Login

Modeling and Simulating a Green Traffic Engineering tool applied to an SDN environment

SA
State: completed by Alexander Hofmann

A network usually builds many redundant links and aggressively over-provisions link bandwidth to accommodate potential link failures and traffic bursts during peak periods. While this increase the overall QoS (Quality of Service) during peak periods, during low utilization periods it decreases the network energy efficiency. Therefore, GreenTE (Green Traffic Engineering) approaches allow to put more devices and links into sleep mode during low utilization periods. Several works try to address this problem [1-4]. However, none of the solutions is readily available as open source.

In this task, the student should describe the relevant related work towards green traffic engineering. As well as to select and to develop one of the related algorithms extending the environment described in [5], which will be available. Therefore, this task requires a background on graph theory to understand network modeling and the Python language to extend the baseline environment.

 *Level of tasks will be adjusted according to with the type of thesis.

References

[1] Zhang, Mingui, et al. "GreenTE: Power-aware traffic engineering." Network Protocols (ICNP), 2010 18th IEEE International Conference on. IEEE, 2010.

[2] Heller, Brandon, et al. "ElasticTree: Saving Energy in Data Center Networks." NSDI. Vol. 10. 2010.

[3] Agarwal, Sugam, Murali Kodialam, and T. V. Lakshman. "Traffic engineering in software defined networks." INFOCOM, 2013 Proceedings IEEE. IEEE, 2013.

[4] C. H. A. Costa, M. C. Amaral, G. C. Januário, T. C. M. B. Carvalho and C. Meirosu, "SustNMS: Towards service oriented policy-based network management for energy-efficiency," Sustainable Internet and ICT for Sustainability (SustainIT), 2012, Pisa, 2012, pp. 1-5.

[5] B. B. Rodrigues, A. C. Riekstin, G. C. Januário, V. T. Nascimento, T. C. M. B. Carvalho and C. Meirosu, "GreenSDN: Bringing energy efficiency to an SDN emulation environment," 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM), Ottawa, ON, 2015, pp. 948-953.

35% Design, 45% Implementation, 20% Documentation
Python skills

Supervisors: Dr. Bruno Rodrigues

back to the main page