Skip to main content
main-content
Top

Hint

Swipe to navigate through the articles of this issue

Published in: Photonic Network Communications 3/2020

10-07-2020 | Original Paper

Virtualized controller placement for multi-domain optical transport networks using machine learning

Authors: Sabidur Rahman, Tanjila Ahmed, Sifat Ferdousi, Partha Bhaumik, Pulak Chowdhury, Massimo Tornatore, Goutam Das, Biswanath Mukherjee

Published in: Photonic Network Communications | Issue 3/2020

Login to get access
share
SHARE

Abstract

Optical multi-domain transport networks are often controlled by a hierarchical distributed architecture of controllers. Optimal placement of these controllers is very important for efficient management and control. Traditional SDN controller placement methods focus mostly on controller placement in datacenter networks. But the problem of virtualized controller placement for multi-domain transport networks needs to be solved in the context of geographically distributed heterogeneous multi-domain networks. In this context, edge datacenters have enabled network operators to place virtualized controller instances closer to users, besides providing more candidate locations for controller placement. In this study, we propose a dynamic controller placement method for optical transport networks that considers the heterogeneity of optical controllers, resource limitations at edge hosting locations, and latency requirements. We also propose a machine-learning framework that helps the controller placement algorithm with proactive prediction (instead of traditional reactive threshold-based approach). Simulation studies, considering practical scenarios and temporal variation of load, show significant cost savings compared to traditional placement approaches.
Literature
1.
go back to reference Wang, G., et al.: The controller placement problem in software defined networking: a survey. IEEE Netw. 31(5), 21–27 (2017) CrossRef Wang, G., et al.: The controller placement problem in software defined networking: a survey. IEEE Netw. 31(5), 21–27 (2017) CrossRef
2.
go back to reference Alvizu, R., et al.: Comprehensive survey on T-SDN: software-defined networking for transport networks. IEEE Commun. Surv. Tutor. 19(4), 2232–2283 (2017) CrossRef Alvizu, R., et al.: Comprehensive survey on T-SDN: software-defined networking for transport networks. IEEE Commun. Surv. Tutor. 19(4), 2232–2283 (2017) CrossRef
3.
go back to reference Lopez, V., et al.: Control plane architectures for elastic optical networks. J. Opt. Commun. Netw. 10(2), 241–249 (2018) CrossRef Lopez, V., et al.: Control plane architectures for elastic optical networks. J. Opt. Commun. Netw. 10(2), 241–249 (2018) CrossRef
4.
go back to reference Muñoz, R., et al.: Integrated SDN/NFV management and orchestration architecture for dynamic deployment of virtual SDN control instances for virtual tenant networks. J. Opt. Commun. Netw. 7(11), 62–70 (2015) CrossRef Muñoz, R., et al.: Integrated SDN/NFV management and orchestration architecture for dynamic deployment of virtual SDN control instances for virtual tenant networks. J. Opt. Commun. Netw. 7(11), 62–70 (2015) CrossRef
5.
go back to reference Rahman, S., et al.: Dynamic workload migration over optical backbone network to minimize data center electricity cost. IEEE Trans. Green Commun. Netw. 2(2), 570–579 (2017) CrossRef Rahman, S., et al.: Dynamic workload migration over optical backbone network to minimize data center electricity cost. IEEE Trans. Green Commun. Netw. 2(2), 570–579 (2017) CrossRef
6.
go back to reference Heller, B. et al.: The controller placement problem. In: Proc. 1st Wksp. Hot topics in software defined networks, pp. 7–12 (2012) Heller, B. et al.: The controller placement problem. In: Proc. 1st Wksp. Hot topics in software defined networks, pp. 7–12 (2012)
7.
go back to reference Yao, G., et al.: On the capacitated controller placement problem in software defined networks. IEEE Commun. Lett. 18(8), 1339–1342 (2014) CrossRef Yao, G., et al.: On the capacitated controller placement problem in software defined networks. IEEE Commun. Lett. 18(8), 1339–1342 (2014) CrossRef
8.
go back to reference Kim, W., et al.: T-DCORAL: a threshold-based dynamic controller resource allocation for elastic control plane in software-defined data center networks. IEEE Commun. Lett. 23(2), 198–201 (2018) CrossRef Kim, W., et al.: T-DCORAL: a threshold-based dynamic controller resource allocation for elastic control plane in software-defined data center networks. IEEE Commun. Lett. 23(2), 198–201 (2018) CrossRef
9.
go back to reference Potluri, A., et al.: An efficient DHT-based elastic SDN controller. In: Proceedings of 9th International Conference on Communication Systems and Networks, pp. 267–273 (2017) Potluri, A., et al.: An efficient DHT-based elastic SDN controller. In: Proceedings of 9th International Conference on Communication Systems and Networks, pp. 267–273 (2017)
10.
go back to reference Rahman, S., et al.: Virtualized controller placement for multi-domain optical transport networks. In: ONDM (2019) Rahman, S., et al.: Virtualized controller placement for multi-domain optical transport networks. In: ONDM (2019)
11.
go back to reference Sallahi, A., et al.: Optimal model for the controller placement problem in software defined networks. IEEE Commun. Lett. 19(1), 30–33 (2015) CrossRef Sallahi, A., et al.: Optimal model for the controller placement problem in software defined networks. IEEE Commun. Lett. 19(1), 30–33 (2015) CrossRef
12.
go back to reference Savas, S.S., et al.: Disaster-resilient control plane design and mapping in software-defined networks. In: Proceedings of the 16th IEEE International Conference on High Performance Switching and Routing (2015) Savas, S.S., et al.: Disaster-resilient control plane design and mapping in software-defined networks. In: Proceedings of the 16th IEEE International Conference on High Performance Switching and Routing (2015)
13.
go back to reference Aguado, A., et al.: ABNO: a feasible SDN approach for multivendor IP and optical networks. IEEE/OSA J. Opt. Commun. Netw. 7(2), A356–A362 (2015) CrossRef Aguado, A., et al.: ABNO: a feasible SDN approach for multivendor IP and optical networks. IEEE/OSA J. Opt. Commun. Netw. 7(2), A356–A362 (2015) CrossRef
14.
go back to reference Lourenco, R.B., et al.: Robust hierarchical control plane for transport software-defined networks. Opt. Switch. Netw. 30, 10–22 (2018) CrossRef Lourenco, R.B., et al.: Robust hierarchical control plane for transport software-defined networks. Opt. Switch. Netw. 30, 10–22 (2018) CrossRef
15.
go back to reference Oliveira, T.P., et al.: Computer network traffic prediction: a comparison between traditional and deep learning neural networks. Int. J. Big Data Intell. 3(1), 28–37 (2016) CrossRef Oliveira, T.P., et al.: Computer network traffic prediction: a comparison between traditional and deep learning neural networks. Int. J. Big Data Intell. 3(1), 28–37 (2016) CrossRef
16.
go back to reference Rahman, S., et al.: Auto-scaling VNFs using machine learning to improve QoS and reduce cost. In: Proceedings of the IEEE International Conference on Communication (2018) Rahman, S., et al.: Auto-scaling VNFs using machine learning to improve QoS and reduce cost. In: Proceedings of the IEEE International Conference on Communication (2018)
17.
go back to reference Bhamare, D., et al.: Models and algorithms for centralized control planes to optimize control traffic overhead. Comput. Commun. 70(1), 68–78 (2015) CrossRef Bhamare, D., et al.: Models and algorithms for centralized control planes to optimize control traffic overhead. Comput. Commun. 70(1), 68–78 (2015) CrossRef
18.
go back to reference Rahman, S., et al.: Dynamic workload migration over optical backbone network to minimize data center electricity cost. IEEE Trans. Green Commun. Netw. 2(2), 570–579 (2018) CrossRef Rahman, S., et al.: Dynamic workload migration over optical backbone network to minimize data center electricity cost. IEEE Trans. Green Commun. Netw. 2(2), 570–579 (2018) CrossRef
19.
go back to reference Morabito, R.: Power consumption of virtualization technologies: an empirical investigation. In: 8th IEEE/ACM International Conference on Utility and Cloud Computing, pp. 522–527 (2015) Morabito, R.: Power consumption of virtualization technologies: an empirical investigation. In: 8th IEEE/ACM International Conference on Utility and Cloud Computing, pp. 522–527 (2015)
Metadata
Title
Virtualized controller placement for multi-domain optical transport networks using machine learning
Authors
Sabidur Rahman
Tanjila Ahmed
Sifat Ferdousi
Partha Bhaumik
Pulak Chowdhury
Massimo Tornatore
Goutam Das
Biswanath Mukherjee
Publication date
10-07-2020
Publisher
Springer US
Published in
Photonic Network Communications / Issue 3/2020
Print ISSN: 1387-974X
Electronic ISSN: 1572-8188
DOI
https://doi.org/10.1007/s11107-020-00895-8