A novel adaptive traffic prediction AQM algorithm

Abstract

In the Internet, network congestion is becoming an intractable problem. Congestion results in longer delay, drastic jitter and excessive packet losses. As a result, quality of service (QoS) of networks deteriorates, and then the quality of experience (QoE) perceived by end users will not be satisfied. As a powerful supplement of transport layer (i.e. TCP) congestion control, active queue management (AQM) compensates the deficiency of TCP in congestion control. In this paper, a novel adaptive traffic prediction AQM (AT-PAQM) algorithm is proposed. ATPAQM operates in two granularities. In coarse granularity, on one hand, it adopts an improved Kalman filtering model to predict traffic; on the other hand, it calculates average packet loss ratio (PLR) every prediction interval. In fine granularity, upon receiving a packet, it regulates packet dropping probability according Z. Na ( ) School to the calculated average PLR. Simulation results show that ATPAQM algorithm outperforms other algorithms in queue stability, packet loss ratio and link utilization.

Queues with Dropping Functions and Autocorrelated Arrivals

“…In addition to such well-recognized algorithms as REM (Athuraliya et al 2001), PI (Hollot et al 2002;Wu et al 2001), BLUE (Feng et al 2002), GREEN (Wydrowski and Zukerman 2002) and AVQ (Kunniyur and Srikant 2004), several other propositions emerged recently, e.g. (Na et al 2012;Suzer et al 2012;Farzaneh et al 2013;Kahe et al 2013). The new algorithms are usually evaluated either by means of simulators (ns2, ns3), or by means of the control theory.…”

Fixed-point analysis of a network of routers with persistent TCP/UDP flows and class-based weighted fair queuing

“…Optimization of AQM parameters for various traffic scenarios has also been an active area of research; see for example [45] that studies a RED-controlled router that automatically tunes its RED parameters, and also [43] for a self-tuning proportional and integral-type feedback controller extension of the basic RED. The reference [33] uses a traffic prediction technique to decide packet drops in AQM whereas in [25], another controller design is proposed to increase the performance of AQM for TCP traffic. As stated before, we assume a certain variant of RED as the particular AQM mechanism to be used in this study although the work can be extended to more general AQM mechanisms.…”

Adaptive active queue management controller for TCP communication networks using PSO-RBF models

“…Zhenyu et al proposed an adaptive traffic prediction based AQM (AT-PAQM) algorithm [104] . NOEKF, which is the combination of the Kalman filtering model and the online noise estimation, accurately predict traffic.…”