Reconstruction of control plane of distributed SDN against large-scale disruption and restoration

T Hirayama, T Miyazawa, H Furukawa… - 2017 IEEE Conference …, 2017 - ieeexplore.ieee.org
T Hirayama, T Miyazawa, H Furukawa, H Harai
2017 IEEE Conference on Computer Communications Workshops (INFOCOM …, 2017ieeexplore.ieee.org
Software Defined Networking (SDN) technology enables us to configure switches in a
network flexibly. Previously, distributed SDN control methods have been discussed to
improve their scalability and robustness. Distributed placement of controllers reduces
computation load of each controller and backing up each other enhances robustness.
However, these techniques do not include an emergency measure against large-scale
failures such as network separation induced by disasters. In this paper, we design …
Software Defined Networking (SDN) technology enables us to configure switches in a network flexibly. Previously, distributed SDN control methods have been discussed to improve their scalability and robustness. Distributed placement of controllers reduces computation load of each controller and backing up each other enhances robustness. However, these techniques do not include an emergency measure against large-scale failures such as network separation induced by disasters. In this paper, we design emergency reconfiguration of distributed SDN especially in control plane (C-plane). In our reactive approach, each node detects disconnection to the main controller. Then, a controller deployed on one of the disconnected nodes becomes the substitute controller to which the others reconnect. Meanwhile, C-plane should be reconstructed when network connectivity recovers in case many controllers exist. The main and substitute controllers detect networks are reconnected, and merge their C-planes to avoid conflict. Simulation results reveal that our proposed method recovers C-plane logical connectivity with probability of about 90% when regional failure occurs in 100 node networks. Furthermore, we show that convergence time of our reconstruction mechanism is proportional to network size.
ieeexplore.ieee.org
Showing the best result for this search. See all results