we evaluate and compare the performance of traditional PID, single neural adaptive PID(SNAPID) and IRAFNPID, simulations with experiment data analysis and find that IRAFNPID has better convergence, stability, robustness, goodput and lower loss ratio.

Simulation Model of Enhancing Performance of TCP/AQM Networks by Using Matlab

“…Jose& Mudholkar [25] used an FL controller to control congestion inside routers for TCP networks (traditional TCP-Africa algorithm) using an FL controller for queue delay. Lin et al [26] proposed to use two units of intelligent buffer overflow controllers (GAC and FLC) to optimize the performance of PIDC. The experimental results showed that GAC and FLC were more accurate and efficient than PIDC.…”

Fuzzy Like Pid Controller Based on Sso Design for Congestion Avoidance in Internet Router

“…It's been proposed that effective (AQM) give congestion warnings to senders as soon as possible, and senders may reduce transfer speeds before Overflow queue and packet loss prevent. AQM was an active research subject [1]- [5]. Several AQM techniques have been proposed for congestion avoidance.…”

“…[4]. Fan, X. L., Du, F. F., & Xie, Z. H. (2014), presented A new AQM system based on a PID controller with a fuzzy neuron algorithm that is adaptive and self-learning input rate implies an Fuzzy Neuron PID Adaptive Control algorithm Input rate dependent (IRAFNPID) [5]. Feng et al, 2014, They presented a minimal modification to RED called TRED stands for three-section random early detection based on (nonlinear RED), in which the likelihood function of packet falling is split into three parts to discriminate among Small, Medium and heavy loads in order to obtain a delay and low throughput Elevated traffic loads [6].…”