Click to learn more about author Nader Salessi.

Once upon a time, terabytes of data seemed like a whole LOT and something only large enterprise organizations could generate let alone need to process or store. Well that has changed significantly in the last few years as companies of all sizes are now creating and managing terabytes of data, and in some cases, even hitting the petabytes region. Connected “edge” devices are also generating exponentially greater amounts of data thanks to everything from remote sensors to content delivery networks (CDNs). 

In 2020, more than ever, we are going to see the enterprise increasingly deploying “edge” workloads to support data-intensive use cases like artificial intelligence and machine learning, as well as real-time analytics, IoT, and 5G.  But these workloads are suffering due to a lack of processing power at the edge.

This is where computational storage has come in and changed the game. Computational storage decreases data movement and processes the data right where it is created – rather than move the information all the way to the host CPU. We call this “in-situ processing” and it is the key to the technology. Overall, computational storage has the capability to reduce the time to process a petabyte of data for high capacity-driven, read-intensive analytics applications.

Nowadays, people need enormous amounts of data analyzed and processed immediately. Computational storage can help with this need – which is why 2020 will be the year when computational storage comes into its own. As such, the following are my predictions about how organizations will store and process data in 2020, particularly enterprises relying on hyperscale, edge, and CDN environments.

NVMe is NOT Enough

Many connected devices, from video surveillance cameras to smart cars, must churn out large amounts of data that need immediate analysis. While NVMe (Non-Volatile Memory Express) has proven to help speed up the processing of data, the fact is that it is still not enough by itself for many edge-related devices. Part of the issue is the need for speed with less movement and the other is the need to extract only small amounts of data out of petabytes for the purposes of analysis. So, how can this be done immediately?  To solve these challenges, computational storage drives, which can offer a 20x or more improvement in capability and smaller overall space, are necessary to work with the NVMe SSDs, allowing AI-enabled systems to read, analyze, and authorize data in ways never before seen.

Let’s look at the airline industry: Did you know that the amount of information generated during a four-hour flight can take more than 10 hours to analyze upon landing? In other words, there are planes flying that may have issues no one is aware of. Computational storage solutions allow for faster AI tools to run when the plane lands and ensure it is safe for the next flight, even if it is in 30 minutes or less.

Computational Storage Enables Better 5G Connectivity:

We all know that 5G increases the amount of bandwidth and speed of communication but along with 5G comes the need to develop more complex infrastructures to support seamless connectivity.

As more cell towers are built to support 5G, there also needs to be a more complex infrastructure at each bay station that can manage the data “in and out of the box” and at the source, so that user data is optimally utilized.Computational storage limits data movement and with its small form factor can pack an analytical uppercut punch in the limited size and power enabled edge-datacenters that live at each of these new cell tower platforms. Providing additional compute to the confined resources that exist is paramount to successful growth of this space. Instead of requiring even more hardware and power to the server, the advent of high=-capacity computational storage provides the needed offload to the system to allow for great deployments.

Computational Storage Can Simplify the Traffic Flow of Content Delivery Networks:

According to a recent report from Deloitte, there are more people in the US with a streaming service subscription (69 percent) than there are who pay for a traditional TV subscription (65 percent). As such, streaming services have continued to dominate headlines, with the recent launches of Apple TV+, Disney Plus, and NBC ‘Peacock’, combined with Netflix, Hulu and Amazon Prime’s increasing investments. This poses a major hurdle for the content delivery networks (CDNs) – and where computational storage can be a major asset.

With more people consuming an increasing amount of streaming content, CDNs will have to invest in new infrastructure to reliably deliver all this content. Customers will have no patience to wait for buffering or for interruptions in video streams when they’re paying between five to$12 for each service. In addition to a general increase in streaming content services and streaming content consumption, consumers are watching video more and more on mobile devices such as tablets or smartphones, making CDNs’ jobs even harder as these devices have less processing power than devices like Rokus or Apple TVs that are designed for streaming content.

Video requires lots of expensive data movement, which makes it more costly and difficult to deliver. CDNs have typically relied on a traditional cloud model to support streaming customers, but they realized centralized clouds were too far on average from the end points to which they sent data, racking up costs, latency, and downtime.

Computational storage can help solve for these issues. While a typical CDN traffic flow involves lots of data movement and processing spread out over a variety of edge infrastructure, computational storage can simplify this flow. This is done via in-situ processing, all within the storage device itself. This means more people get to watch their content faster with less overall hardware overhead.

In 2020, we will see computational storage come into its own as adoption for the disruptive technology increases.  Since the computational storage IT architecture allows data to be processed at the storage device level to reduce the amount of data that has to move between the storage and compute planes, organizations will come to appreciate how the technology provides a faster and more efficient means to address the unique challenges of our data-heavy world. 

In other words, computational storage is a true windfall for the edge in the new year and beyond.