Abstract:
Elastic optical networks (EONs) are considered as the most promising technology for interconnecting data centers. With the rapid growth of inter- datacenter traffic, powe...Show MoreMetadata
Abstract:
Elastic optical networks (EONs) are considered as the most promising technology for interconnecting data centers. With the rapid growth of inter- datacenter traffic, power consumption of EONs becomes a significant challenge. In this work, we present a lightpath management algorithm that uses traffic prediction techniques to eliminate unnecessary lightpath termination and re- establishment so as to decrease switching power and enhance the energy efficiency of the network. Our algorithm builds upon the centralized control and capabilities of software defined networking (SDN) technology. Numerical results show that the proposed algorithm is effective in achieving substantial savings in power consumption while maintaining a bandwidth blocking ratio at levels comparable to those of earlier algorithms.
Date of Conference: 31 July 2017 - 03 August 2017
Date Added to IEEE Xplore: 18 September 2017
ISBN Information: