1
Internet Traffic Prediction Using Recurrent Neural
Networks
Mircea Eugen Dodan
1
, Quoc-Tuan Vien
1,*
and Tuan T. Nguyen
2
1
Faculty of Science and Technology, Middlesex University, United Kingdom. Email: mircea.eugen.dodan@gmail.com;
q.vien@mdx.ac.uk.
2
School of Computing and Mathematical Sciences, University of Greenwich, United Kingdom. Email:
Tuan.Nguyen@greenwich.ac.uk.
Abstract
Network traffic prediction (NTP) represents an essential component in planning large-scale networks which are in general
unpredictable and must adapt to unforeseen circumstances. In small to medium-size networks, the administrator can
anticipate the fluctuations in traffic without the need of using forecasting tools, but in the scenario of large-scale networks
where hundreds of new users can be added in a matter of weeks, more efficient forecasting tools are required to avoid
congestion and over provisioning. Network and hardware resources are however limited; and hence resource allocation is
critical for the NTP with scalable solutions. To this end, in this paper, we propose an efficient NTP by optimizing recurrent
neural networks (RNNs) to analyse the traffic patterns that occur inside flow time series, and predict future samples based
on the history of the traffic that was used for training. The predicted traffic with the proposed RNNs is compared with the
real values that are stored in the database in terms of mean squared error, mean absolute error and categorical cross
entropy. Furthermore, the real traffic samples for NTP training are compared with those from other techniques such as
auto-regressive moving average (ARIMA) and AdaBoost regressor to validate the effectiveness of the proposed method. It
is shown that the proposed RNN achieves a better performance than both the ARIMA and AdaBoost regressor when more
samples are employed.
Keywords: Internet traffic prediction; recurrent neural networks; network planning
Received on 09 June 2022, accepted on 28 August 2022, published on 02 September 2022
Copyright © 2022 Mircea Eugen Dodan et al., licensed to EAI. This is an open access article distributed under the terms of the CC
BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so
long as the original work is properly cited.
doi: 10.4108/eetinis.v9i4.1415
*
Corresponding author. Email: q.vien@mdx.ac.uk
1. Introduction
Over the last couple of decades, network traffic has become
increasingly more diverse and complex. According to [1],
the global IP traffic reached 1.2 zeta Bytes (ZB) of data
in 2016 and such trend is growing exponentially.
Considering this exponential growth in traffic, it is useful
for a network manager to have more efficient tools that
would help to make more reliable decisions in planning
future expansions of the network and consider a better
management of resources including bandwidth allocation for
certain flows while at the same time alleviating congestion
in the network [2], [3]. The forecasting of traffic is also
important in the security field, since unusual patterns in
traffic can be detected and compared with the predicted
results [4], [5], in case of botnets attacks. There are
techniques such as [6] that do not require machine learning
or artificial intelligence in order to forecast traffic, but they
are not reliable since long-term dependencies are not
considered.
Network traffic prediction (NTP) represents a branch of
network planning and capacity monitoring, that heavily
depends on a set of historical data collected throughout the
years. In order to make accurate forecasts about the future
characteristics of the flows, multiple factors need to be
considered in forecasting future traffic based on previous
EAI Endorsed Transactions
on Industrial Networks and Intelligent Systems Research Article
EAI Endorsed Transactions on
Industrial Networks and Intelligent Systems
Online First