ZeroStack uses machine learning to create self-driving clouds

The content below is taken from the original (ZeroStack uses machine learning to create self-driving clouds), to continue reading please visit the site. Remember to respect the Author & Copyright.

Cloud mania continues to grow as businesses move more and more workloads to platforms such as Microsoft Azure and Amazon Web Services (AWS). But while public cloud hype is stealing all the headlines, private data centers are quietly plodding along and growing, as well. There is so much data growth today that businesses have to invest in both public clouds and private data centers, hence the high adoption rate of “hybrid” environments. 

The landscape for public cloud services is set—Azure and Amazon have won that battle—but private data centers are in a state of change. The legacy model of buying best-of-breed components and cobbling the technology together to build a private cloud is a long, complex process that just can’t keep up with the needs of a digital organization. Turnkey private clouds are becoming increasingly popular because they give businesses an Amazon-like experience but in a private cloud model, so the data and infrastructure stays in the company data center. 

While the platforms used to build self-service private clouds continue to evolve, there is still a significant amount of overhead for the IT department to deploy, manage and optimize the infrastructure. I’ve talked to a number of businesses that have deployed a private cloud “stack” that have told me it can take up to six months of tweaking and tuning to get the deployment right. But then changes have to be made to accommodate new workloads or increased traffic, putting IT behind the eight ball once again. 

ZeroStack’s private cloud managed by AI 

This week, ZeroStack announced the first-ever private cloud stack managed by an artificial intelligence (AI) “learning engine,” delivering a true self-driving environment. ZeroStack’s solution involves on-premises hardware and software that is managed by a cloud-based, self-service portal. This “cloud-managed” platform has enabled the company to collect, monitor, analyze and model over 1 million objects over the past 18 months. ZeroStack has taken this experience and all that data and used it to build its own AI known as Z-Brain. The smart folks working at ZeroStack have leveraged the data to build algorithms to productize predictive models to help improve both short- and long-term decision making. As someone who has his own Z-Brain, I can appreciate how powerful this can be! 

The solution will continue to collect telemetry data and leverage machine learning to provide new insights that can help customers have a better-running private cloud. Changes can then be fully automated or recommended to organizations that aren’t comfortable with an AI making decisions about their data centers. 

With all the hype out there about AI, it is refreshing to see ZeroStack talk about how it develops its algorithms and is essentially building best practices into its software. 

What ZeroStack’s Z-Brain does 

The Z-Brain provides self-driving capabilities in the following areas: 

  • Capacity planning. The AI does three types of capacity planning: infrastructure utilization, project-based capacity planning and an infrastructure advisor to help with future needs.
  • Zero touch upgrades. No intervention from the IT organization is needed because the Z-Brain handles the upgrades of all the software modules in the ZeroStack solution. If you have tried to manage a complex software stack, you know how much time this can save.
  • Efficiency optimization. Virtual machines can be “auto-sized” to specific workloads, preventing organizations from using more resources than necessary. 

The above features are available to customers in the latest release, but as they say in infomercials, “But wait, there’s more.” ZeroStack 3.0 will use the AI capabilities to build cloud optimization capabilities that can determine the best cloud to run specific workloads based on cost and performance. Version 4.0 will include automated performance troubleshooting where the root cause of application performance issues can be identified quickly and remediated, maximizing cloud uptime. 

ZeroStack’s mission has been to lower the burden on the infrastructure and optimization teams with respect to running a private cloud. The AI can offload many of the day-to-day operational tasks that weigh down IT today. As the complexity of data centers continues to increase and the business demands become more challenging to meet, ZeroStack’s AI-driven approach will become a key requirement of running a private cloud.

Join the Network World communities on




to comment on topics that are top of mind.