A novel adaptive traffic prediction AQM algorithm |
| |
Authors: | Zhenyu Na Qing Guo Zihe Gao Jiaqi Zhen Changyu Wang |
| |
Affiliation: | 1. School of Information Science and Technology, Dalian Maritime University, Dalian, China 2. Communication Research Center, Harbin Institute of Technology, Harbin, China 3. Information and Communication Engineering College, Harbin Engineering University, Harbin, China 4. Department of Information Countermeasure, Aviation University of Air Force, Changchun, China
|
| |
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 (ATPAQM) 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
to the calculated average PLR. Simulation results show that ATPAQM algorithm outperforms other algorithms in queue stability,
packet loss ratio and link utilization. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|