The Edge is Where IT’s At
More and more data is being created at the edge. In fact, it is predicted that by 2025, 75% of all data will be created and processed outside a traditional centralized data center or cloud. Contributing to this data explosion are the technologies of the Fourth Industrial Revolution, including AI, 5G, and IoT. The challenge and opportunity for organizations of all types is how to best gather, process, and manage this data now and in the future.
Edge data is growing faster and is different. Eighty percent (80%) of edge data is unstructured – documents, email, video, images, audio, machine data, etc. – and it is growing at a rate two to three times greater than structured data at the edge. To manage this data, organizations are moving more processing and storage to the edge — not only to meet requirements but also to reap certain benefits.
Edge sites pose unique challenges. There may be dozens, hundreds, or even thousands of sites, often in remote and/or harsh locations. Bandwidth and latency issues frequently exist, along with high costs to move data to the cloud or data centers. Requirements around compliance and data sovereignty may also be factors. There is often little to no technical staff on-site, requiring robust and available systems. And the sheer volume of data generated can be massive – a single high-resolution video camera recording at 30FPS (frames per second) can exceed 20GB of video storage per day.
While costs and conditions may necessitate moving processing to the edge, there are also benefits to consider. Processing at the edge enables decision-making in real-time, whether those decisions are man- or machine-made. And with the data gathered at the edge, analytics and business intelligence can be applied for insight and future benefits. Decision-making at and from the edge allows for the fastest, and hopefully best, outcomes, keeping organizations agile and responsive.
Data at and from the edge is a blessing and a curse, as not all edge data is equal in value. Quantity does not equal quality, so data policies for movement, retention, archiving, and removal are important. It is important to deploy processing and storage solutions that can identify, separate, and utilize the valuable data, keep it available and secure, and move and retain it for future use when and if needed. Some edge data, such as a video clip, has no value until it is needed, but then its value is very high.
Solid active-use and active archive solutions are required to get the most benefit from and meet any requirements for, edge data. Solutions must include the ability to intelligently process data at the edge, allow quick decisions and future insights, and then move data to the proper storage tier based on expected use, value, and policy. These solutions must be available and secure and provide for fast retrieval of any data from any tier. With the amount of unstructured data continuing to grow, and the potential high future value for video, images, audio, and other data, an active archive solution is just as important for the edge as it is for the datacenter and cloud.
 “What Edge Computing Means for Infrastructure and Operations Leaders,” Rob van der Meulen, Gartner, October 2018
 Schwab, Klaus. “The Fourth Industrial Revolution: what it means, how to respond”. World Economic Forum, January 2016. “The possibilities of billions of people connected by mobile devices, with unprecedented processing power, storage capacity, and access to knowledge, are unlimited. And these possibilities will be multiplied by emerging technology breakthroughs in fields such as artificial intelligence, robotics, the Internet of Things, autonomous vehicles, 3-D printing, nanotechnology, biotechnology, materials science, energy storage, and quantum computing.”