The increased demand for streaming services for home offices, games, music and movies, and the rise of data-intensive applications such as machine learning and artificial intelligence (AI) are just a few of the many factors that have contributed to the rise in bandwidth demands…

These developments present challenges for hyperscalers, as well as enterprise and colocation data centers, because in addition to increasing capacity requirements, they must ensure reduced latency while meeting climate goals.

One way to achieve this is to make more efficient use of existing switch architectures (high cardinality ASICS). For example, a 32-port switch offers up to 12,800 Gb/s of bandwidth (32 x 400G) and also offers 800G transport versions up to 25,600 Gb/s. These high-speed ports can be easily divided into smaller bandwidths. This enables more power-efficient operation while increasing package or port density (32 x 400G = 128 x 100G).

The need to support low-latency, high-availability, and ultra-high-bandwidth applications will continue to grow in the future. The question is not whether data center operators need to upgrade to meet growing bandwidth demands, but when and how. Therefore, operators should prepare now and adjust their network design. After all, with a flexible infrastructure, it is possible to upgrade from 100G to 400G to 800G with very little change.

Network design is getting more complex

However, higher data rates also increase solution and product complexity. As mentioned earlier, it is not necessary to fully utilize 800G for each port, but to support the bandwidth requirements of the end device. For example, a Spine-Leaf connection with 4 x 200G or a Leaf-Server connection with 400G ports, operate as 8 x 50G ports while making the network more power efficient. To achieve this, various solutions exist as well as new transceiver interfaces.

LC duplex and MPO/MTP connectors (12/24 fiber) are well known interfaces for 10, 40 and 100G transfer speeds. For higher data rates, such as 400G and 800G and beyond, other connector types have been introduced, such as MDC, SN, and CS (subminiature connectors), as well as MTP/MPO connectors with 16 fibers in a single row.

It is often a challenge for network operators to track and select the technology and network components that suit their needs. The requirement for increased bandwidth in network expansion often conflicts with the lack of space for additional racks and frames, or the resulting cost. As a result, network equipment vendors are constantly working on developing new solutions to achieve higher densities in the same space and keep network designs scalable while keeping them as simple as possible.

Port Breakthrough Applications to Improve Sustainability

In addition to better utilization of high-speed ports and associated port densities, port branching applications can positively impact the power consumption of network components and transceivers.

A 100G duplex transceiver for QSFP-DD consumes about 4.5 watts, while a 400G parallel optical transceiver operates as four 100G ports in breakout mode, consuming only 3 watts per port. This equates to savings of up to 30%, despite the additional savings in air conditioning/cooling and switch chassis power consumption and their contribution to space savings.

Impact on network infrastructure

When the lowest common multiple is used as the basis, the use of trunk or trunk cabling can be extended. For duplex applications, this typically corresponds to "factor 4," or base-8 routing, upon which a -R4 or -R8 transceiver model can be mapped. Therefore, this type of cabling supports current technology and future developments.

In addition to choosing a fine-grained, scalable backbone, it is also important to plan for sufficient fiber reserves for future upgrades or to implement expansions with as little change effort as possible. After planning enough fiber reserves, network adjustments can be achieved with only a few component replacements: for example, an upgrade from 10G to 40/100G or 400/MTP can be achieved by replacing MPO/MTP with LC modules and LC duplex patch cords 800G MTP adapter panels and MTP patch cords without any changes to the backbone (fiber optic equipment).

The modular fiber optic housing also allows mixing different technologies and integrating new connector interfaces (subminiature connectors) in a few simple steps. Termination options are already available: 8-fiber, 12-fiber, 24-fiber and 36-fiber modules. The use of bend-insensitive fiber also helps make the cabling infrastructure durable, reliable, and fail-safe.

Preparedness pays off

Data rates of 400G or 800G are still a long way off for most enterprise data center operators, but bandwidth demands are growing rapidly. Sales of 400G and 800G transceivers are already on the rise, and it pays to be prepared, rather than having to upgrade later under time pressure. With just a few changes now, data center operators can make their facilities 400G and 800G-ready, optimally prepared for the future. Of course, this also applies to Fibre Channel applications.