SAM: Support Vector Machine Based Active Queue Management
This work addresses network congestion control for varying loads, delays, and bandwidth, but it appears incremental as it applies an existing machine learning method (SVM) to a known problem in AQM.
The authors tackled network congestion management by proposing a new Active Queue Management (AQM) controller called SAM, which uses Support Vector Machine (SVM) with RBF kernel for training, and found it to be more efficient in controlling queue size compared to conventional controllers like Random Early Detection, Blue, and Proportional Plus Integral Controller.
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.