|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
Analytical Modeling Of Rate-Based Overload Control With
Token Bucket Traffic Shaping On Client Side |
Authors: |
Konstantin Samouylov, Yulia V. Gaidamaka, Pavel O. Abaev, Margarita Talanova, Oleg Pavlotsky |
Published in: |
(2015).ECMS 2015 Proceedings edited
by: Valeri M. Mladenov, Grisha Spasov, Petia Georgieva, Galidiya Petrova, European
Council for Modeling and Simulation. doi:10.7148/2015 ISBN:
978-0-9932440-0-1 29th
European Conference on Modelling and Simulation, Albena (Varna), Bulgaria,
May 26th – 29th,
2015 |
Citation
format: |
Konstantin Samouylov,
Yulia V. Gaidamaka, Pavel O. Abaev, Margarita Talanova, Oleg Pavlotsky
(2015). Analytical Modeling Of Rate-Based Overload Control With Token Bucket
Traffic Shaping On Client Side, ECMS 2015 Proceedings edited by: Valeri M. Mladenov, Petia Georgieva, Grisha Spasov, Galidiya Petrova European
Council for Modeling and Simulation. doi:10.7148/2015-0669 |
DOI: |
http://dx.doi.org/10.7148/2015-0669 |
Abstract: |
Providing multimedia services to users
assumes perfect quality of transfer and modern processing equipment that
involves need of development of new methods of the analysis and forecasting
of functioning of a communication network. In the paper we investigate the
problem of the overload that occurs on a SIP (Session Initiation Protocol)
server. SIP overload mitigation is based on RBOC (Rate-based overload
control) schema, which was designed by IETF SIP overload control workgroup.
The aim of RBOC schema is to restrict signaling message flow rate from the client
side towards the server side. Hysteretic overload control
algorithm is used to define trigger point for sending control information by
the server to the client. Token bucket algorithm is applied to
restrict the number of the tokens that the server grants the client.
Simulation model for estimation main performance metrics is developed.
Traffic with different type of distribution is used for investigation the
behavior of the system with tandem servers. The optimization problem for
maximization of processor utilization of SIP server on the dependence of
threshold values and the number of token is formulated. |
Full
text: |