Link Congestion Prediction using Machine Learning for Software-Defined-Network Data Plane
Junying Wu, Yunfeng Peng, Meng Qing Song, Manman Cui, Liang Zhang · 2019
This paper presented a machine learning method to reduce link congestion for Software-Defined Network (SDN). The updated status of switches and links are collected using the SDN southbound interface to train four popular machine learning algorithms to predict network congestion degree. Simulations show that the one-dimensional convolutional neural network algorithm outperforms the other three.