What's new for Data Centers? Will they survive the data demand?

Data center has been a hot topic of discussion among IT teams for several years now. Massive facilities housing huge amounts data, data centers by tech giants like Google, Amazon, Microsoft, Apple, and other companies offer numerous services to users worldwide. However, with the expansion of Internet infrastructure, the advent of 5G technologies, the surge in Internet of Things (IoT) devices and bandwidth-intensive applications have increased traffic on data centers and hence higher latency. Hence, to counter this, today, companies are shifting to data centers that are closer to the point of application or generation, i.e., edge. This is bringing an age of edge data centers.

Though there isn't any true definition of an edge data center, it can be considered as a smaller version of data center with facilities that extend the edge of the network to deliver cloud computing resources and cached streaming content to local end users. By moving near to the point of data activity, companies can have better control over data processing and storage at the edge of a network compared to establishing it in existing centralized data center. It is important to note that edge data center can be a part of a complex network including a central enterprise data center. They can also use larger-scale facilities to perform services that aren't time-sensitive, for instance data backup.

Gartner, predicts that by 2025, there will be a 75% jump in the data generation and processing happening at the edge and not at the central data center. Meanwhile, IDC reports that more than half of all data will be generated at the edge of the network by as many as 80 billion Internet of Things devices. The fallout from this trend is that 70% of enterprises will be forced to institute data processing at the edge by 2023.  According to PWC, global market for edge data centers is expected to nearly triple to $13.5 billion in 2024 from $4 billion in 2017, thanks to the potential for these smaller, locally located data centers to reduce latency, overcome intermittent connections and store and compute data close to the end user.

Presently, edge computing is leveraged by autonomous driving vehicles, drones, content delivery streaming, video monitoring services, augmented reality and virtual reality gadgets, and some artificial intelligence applications. Each of them run on real-time data inputs, and generate data that has value for a very short time frame. Edge enables filtration, analysis and relaying the data output back to end users more quickly. This means bypassing a series of switches, routers, base stations, and other touchpoints that could make it a lengthy process and cost more time and resources.

Through edge data centers, companies can curtail the physical distance that data needs to travel to reach a data facility, thus resulting in reduced latency. Further, owing to it redundant feature, suppose one edge data center goes offline due to power outage or any other reason, surrounding facilities can pick up its services to ensure higher percentage of uptime. In a Network World article, Zeus Kerravala explains that Tier 3, N+1 data center can qualify as an edge data center. This is because a Tier-3 data center guarantees 99.982% uptime, which is a must along with redundant power and links, to be considered as part of the internet edge. The article also mentions that close proximity to the peering points and content provide a greater ability to isolate the network from DDoS attacks.

Further the PWC report also states that by filtering the data close to the source, low-cost edge centers can help close the potential 64 zettabyte gap between global data center traffic and useable data created.