The Internet traffic pattern is quite fluctuating since there
are many users who share the same resource [1], [2]. A goal
of Traffic Engineering (TE) is how to use the network
resources effectively e.g. using intelligent routing or/and
load-balancing algorithms for avoiding congested paths [2].
This results in providing a better throughput and service
quality. The internet traffic pattern is needed to train the
intelligent routing, classification, or load balancing built on
a neural network [3], [4] or a neuro-fuzzy [2]. Therefore,
this paper presents the Internet traffic pattern, which is
essential for an Intelligent TE tool, e.g. load balancing, in
order to improve the quality service for the real-time
applications or telemedicine over the Internet.