Many applications in use by consumers, businesses and network operators are running in “the cloud” – that is, on compute/storage facilities connected by wide area networks, mostly in big centralized data centers (DCs) or smaller regionally distributed DCs, or even some metro-distributed DCs. But many applications are better served if they reside on compute resources nearer the “edge” – that is, closer to the end user, device, machine, or application.
The edge ‘is in’ these days in conversations, conferences and considerations—and there are many definitions. Our conclusion is that there are many edges, and we chose a fairly common definition of 20 milliseconds (ms) (round trip time = RTT) from the edge compute location to the end user, device, machine, or application. The two main drivers for deploying applications at the edge are latency and bandwidth efficiency.
In the first-ever survey of its kind, IHS Markit asked 14 major edge thought leaders and market movers a range of questions on the most pressing issues surrounding edge applications and services.