Westcoast Ignite: HPE OneSphere

THE FUTURE OF IT MANAGEMENT IS AI-DRIVEN FROM EDGE TO CORE On February 1, 2017, HPE acquired Niara to enhance security at the intelligent edge. Niara uses machine learning to characterise the “normal” behaviour of users and other entities like applications. Consider your credit card issuer. They characterise your normal behaviour – using the card for gas and meals, etc. If, suddenly, you jump to Malaysia and buy diamond rings, this is out of character and is flagged. Same with security systems. So, a series of things happen, and there is an undesirable outcome – a breach attempt. HPE use a whole series of scenarios – the situation’s data + outcome – to train the ML based characterisation system. This is known as “supervised learning”. Sadly, that’s not all that has to be done. Attackers are always adjusting their modus operandi just because of systems described above. Think human immune system – the things attacking our bodies are morphing all the time. And just like with the human immune system, the defenders must also morph too. And so, Niara does unsupervised learning too. Without training, it tries to characterise new types of attacks. In April 2107, HPE completed it’ acquisition of Nimble Storage , a provider of all-flash and hybrid –flash storage solutions. Nimble’s InfoSight product uses machine learning in two ways. Firstly, just like with the supervised learning with Niara, above, it looks at the situation data and tells if it was a bad outcome of not – a performance problem, for example. From these “training data sets”, Nimble learns what causes bad outcomes and can start to understand what may have happened should a bad outcome occur – just like a 1st/2nd level support person might do. In order to do this, Nimble doesn’t just look at logs and events from storage devices. It must gather other data from the infrastructure too. This use of ML allows Nimble to recognise when a bad outcome is about to occur and proactively report it to support. It is able to perform the tasks that 1st and 2nd level support would typically do too. Secondly, Niara uses the same techniques to proactively determine that customers are running out of storage capacity. This is really a form of proactive maintenance, where the “maintenance fix” is to add more storage. 9 For further information visit: www.ignite-westcoast.co.uk