Equinix Taking Storage to the Edge

News Analysis Mitch Wagner, Executive Editor, Light Reading 2/28/2017

BARCELONA -- Mobile World Congress 2017 -- Equinix is working on beefing up storage at the edges of its network, looking to help enterprises maximize Internet of Things and other applications requiring low latency and high performance.

Internet of Things (IoT) applications require storage and compute located at the edge of the network -- physically near the devices that the applications monitor and control. Applications that monitor networks for attacks, or inventory for shortages an discrepancies, or industrial machinery for potential failures, don't have time to phone home to a centralized data center. They need access to analytics and decisions now, Equinix CTO Ihab Tarazi tells Light Reading.

To meet those needs, Equinix Inc. (Nasdaq: EQIX) plans this year to deploy software-defined storage at the edge of the network, as well as security and compute services, Tarazi says.

Software-defined storage allows operators to move storage capabilities anywhere in the world where it's needed, Tarazi says. "The volume of data is exploding, and the need to use it in real time is more pressing," he says. Economically, it makes sense to go to a hybrid storage model, with some in the cloud, and some on premises.

"Instead of your data being in one spot, you can put it all over the world," Tarazi says.

Equinix is teaming with leading storage providers, and will deliver technology it calls "data fabric" by the end of the year, to make it simpler for customers to migrate to a hybrid storage model.

The exploding volume of data generated by IoT sensors requires a hybrid approach to analytics -- traditional, batch analytics that can be done in a centralized data center, as well as real-time analytics that needs to happen at the edge to achieve necessary performance, Tarazi says.

For example, financial institutions collecting credit card data need to be able to detect fraud in real time, but that requires comparing data globally in real time, Tarazi says. "Data is going to be distributed and hybrid" -- residing on both the data center and the network edge.

Want to know more about the cloud? Visit Light Reading Enterprise Cloud.

Anyone doing predictive analytics for applications such as security, business decisions for IoT, weather data or industrial Internet of Things, has similar needs. "All of these applications require you to collect massive amounts of data from some device, compare it to data locally, and act on it," he says.

Additionally, Equinix is improving data throughput and latency to support public cloud, private storage and hybrid storage, Tarazi says. And the company is developing new security and compute capabilities at the edge of the network to support data residing there. Equipment is moving to a hyper-converged model, with shared pools of compute and storage, to meet those needs.

Equinix sees edge storage as an extension of its main business, providing connectivity between cloud providers, service providers and enterprises, using fast, high-performance networks. (See Equinix Says It's All About the Network.)

Equinix recently expanded its footprint to about 150 data centers worldwide, and is acquiring 29 data centers from Verizon. (See Finally! Equinix Pays $3.6B for Verizon Data Centers.)

Related posts:

— Mitch Wagner, , Editor, Light Reading Enterprise Cloud

CALLING ALL CLOUD, NFV AND SDN COMPANIES:
Make sure your company and services are listed free of charge at Virtuapedia, the comprehensive set of searchable databases covering the companies, products, industry organizations and people that are directly involved in defining and shaping the virtualization industry.