The concept of edge computing was first introduced as Mobile Edge Computing (MEC) by ETSI in 2015 and later renamed as Multi-Access Edge Computing in 2017 in order to widen its scope beyond its initial focus on mobile radio access networks (RAN). According to ETSI: “Mobile edge computing provides an IT service environment and cloud computing capabilities at the edge of the mobile network, within the radio access network and in close proximity to mobile subscribers”. In other words, the basic idea of MEC is to provide IT and cloud computing capabilities within the RAN. This is achieved by co-locating local computing servers with base stations or access points, or at least deploying the MEC servers in their close vicinity.
By shortening the physical distance between the locations where the data or the computation is consumed (i.e. the mobile device) and where it is stored or provided (i.e. the MEC server), metrics such as delay and bandwidth can be greatly improved compared to the case when the same services are provided by centralized cloud servers. Additionally, edge computing promises to reduce the energy consumption of mobile devices through the computation offloading of intensive tasks to the edge of the network. An array of disparate applications may benefit from the low latency and the high bandwidth provided by MEC. Examples of applications that MEC enables include: augmented reality, content delivery and caching, video analytics, automated driving and mobile data analytics. Additionally, edge computing plays a central role in providing computational capabilities for IoT.
Edge computing is considered as a key enabler for 5G networks in order to be able to meet the stringent requirements set by some of the verticals supported in 5G, such as automotive, healthcare and the aforementioned Internet of Things.