Financial-Oriented Controller Placement Problem for Software-Defined Networks
Abstract
Controller placement problems seek to spatially position the controllers of a software-defined network (SDN) and choose the links that will serve them. These problems are NP-Hard. In this work, we propose a new formulation focused on long distance networks based on minimizing the financial costs of network maintenance. Our modeling still limits latency within the network and avoids controller overloading. The decision version of our formulation as NP-Complete has been proven. An exact algorithm for offline network structuring and a set of distributed heuristics for runtime topology adaptation were created. The heuristic results reach about 5% over the optimal cost within the simulated test cases. Therefore, the proposed solution can lead to financial savings for maintaining long distance SDN networks.
References
Glpk: Gnu linear programming kit. www.gnu.org/ software/glpk. [Online accessada 23-05-2018].
Guedes, D., Vieira, L., Vieira, M., Rodrigues, H., and Nunes, R. V. (2012). Redes definidas por software: uma abordagem sistêmica para o desenvolvimento de pesquisas em redes de computadores. Minicursos do Simpósio Brasileiro de Redes de Computadores-SBRC 2012, 30(4):160–210.
Heller, B., Sherwood, R., and McKeown, N. (2012). The controller placement problem. In Proceedings of the first workshop on Hot topics in software defined networks, pages 7–12. ACM.
Hu, Y.,Wang,W., Gong, X., Que, X., and Cheng, S. (2014). On reliabilityoptimized controller placement for software-defined networks. China Communications, 11(2):38–54.
Jain, S., Kumar, A., Mandal, S., Ong, J., Poutievski, L., Singh, A., Venkata, S.,Wanderer, J., Zhou, J., Zhu, M., et al. (2013). B4: Experience with a globallydeployed software defined wan. In ACM SIGCOMM Computer Communication Review, volume 43, pages 3–14. ACM.
Jouet, S. and Pezaros, D. P. (2017). Bpfabric: Data plane programmability for software defined networks. In Proceedings of the Symposium on Architectures for Networking and Communications Systems, pages 38–48. IEEE Press.
Kao, M.-J., Chen, H.-L., and Lee, D.-T. (2015). Capacitated domination: Problem complexity and approximation algorithms. Algorithmica, 72(1):1–43.
Koomey, J. (2011). Growth in data center electricity use 2005 to 2010. www.analyticspress.com/datacenters.html. Analytics Press. July.
McKeown, N., Anderson, T., Balakrishnan, H., Parulkar, G., Peterson, L., Rexford, J., Shenker, S., and Turner, J. (2008). Openflow: enabling innovation in campus networks. ACM SIGCOMM, 38(2):69–74.
Robusto, C. C. (1957). The cosine-haversine formula. The American Mathematical Monthly, 64(1):38–40.
Ruiz-Rivera, A., Chin, K.-W., and Soh, S. (2015). Greco: An energy aware controller association algorithm for software defined networks. IEEE communications letters, 19(4):541–544.
Wang, G., Zhao, Y., Huang, J., andWang,W. (2017). The controller placement problem in software defined networking: a survey. IEEE Network, 31(5):21– 27.
Zhang, B.,Wang, X., Ma, L., and Huang, M. (2016). Optimal controller placement problem in internet-oriented software defined network. In Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2016 International Conference on, pages 481–488. IEEE.
