Adaptive random early detection algorithm based on network traffic level grade prediction

Abstract

In view of the problem that the calculation of average queue length and maximum packet drop probability in random early detection algorithm and its variants reflect the changes of network traffic slowly, an adaptive random early detection algorithm based on network traffic level grade prediction was proposed.Based on the statistical characteristics of self-similar network traffic, the transition probability table of network traffic level grade was established, and a grade prediction method of self-similar network traffic level with low complexity and high accuracy was proposed.Furthermore, the prediction results were applied to calculate the average queue length in equal interval and adjust the maximum packet drop probability.Under the condition of fixed and variable bottleneck link capacity, it is found that regardless of the degree of self-similarity of network traffic, the proposed algorithm can improve the throughput and packet loss rate, especially when the Hurst parameter is large and the traffic is light.

Keywords

• active queue management;network traffic;self-similar;traffic level grade prediction