SAM: Support Vector Machine Based Active Queue Management

TL;DR

This paper introduces SAM, an SVM-based active queue management controller that effectively manages network congestion and outperforms traditional controllers in queue size regulation.

Contribution

The paper presents a novel SVM-based AQM controller called SAM, trained with RBF kernel, demonstrating improved efficiency over conventional methods.

Findings

SAM controls queue size more efficiently than traditional AQM controllers.

Simulation results show SAM's performance is comparable to existing controllers.

SAM is trained using SVM with RBF kernel for network congestion management.

Abstract

Recent years have seen an increasing interest in the design of AQM (Active Queue Management) controllers. The purpose of these controllers is to manage the network congestion under varying loads, link delays and bandwidth. In this paper, a new AQM controller is proposed which is trained by using the SVM (Support Vector Machine) with the RBF (Radial Basis Function) kernal. The proposed controller is called the support vector based AQM (SAM) controller. The performance of the proposed controller has been compared with three conventional AQM controllers, namely the Random Early Detection, Blue and Proportional Plus Integral Controller. The preliminary simulation studies show that the performance of the proposed controller is comparable to the conventional controllers. However, the proposed controller is more efficient in controlling the queue size than the conventional controllers.