Juniper uses Mist AI and Marvis to facilitate network user experience
Juniper Networks is expanding its artificial intelligence (AI) capabilities to make it easier for businesses to manage wired and wireless networks on their campuses and while providing administrators with more information and automation tools.
The expansion of the provider’s Mist AI portfolio and Marvis platform this week is part of its broader Experience First Networking initiative, aimed at shifting the focus of network management from how the network operates to the user and operator experience. AI is a key part of the strategy.
“The complexity increases – more devices, the more you see the IoT [Internet of Things] coming into play, adding to mobility, ”said Christian Gilby, senior director of product marketing for Juniper’s AI-based company. Corporate networking planet. “I want to make it easier for IT teams to manage the network and understand what’s going on. It really covers our portfolio for the company. … At the end of the day, the results we are aiming for are truly confident experiences. It is automation and ultimately the evolution towards an autonomous network. I don’t think everything will be stand-alone and the network will work on its own, but there are definitely areas where we can take advantage of this to make it easier to operate the network.
Buy haze for AI
Juniper quickly expanded its AI capabilities by buying Mist in 2019 for $ 405 million, with the goal of injecting AI into its entire network portfolio. At the time of the acquisition, Mist was focused on using AI for wireless LANS, but Juniper’s officials saw an opportunity to push AI across the entire IT stack and advance solutions for it. supplier management. It also dovetailed with Juniper’s cloud ambitions, which were amplified by the COVID-19 pandemic and the ensuing accelerated shift to cloud services as IT environments became even more distributed.
As businesses envision a post-pandemic IT environment, they are seeing a new trend of hybrid working and are even considering downsizing their central office sites and adding satellite offices, Gilby said. The key to this will be agility, which Juniper aims to drive with updates to Mist AI and the Marvis AIOps platform.
The vendor envisions AI-driven management of campus networks, which are under pressure from the growing number of mobile users and IoT devices. EVPN-VXLAN technology can help fabric management by being an overlay on top of the physical network infrastructure, but it is also complex to deploy and manage, according to Juniper. The company aims to enable EVPN-VXLAN management through its Mist Wired Assurance cloud service for wired, wireless and WAN networks.
Read also : Bring hyper-automation to ITOps
Facilitate EVPN-VXLAN management
Juniper’s EVPN-VXLAN structures use the same technology – Juniper Mist Wired Assurance and Marvis Virtual Network Assistant – as that offered by the vendor to manage wired access on campus. The offerings provide network administrators with enhanced automation, analysis and troubleshooting capabilities. The goal is to bring a more modern management capacity to an architecture that was not designed for what is happening today in IT.
“Mobility was not really important when the architecture was designed; IoT wasn’t even a thing, “Gilby said, adding that Mist AI’s capabilities are about” the need for a dynamic environment. You have more devices connecting to the network. You must be able to secure it. When you look at many of these security flaws over the past few years, it comes down to IoT devices because a lot of shortcuts come due to the cost people face. You have to be able to segment the network and that’s where the complexity comes in. VLANs work to a degree, but they just don’t scale, so we’re starting to see a need for micro-segmentation. Moreover, how to secure it? Access control lists have traditionally been used, but again, it’s a very static way of thinking about the network. “
The Juniper EVPN-VXLAN fabric provides a common operational framework for all wired access deployments, configurations and Day 2 operations, as well as a unique AI-based support model that includes auto-operations. driving and predictive actions. By moving EVPN-VXLAN into Mist Fabric Manager, administrators can perform tasks such as choosing a topology, defining networks of interest, identifying physical connections, and enforcing underlying policies.
For segmentation, Juniper opted for a standards-based IPv6 rather than developing its own overlay, and then leveraging Juniper Mist Cloud to simplify the process of bringing a switch into the network, Gilby said. The company is also using its AI capabilities to help meet Service Level Expectations (SLEs) by understanding the traffic passing through the network through metrics and telemetry to detect and resolve issues and anomalies before they go. they don’t become problems.
“The area that a lot of vendors haven’t really focused on is network operation and that was key with Mist,” he said. “When we went out of wireless, we really focused on, ‘You can design and deploy the network, but you have to make it easier for the team to manage the network, to get the information they need to know what is. happens, because that’s where they spend a lot of their time.
User experience is the key
It’s a key differentiator for Juniper, according to Gilby.
“A lot of vendors are talking about AI and algorithms,” he said. “What we really focus on is what AI can do for a customer. This is where all of us as sellers really have to move on, figuring out what the benefit to the customer is, because it’s okay to say you’re forward thinking and using AI, but how does this translate into a result for the company? We’ve been there and will continue to do more, because that’s what’s going to accelerate customers’ transition to it.
Marvis is Juniper’s AIOps Network Assistant and Marvis Actions is a dashboard used to monitor and manage the health of a Juniper Mist network, including wired, wireless, and software-defined (SD-WAN) WANs. It leverages the information generated by the Mist AI engine, such as identifying the root cause of a problem, and provides actionable recommendations to IT managers.
Juniper has added functionality to Marvis since its introduction in 2018 to address common issues such as misconfigured VLANs, non-compliant software, and offline devices. The company added nine new actions to address issues such as persistent wireline and wireless client failures, faulty cables, coverage holes in access points (APs), poor WAN links, and insufficient RF capacity. .
Cover holes can be a challenge for businesses, Gilby said. An access point can be placed in an area where there is interference with the signal. Marvis is designed to detect user experience.
“In fact, we are not only looking at the AP to AP connection – all APs will listen to see if they have a peer and create a map – we are also looking at the user experience,” he said. “Maybe the access points can hear each other, but there are metal conduits blocking the signal for customers. This is where it is important to look at the user experience as well to detect these coverage holes.
Read more : The future of network management with AIOps