Closing In on the Autonomous Data Center

    Of all the changes coming to the data center, perhaps none is as futuristic as autonomy. The idea that users, whether they be humans or machines, can simply request the resources they need in order to complete a given task and the data center automatically provisions them cuts to the very heart of IT’s core function.

    But is this scenario realistic? And exactly how does this differ from the broad adoption of automated processes that has been going on for years?

    For those who may think that data center autonomy is still some years away, the fact is that solutions are already hitting the channel. As data environments scale in both size and complexity, many organizations are finding that varying levels of autonomy are necessary just to keep basic services afloat, and tech vendors are moving quickly to make it happen. Flash storage firm Kaminario, for instance, recently teamed up with Splunk to produce a new app that merges an intuitive dashboard with advanced analytics to enable real-time scale and performance adjustments for machine learning and IoT infrastructure. The goal is to enable eliminate bottlenecks and optimize resource utilization by taking over many of the manual monitoring and configuration tasks that currently hamper real-time system performance.

    Meanwhile, HPE is touting the latest advances to its InfoSIght predictive analytics platform as the next step toward the autonomous data center, says SDX Central’s Jessica Lyons Hardcastle. The platform was originally developed by Nimble Storage, which HPE acquired earlier this year, as a means to drive data center operations through a mixture of sensor-driven data collection and artificial intelligence. One of the newest additions to the platform is a “recommendation engine” that will instruct IT on ways to preemptively avoid potential performance issues and optimize resource consumption. Expect the platform to become a standard feature on the 3PAR storage system where it will be able to leverage cross-stack analytics capabilities and global visibility into the 3PAR installed base.

    None of the current platforms on the market provide full end-to-end autonomy, nor do they completely cut humans out of the management process for the areas they do cover. But this is to be expected considering there is no fine line between a manual and self-functioning data environment. In fact, says CA’s Ashok Reddy, the autonomous data center can be expected to evolve along the same lines as the autonomous car, going from a Level 1 status involving network monitoring, which would be akin to cruise control or driver-assisted brakes, and proceeding up to the hands-free operations of a Level 5 environment in which humans need only become involved in the most unusual circumstances. It will take some time to complete this transition, of course, but this will allow IT to adjust to the new paradigm gradually with, hopefully, little to no disruption.

    Those contemplating autonomous data operations should also take into consideration the fact that the data ecosystem is no longer confined to the data center. Hybrid clouds are quickly emerging as the infrastructure-of-choice for the enterprise, which means autonomous platforms will have to become highly adept at navigating distributed infrastructure. A key consideration in this movement is the interconnect between local and remote resources, says Oracle’s Pragnesh Panchal. Automated environments work best when there is direct, consistent and predictable connectivity between endpoints, which will likely require the enterprise to shed the public internet as a means to access the cloud in favor of private, dedicated networks.

    It might seem like the autonomous data center is coming completely out of the blue, but in fact it is a continuation of the automation that has taken hold across many aspects of the data stack. The biggest difference is that machines will no longer have to wait for instructions to carry out predefined tasks but will be able to react and respond to changing conditions on their own, although still within predefined limits.

    Going forward, then, it seems that the biggest question for IT executives is not whether to embrace autonomy, but by how much.

    Arthur Cole writes about infrastructure for IT Business Edge. Cole has been covering the high-tech media and computing industries for more than 20 years, having served as editor of TV Technology, Video Technology News, Internet News and Multimedia Weekly. His contributions have appeared in Communications Today and Enterprise Networking Planet and as web content for numerous high-tech clients like TwinStrata and Carpathia. Follow Art on Twitter @acole602.


    Arthur Cole
    Arthur Cole
    With more than 20 years of experience in technology journalism, Arthur has written on the rise of everything from the first digital video editing platforms to virtualization, advanced cloud architectures and the Internet of Things. He is a regular contributor to IT Business Edge and Enterprise Networking Planet and provides blog posts and other web content to numerous company web sites in the high-tech and data communications industries.

    Latest Articles