查看文章

Over the years, efforts have been made by various researchers to optimize Wireless area network enterprise to improve network performance with reduced cost. With necessary and appropriate network control and monitoring methods, reliable QoS of network traffic can be achieved which in turn would improve connections especially with high reliance of today businesses and commercial enterprises on fast internet. Moreover, the need for efficient network monitoring to improve quality of services have driven many companies to employ Multiprotocol Label Switching circuit for connectivity to see how to have control over traffic flow to and from branch offices in order to achieve QoS with optimize WAN enterprise. In this paper, machine learning algorithms with various backpropagation algorithms are analysed for effective network traffic control and monitoring. Specifically, the paper analyze the impact of neural network approach with various network parameters to improved network quality of service (QoS). In this case, ten different Back-propagation training algorithms were used to carryout ten different training attempts in order to determine the algorithms with the best performance. The result showed that there is a perfect correlation between the predicted values of the neural network model and the target output which implies that the model was successful in the prediction of the network traffic flow. The result also confirmed that the training algorithm of Back-Propagation was sufficient for predicting network traffic flow using the BR algorithms.