Big data, cloud services, content delivery, artificial intelligence, neural networks and 5G services must store and process massive amounts of data through advanced, interconnected computing resources and storage devices. The very diverse requirements of these services in terms of processing power, storage capacity, communication bandwidth, delay, mobility, etc., drive the need for a combination of a large number of distributed micro Data Centers (DCs) as well as both centralized and remote mega-size DCs scaling up to hundreds of thousands of server and storage modules. In view of this, high-speed communication across DCs is key. Additionally, for mega-DCs, the main challenge involves scaling internal computing and storage resources and interconnection capacity. Traditionally, computing, storage and communication resources have been considered separately; however, there are significant measurable benefits when a unified allocation approach is considered and these heterogeneous resources are shared.
To address these challenges and take advantage of potential benefits, there is a clear need for novel architectural approaches, network solutions, and technologies to interconnect the distributed computing and storage resources, both within a DC and between DCs, referred to as intra- and inter-DC networking, respectively. In this context, it is important to ensure that resilience, sustainability, and efficiency in the utilization of resources are maximized, thus reducing the associated capital and operational expenditures, as well as the overall energy consumption and CO2 footprint.
Optical networking plays a key role in meeting these requirements by offering high-capacity, energy-efficient, and flexible connectivity. Moreover, to address the challenge of managing and operating these infrastructures efficiently, a high degree of agility and adaptability in the functions that the network can perform is required. These goals can be achieved by adopting open software and hardware platforms such as software-defined networking (SDN) and network function virtualization (NFV), as well as OpenCompute approaches. Exploiting open platforms could lead to new business and operational models such as multi-tenancy through slicing and virtualization.
This special issue will comprise a set of original invited and contributed papers addressing some of the key challenges in the context of intra- and inter- DC networking. Papers in the issue will also propose novel optical networking architectural approaches, solutions and technologies. Overall the goal of the special issue is to provide an overview of the current technical challenges in the area of DC networking and to capture the latest technology advancements that make optical networking a key technology enabler.
Submissions to the special issue should be prepared according to the usual standards for the Journal of Optical Communications and Networking and will undergo the normal peer review process. Manuscripts must be uploaded through OSA's online submission system specifying from the Feature Issue drop-down menu that the manuscript is for the Optical Data Center Networks issue.
Hong Liu, Google, USA
Laurent Schares, IBM, USA
Dimitra Simeonidou, University of Bristol, UK
Anna Tzanakaki, National and Kapodistrian University of Athens, Greece
Lena Wosinska, KTH, Sweden