Tuesday, May 18, 2021

SSD: Google and Seagate think they will tell when your HDD will fail

SSD: Google and Seagate think they will tell when your HDD will fail

SSD: Google and Seagate think they will tell when your HDD will fail

New AI system will come to all or any Seagate drives soon, says Google

Hard drive
(Image credit: Shutterstock)

Google Cloud and Seagate have devised a machine learning (ML) system to predict when disks inside Google’s data centers might fail.

Despite their volatility and high fail rates, hard disc drives (HDD) are the well-liked means of housing data inside a knowledge center. 

While newer and more reliable technologies like non-volatile storage are being touted as viable alternatives, IDC predicts that data centers will increase their storage capacity by 17.8% over the subsequent few years, with HDDs leading the way.

Here’s our collection of the simplest hard disc drives for desktops and laptops
These are the simplest cloud storage services on the market
Also, check our collection of the simplest SSDs

“At Google Cloud, we all know first-hand how critical it's to manage HDDs in operations and preemptively identify potential failures,” wrote Nitin Aggarwal, Technical Program Manager, and Rostam Dinyari, AI Engineer, with Google Cloud, during a joint blog post announcing the collaboration with Seagate.

The duo outlined the new ML system that helps them identify potential disk failures to avoid any outages and disruptions to their cloud services - and note that it could soon be unrolled wider also, meaning it'd soon be possible to identify issues in other HDDs.

ML in production
In the past, engineers contend that manually sifting through the terabytes of raw telemetry data generated by the many HDDs to spot problems isn’t feasible. 

This led them to plan an automatic ML system to predict the health of the HDDs.

Together with Accenture, Google Cloud helped Seagate build a symbol of concept that supported by the 2 commonest drive types. 

The companies tested two models. One supported an AutoML Tables classifier and another was custom-developed for the project. the previous clothed to possess the upper precision of the 2 (98%) after analyzing the forecasts and predictions for a month.

While Google Cloud is using this as an example to hawk its ML tools that help put automation into production environments, the corporate said it plans to expand the system to support all Seagate drives. 

No comments:

Post a Comment