2014 12th International Conference on Frontiers of Information Technology (FIT) (2014)
Dec. 17, 2014 to Dec. 19, 2014
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FIT.2014.21
Traditional Data Center Networks (DCNs) are suffering from many problems which include high energy consumption, high latency, fixed throughput of links and limited reconfigurability to the traffic demands. This leads towards the a change in the paradigm from electrical to optical interconnects between the servers. Compared to electrical counterparts optical interconnects give various advantages which include low energy consumption, high bandwidth, reconfigurability, high radix switch design, wavelength multiplexing, and fast switching transition times. Now a days there are a large number of emerging cloud computing applications which include video streaming (YouTube, Google Video etc), Search Engines (Google, Bing etc), Social Networking (Face book, Google Plus etc), Email (Gmail, Yahoo Mail, Hotmail etc), Cloud Computing, Climate and Geographic Information Systems. Each of these application has it's own latency, blocking, reconfigurability and radix requirement. Thus classification of architectures is necessary to decide which architecture suits the demands of which application. In this paper we have classified the optical interconnects in DCNs on the basis of their inherent nature. Basic optical components form the basis for the optical interconnects. This paper has following sections, Section I gives a motivation for the optical interconnects in DCNs, Section II highlights basic optical components used in optical interconnects and Section III gives a classification tree of optical Interconnects in DCNs.
Optical switches, Optical interconnections, Arrayed waveguide gratings, Ports (Computers), Multiplexing, Optical devices,Classification, Data Center Networks, Optical Interconnects
Mohsin Fayyaz, Khurram Aziz, "Classification of Optical Interconnects in Data Center Networks", 2014 12th International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 61-66, 2014, doi:10.1109/FIT.2014.21