Rights statement: The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-70139-4_6 © Springer International Publishing AG 2017
Accepted author manuscript, 181 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Modeling Server Workloads for Campus Email Traffic Using Recurrent Neural Networks
AU - Boukoros, Spyros
AU - Nugaliyadde, Anupiya
AU - Marnerides, Angelos
AU - Vassilakis, Costas
AU - Koutsakis, Polychronis
AU - Wai Wong, Kok
N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-70139-4_6 © Springer International Publishing AG 2017
PY - 2017/11/14
Y1 - 2017/11/14
N2 - As email workloads keep rising, email servers need to handle this explosive growth while offering good quality of service to users. In this work, we focus on modeling the workload of the email servers of four universities (2 from Greece, 1 from the UK, 1 from Australia). We model all types of email traffic, including user and system emails, as well as spam. We initially tested some of the most popular distributions for workload characterization and used statistical tests to evaluate our findings. The significant differences in the prediction accuracy results for the four datasets led us to investigate the use of a Recurrent Neural Network (RNN) as time series modeling to model the server workload, which is a first for such a problem. Our results show that the use of RNN modeling leads in most cases to high modeling accuracy for all four campus email traffic datasets.
AB - As email workloads keep rising, email servers need to handle this explosive growth while offering good quality of service to users. In this work, we focus on modeling the workload of the email servers of four universities (2 from Greece, 1 from the UK, 1 from Australia). We model all types of email traffic, including user and system emails, as well as spam. We initially tested some of the most popular distributions for workload characterization and used statistical tests to evaluate our findings. The significant differences in the prediction accuracy results for the four datasets led us to investigate the use of a Recurrent Neural Network (RNN) as time series modeling to model the server workload, which is a first for such a problem. Our results show that the use of RNN modeling leads in most cases to high modeling accuracy for all four campus email traffic datasets.
KW - Email Traffic
KW - Model Server Workload
KW - Recurrent Neural Network
KW - Time Series Modeling
U2 - 10.1007/978-3-319-70139-4_6
DO - 10.1007/978-3-319-70139-4_6
M3 - Conference contribution/Paper
SN - 9783319701387
T3 - Lecture Notes in Computer Science
SP - 57
EP - 66
BT - Neural Information Processing. ICONIP 2017
A2 - Liu, D.
A2 - Xie, S.
A2 - Li, Y.
A2 - Zhou, D.
A2 - El-Alfy, E.S.
PB - Springer
CY - Cham
ER -