How SSDs are fueling the data revolution

Digital data on a globe
Image Credit: Shutterstock (Image credit: Shutterstock)

In our hyperconnected world, data surges like a digital torrent. Every minute, transactions worth over $500,000 ripple through Venmo and AWS, while 6 million Google searches light up our screens. Meanwhile, 66,000 Instagram photos flicker like virtual fireflies, illuminating our digital landscape.

The Internet of Things (IoT) amplifies this data explosion. By 2023, an estimated 14.5 billion IoT devices will weave a web of connectivity, demanding efficient storage solutions. Artificial intelligence (AI) and machine learning (ML) applications take it a step further, as these processes and applications demand high performing data storage to ensure speed and proficiency at the edge. Nearly 77% of devices today use AI technology in one form or another, while 77% of businesses are using or exploring AI. Without quick access to data, IoT-powered devices and AI applications cannot function.

Enter edge computing, the secret sauce that transforms data into actionable insights. But what exactly is edge computing? Imagine autonomous cars making split-second decisions, drones capturing breathtaking vistas, and satellite images unveiling Earth’s hidden mysteries. At the edge, data flows from these endpoints to enterprise-hardened locations, bridging the gap between real-world events and digital intelligence.

Tahmid Rahman

Director of product marketing at Solidigm.

Why edge computing matters:

1. Data Hunger Increases at the Edge: As workloads shift toward the edge, hunger for data intensifies. High-density storage solutions become essential to keep pace with this voracious appetite.

2. Cloud-Native Dominance: Gartner predicts that by 2025, more than 95% of new digital initiatives will be cloud-native. Data centers, the guardians of this content, must stay cool while accommodating advanced AI models that multiply in power every few years.

3. Edge Magic: Edge computing isn’t just a buzzword; it’s where magic happens. From split-second decisions in autonomous cars to breathtaking drone vistas, the edge is where data transforms into action.

In this era of data-driven possibilities, modern storage at the edge isn’t just a luxury—it’s the beating heart of innovation.

SSDs: The unsung heroes of edge computing

Solid-state drives (SSDs) are the unsung heroes of the data revolution. They’re like tiny vaults where data is expeditiously stored and retrieved.

Why SSD’s Matter:

• Speed of Light: SSDs read and write data at warp speed, whether it’s analyzing satellite images or processing real-time sensor data.

• Endurance Titans: SSDs can handle heavy workloads without breaking a sweat.

• Energy Efficiency: SSDs are efficient, and less power means less heat—a critical factor for edge deployments.

• Compact Marvels: SSDs come in various types, including the Enterprise and Data Center Standard Form Factor (EDSFF) allowing for more data stored in the same footprint as a hard disk drive (HDD). Not only that, but modern SSDs are available in capacities as large as 61TB, much larger than HDDs.

How technology is evolving as storage shifts to the edge:

• Autonomous Driving: Autonomous driving systems require massive data logging and detection capabilities, and SSDs excel in shock resistance and vibration tolerance—essential for bumpy roads. Picture this: ADAS systems churning out data at a staggering 19TB per hour! Even though they’re not on duty 24/7, a year of driving generates a whopping 5PB of data. While it is not a 24/7 duty cycle, 17,600 mins per year driving profile will generate 5PB/year of data.

• Robotic Systems: Robotic systems, drones, and satellite image analysis thrive on real-time data. For instance, some tractor technologies leverage a “See and Spray” feature, which capture 20 images per second per crop all while the vehicle zips along. These images are then compared against a million stored images to pinpoint areas needing treatment. Imagine the storage appetite—an onboard camera churning out 6TB of data per day, per sprayer.

• AI: Recognizing the increasingly critical need to make sure data can be collected and processed at the edge, some storage providers leverage solid-state drives (SSDs) for high performance, reliable data storage. These can handle the terabytes (TB) of data required by ML/AI applications and maintain operations under the extremely challenging conditions often found at the edge (e.g., vibrations, shocks, humidity, and large temperature swings).

Selecting an SSD that fits your needs:

In this era defined by innovation and adaptability, data storage providers should prioritize creating nimble, efficient, and scalable solutions. Pretty simple, if there wasn’t so much to choose from! Nowadays, data storage solutions are endlessly customizable, which has intensified customer decision making. Which SSD you choose for your application will depend on your target drive writes per day (DWPD) as well as your workload; write-heavy, read-heavy, or some mixture of both. One size does not fit all, and the best results will come from weighing multiple factors as you plan your storage solution build.

Consider:

1. Endurance: Beyond First-Gen SSDs First-generation SSDs carried hefty write endurance requirements—sometimes 10 to 20 DWPD (drive writes per day). But times have changed. Write amplification factors have improved, thanks to smarter SSD firmware and standardized NAND endurance levels (SLC, TLC, and QLC). JEDEC219 standards now provide clarity on workload-based endurance measurement.

2. Performance with Precision: As solid-state storage evolves, performance isn’t just about bandwidth and IOPS. We’re diving deeper. Drive sizes are ballooning, and new techniques emerge. Multi-tenancy applications ensure one tenant’s IOs don’t impact another’s latency. And watch out for Flexible Data Placement (FDP) mode—it’ll let hosts place data without sacrificing endurance or performance due to internal garbage collection.

3. Form Factor Flexibility: Data center SSDs no longer adhere to the old 2.5" HDD form factor. EDSFF (Enterprise and Data Center Standard Form Factor) offers diverse shapes, better signal integrity, and robust hot plug connectors. It’s like having a tailored suit for every workload.

The Edge beckons

The edge is where the action intensifies, and technologies like ML and AI demand data storage that can keep up. The next-generation SSDs must rise to the challenge. Remember the days of fitting one density, one form factor for the entire market? Innovation now wears a custom suit. Customizable, workload-driven data storage SSDs define the future.

We've featured the best portable SSD.

This article was produced as part of TechRadarPro's Expert Insights channel where we feature the best and brightest minds in the technology industry today. The views expressed here are those of the author and are not necessarily those of TechRadarPro or Future plc. If you are interested in contributing find out more here: https://www.techradar.com/news/submit-your-story-to-techradar-pro

Tahmid Rahman is the director of product marketing at Solidigm.