Multi-access Edge Computing (MEC), or simply edge computing, is the application of cloud architecture principles to compute, storage and networking infrastructure close to the user, at the edge of a network. With rich new services expected in the near future ranging from connected cars, augmented/virtual reality (AR/VR) to smart cities, it will become critical for communications service providers (CSPs), governments and enterprises to build edge computing infrastructure to enhance user experience and reduce costs.
A major driver for edge computing is 5G. While 5G will dramatically increase speeds and feeds — 10+ Gb/s peak data rates, 100 Mb/s sustained rates, 10-100x more devices supported, <1ms radio latency and reliability — its true power is in completely transforming mobile communications network. The combination of above improvements with network slicing (end-to-end partitioning of network bandwidth with different performance, availability and scalability characteristics) will create a whole range of new services connecting machines, users, governments and enterprises. In addition to 5G, other technologies such as DOCSIS 3.1, a CableLabs standard with full duplex 10Gb/s throughput, and even current-generation LTE will also bring advanced services.
So let’s consider why we need edge computing, and why cloud computing is not adequate for all foreseeable requirements?
Edge computing will bring seven unique benefits that a centralized data center or centralized cloud cannot offer: