Authors
1 Informatics Institute for Postgraduate Studies, University of Information Technology and Communications,
2 Informatics Institute for Postgraduate Studies, University of Information Technology and Communications, Iraqi Commission for Computers & Informatics
Abstract
monitoring the behavior of computer networks is essential for
problem identification and optimal management. Part of this behavior to be
monitored is the utilization of the network bandwidth. Several techniques are
used to model and forecast network traffic such as time series models, modern
data mining techniques, soft computing approaches, and neural networks are
used for network traffic analysis and prediction. Efficient bandwidth utilization
and optimization are very interesting research issues in effective networks
because bandwidth is one of the most required and expensive Internet
components needed today. It is generally known that the higher the bandwidth
available, the better the network performance, thus an essential aid for network
design and bandwidth wastage control and a need for traffic models which can
capture the characteristics is necessary. In this paper, a time series prediction
models were proposed for LAN office network bandwidth utilization. The
proposed prediction models are tested by using evaluation metrics used in time
series such as MSE and performance evaluation plot. Testing results show that
the proposed models can enhance the detection of bandwidth traffic and provide
an efficient tool for bandwidth utilization.
Keywords
)