What is Edge Computing?
A quick answer is, Pushes “Intelligence” to the Edge of the Network. What we could make out of this depends on, how much we know about different aspects of the network architecture and its evolution. Herewith I am trying to give an outlook to these attributes. To begin with, we will get down to the evolution of computing architecture in terms of network layer [components] placement.
As expressed in the above picture, In the ’1990s, the rise of GRID computing was to speed up the computation time by splitting the requests into multiple sub-tasks and process those in parallel using a group of computers connected to each other physically; so that we can serve the user faster. In the ‘2000s, cloud computing takes the center stage and start moving towards accessing resources using Web instead of users owning the entire infrastructure in their premises [own infra could increase the CapEx, and we end up underutilizing most of the resources]. Cloud addresses these issues; the user would eventually use the resources on-demand basis (pay only for what you use).
Between the 2010s to present, we hear the term “Edge Computing” more often. This requirement arises when the number of users to cloud increases [put the stress on bandwidth] and the need for ultra-low latency of critical fields like IoT. Hence cloud data center computing capacity is extended to users via the architecture called “EDGE”. Edge would introduce a new layered approach by placing infrastructure close to user proximity. So that users would get the response without much delay which was caused by transmitting the data to a larger distance to the cloud. This EDGE layer is now having the capacity to do computation/storage/caching for the user without reaching to the cloud. This is what we define it as pushing intelligence to the edge of the network.
To take one level deep in the understanding of the Edge Computing, we will see what is Network Edge? Network Edge is what connects each layer of the network [user-edge-cloud]. This is categorized into two parts: First, the core network which connects the edge and the cloud. Second, the access network which connects the edge and the user. So any networking function which contributes to wiring up these layers is falling under Network Edge [It could be virtual/physical components].
Edge Computing is a concept that takes different forms when it gets materialized such as Mobile Cloud Computing [MCC], Fog Computing [FC] and Multi-Access Edge Computing [MEC]. MCC is mainly aimed at offloading the computing and storage tasks from mobile devices. Fog computing, on the other hand, addresses the demand raised by exponentially increasing IoT devices by setting up geographically distributed data centers that are closer to users [backed up by cloud data centers]. MEC is the approach used by Radio Access Network (RAN) technologies to bring the Network Functions (Evolved Packet Core => Subscriber Management, Mobility Tracking,.) close to users so that it would be served faster. Whatever be the name [could be more than what is listed here], all these approaches take us to the same direction of achieving ultra-low latency by introducing some new layers between the user and the cloud.
I’m hopeful that this blog would have given some insights into the term “Edge Computing”.
A mentor is someone who allows you to see the hope inside yourself.
Thanks, Manu Mathews. You are such a person!
Subscribe to FAUN topics and get your weekly curated email of the must-read tech stories, news, and tutorials 🗞️
Follow us on Twitter 🐦 and Facebook 👥 and Instagram 📷 and join our Facebook and Linkedin Groups 💬
