Edge computing processes and stores data locally and transmits only selected summaries to the cloud. Rather than trying to analyze data in the cloud, edge processes it locally, which is cheaper and easier to manage and enables real-time insights value. It pushes computing power to the edges of a network, implementing data analytics close to the end devices and close to the source of data.
This improves network response times. It is different from today’s Cloud-based system, where information is sent to a distant data centre. It is a distributed IT architecture in which client data is processed at the periphery of the network, as close to the originating source as possible. It uses a network of micro-data stations to process or store the data locally, within a range of 100 square feet, and transmits only selected summaries to the cloud. Edge is cheaper and easier to manage and enables real-time insights value. It is a decentralised system of cloud computing.
Besides collecting data for transmission to the cloud, edge computing also processes, analyses, and performs necessary actions on the collected data locally. Costly bandwidth additions are no longer required as there is no need to transfer gigabytes of data to the cloud. Edge computing allows agencies to take the power of the cloud all the way to the network edge, especially to areas where they have not been able to use it before. Agencies can perform data analytics and processing and gain insights at the edge before routing that data back to centralised data centers for further analysis. Edge computing device nearby can be a gateway device like a router or a switch to process or analyse the data.
Cloud is not necessarily the best place for mission critical decisions that could help a vehicle avoid a collision on the highway — given the time (latency) demands, this type of processing is best handled at the network edge. On average, it takes roughly 100 milliseconds for large amounts of data to travel back and forth from the cloud.
As IoT becomes more widespread, the demand for bandwidth will increase dramatically, resulting in poor, inconsistent connections. The solution? Edge computing to complement the cloud. Edge computing is meant to complement the cloud, not completely replace it.
Examples of Edge computing: Autonomous vehicles, streaming services (Netflix, Amazon Prime), smart homes and factories where robots perform complex operations.
IoT use cases that require edge computing: smart buildings, drone-based delivery services, real-time subsurface imaging, traffic congestion management and video surveillance.
Real-time Data: In an age where real-time data is extremely valuable, there is a need for processing and analysing data closer to the location. This issue can be resolved by edge data centres, which can not only help enterprises process more data on the edge, but also help in saving a lot of bandwidth related costs, as the number of data hops are reduced significantly. Research firm Gartner expects more than 15 billion devices to connect to enterprise infrastructure by 2029.
As more processing shifts to edge data centres, we can expect a rise in prefabricated modular and micro-data centres which are small data centres which come with their own air-conditioned cabinets, a server rack, a UPS and a power distribution unit. These micro-data centres will be increasingly preferred as they do not require huge space, and can be comfortably placed in environments such as hospitals, retail stores or offices.