The ‘edge’ is the latest IT buzzword — and now we’re hearing more about the mobile edge, or MEC, or multi-access edge computing (which are the same thing). But how close should you be getting to the edge?
MEC is a network architecture that enables cloud computing at the edge of a mobile network, which will increase connection speeds and reduce latency.
And this is going to play a crucial role in 5G, the fifth generation of mobile networks — necessary for Industry 4.0 and all that it entails, including connected cars, smart city grids and automated factories.
Research from the IEEE suggests that MEC can “decrease the end-to-end latency dramatically through service localization and caching,” a key requirement of 5G.
Gartner goes so far as to say “the edge will eat the cloud.” That’s a bold statement, but in a recent report the research firm found that 40 per cent of large enterprises plan to integrate edge computing ‘principles’ into their 2021 projects, compared to less than one per cent in 2017. The driver: latency and bandwidth requirements.
The report predicts that using cloud and edge computing together will benefit business and bring a decentralized “complement” to cloud and legacy data centres.
While MEC and 5G are disruptive on their own, combined they will be a powerful force, particularly for applications that rely on a consistent connection, rapid deployment and low latency, according to an article on SDxCentral.
“The demands of modern applications running on 5G — which requires instant computing power — is driving enterprises to move computing resources even closer to where that data is created (the user and device),” writes Jonathan Lewin in an article for The Data Center Journal.
“Data centers in Tier One markets will continue to handle more-static content that has laxer latency requirements, such as big data analytics. But dynamic content, such as that from IoT devices, will move to the edge,” he adds.
Add network slicing into the mix, and 5G becomes a heck of a lot more powerful. Network slicing — aka multiple virtual networks on a shared physical infrastructure — allows you to ‘slice’ network functions according to their demand on the network.
It should be pointed out, network slicing will be made possible by 5G; it’s not in use today. According to the IEEE, there are different ‘slice types.’ One slice type is targeted for ultra-low latency and high reliability, such as self-driving vehicles, while another is targeted at ultra-high speed required for 4K or immersive 3d video.
“Since it would be far too expensive to allocate a complete end-to-end network to each type of slice, the network infrastructure that supports 5G (and likely 4G) will employ sharing techniques (virtualization and cloud), which allow for multiple slice types to co-exist without having too many multiples of the resources,” according to the IEEE.
While many are taking a wait-and-see approach with 5G, should you also take a wait-and-see approach with MEC?
One of the “MEC myths,” according to Alex Reznik, chair of MEC ISG, in a blog post, is that since MEC is a 5G technology, you don’t need to worry about it until you roll out a 5G network. But anyone who feels that way may want to reconsider.
MEC allows you to roll out 5G applications on existing 4G networks, he says, and will allow you to eventually evolve from 4G to 5G.
Reznik sums it up: “Remember MEC stands for Multi-access Edge Computing – with ‘computing’ being key. It is much more about the cloud at the edge – how to manage it, how to run applications on it, what services such a platform can offer.”