Data volume, mobility and the Internet of Things all require decentralised computing power as an extension to hyperscale data centres. Shibu Vahid, Head of Technical Operations, R&M Middle East, Turkey and Africa talks further about this shift to the edge and how telcos can help prepare for it.
The growth in private and business data traffic continues unabated. And the Internet of Things, 5G and mobility now need to be taken into earnest consideration as they have begun to cause an additional exponential growth of IP traffic while requiring ultra-low latency even in remote places.
The hyperscale data centres that service providers have been investing in will not be able to fully cover the new network, computing and storage requirements of the coming years. Therefore, telcos will have to extend computing power to the edge of their network to support their large, central data centres.
Service providers and network operators can prepare for this by setting up the necessary infrastructures for the periphery in good time – providing they start doing so now.
This will entail a wide-scale increase in fibre optic cabling – something that is presently happening with the many FTTH undertakings in the region – and the installation of decentralised micro data centres.
These micro data centres are autonomous, automatable and sturdy solutions which have to be powerful enough to assume a leading role in the cloud.
When highways become data centres
A striking application example for edge computing is future of road traffic. A study by the German Fraunhofer research institute, has shown that for cars to be fully automated and safe, they would have to be able to react within 0.1 milliseconds.
The exchange of information with the environment, with antennas, sensors and other vehicles would effectively have to take place at the speed of light. Along with future 5G services, this will require a fibre optic network along the roadside.
There would have to be servers or micro data centres on the roads or at base stations every 15 kilometres to guarantee virtually latency-free interaction and processing of the most important data on site. Exchanging data using remote cloud data centres would be too slow to control traffic and ensure there are no accidents with the typical one to two milliseconds latency.
So, while the cloud could compile, analyse and store all traffic data that is not critically time-bound, the edge will require micro data centres as there is zero tolerance for latency and a need for unconditional availability.
This latency, hyper-interactivity and decentralised intelligence will play a role in numerous other applications in the digitalised world. These include industrial manufacture, industrial Ethernet and robotics, 5G and video communication, smart grids, the Internet of Things (IoT) as well as Blockchain, AI and AR applications.
Edge computing can support all these tasks by shortening the path between the acquisition, collection, analysis and feedback of intelligence to the networks.
Micro data centre requirements
The locations at which micro data centres will have to be deployed could be demanding. To minimise risks, application sites will have to be chosen carefully and edge solutions will have to be as robust and maintenance-free as possible.
They should also be able to run independently without specialist personnel. But there will still have to be safe rooms or containers to protect micro data centres from manipulation, environmental influences and electromagnetic loads.
Installation and operation at the edge will have to be made as simple as possible with the ‘plug and play’ principle applied to connectivity and IT. Micro data centres will require the ability to be connected directly to fibre optic or broadband networks everywhere and will require integrated cooling, sound insulation, UPS, access control and remote monitoring.
Given the likely locations for their deployment, they would have to be climate-resistant, closed and shielded and designed for maximum density and compactness.
Paradigm shift in network planning
The edge trend is leading to a paradigm shift in the way we design, provide and monitor networks as specific security, connectivity and bandwidth requirements will have to be taken into consideration. Infrastructures will have to be designed with the ability to spread computing power on a wide scale and support software defined WAN (SD-WAN). This means that service providers will have to adapt their business models.
The base stations of cellular phone network providers will be particularly suitable as sites for edge data centres. Because with the introduction of 5G technology, mobile communication antennas will become locks for enormous amounts of data. Hubs or gateway exchanges of cable and telecommunication networks are also a possibility.
The exponential growth of data from the various applications and devices which can be found everywhere is forcing us to rethink today’s network structures. Weak sub-networks can slow down the entire communication chain. Bottlenecks in network interfaces, transmission and computing capacities are to be avoided at all levels to be able to guarantee a smooth flow of data traffic.
Decentralised mini or micro data centres can reliably connect IoT devices on short links and can easily be scaled when local IoT networks grow, thus serving as the backbone for smart city infrastructure. They can replicate cloud service and business-critical processes on site and buffer bandwidth-intensive applications such as mobile HD video. And, if cloud connections falter or fail altogether, the networks, servers, memories and devices at the edge will continue to work.
Edge data centres can even form geo-redundant groups if they are sufficiently networked and thus promote the security and availability of services in extreme conditions.
By decentralising and preparing for this paradigm shift in networking and data centre deployment, service providers can build the infrastructures upon which the host of next-generation services for the smart city can be realised.