Mist today announced the addition of several new enhancements to the company’s Wi-Fi Assurance and Marvis Virtual Network Assistant (VNA) services that bring unprecedented insight and automation to wireless networks. New features include an expanded conversational UI leveraging Natural Language Processing (NLP) for enhanced queries and insight, anomaly detection using deep learning to proactively identify and fix problems without false positives, AI-driven Radio Resource Management (RRM) for automated self-healing and new Wired and Wide Area Network (WAN) classifiers that augment the extensive range of service levels available via the Mist platform. With the Mist Learning Wireless LAN (WLAN), Wi-Fi is more predictable, reliable and measurable than ever, with proactive automation and insight that saves IT time and money.
According to Gartner, “The intricacy of access layer network decisions and the aggravation of end-user downtime are more than IT organizations can handle. Infrastructure and operations leaders must implement automation and artificial intelligence solutions to reduce mundane tasks and lost productivity.”1
“While other vendors are trying to bolt AI on top of legacy platforms, Mist built an AI engine from scratch on top of a real-time microservices cloud platform,” said Sudheer Matta, vice president of products at Mist. “This eliminates the need for expensive overlay hardware and software, it saves time and money with elastic scale and it provides unprecedented feature agility. Only Mist is able to roll out groundbreaking new features with relability and stability in weeks instead of months or years, bringing incredible value to Mist customers.”
Mist uses various techniques like Natural Language Processing, Machine Learning, Deep Learning, and Data Science to deliver the best Wi-Fi experience to end users, IT administrators and Managed Service Providers (MSPs), putting ever increasing business-critical services on top of their wireless networks. The latest enhancements expand upon Mist’s extensive leadership in this space by bringing the following unique capabilities to customers:
- Expanded Natural Language Processing (NLP). Mist is the only vendor to offer an AI-driven
virtual network assistant (Marvis), which provides unsurpassed insight
into WLAN behavior and expert guidance for rapid Wi-Fi
troubleshooting. Marvis uses NLP to provide IT administrators with
detailed answers to complex questions without having to hunt through
endless dashboards or Command Line Interfaces (CLI).
Marvis has been continuously learning since first launched in February 2018, and can now understand and answer hundreds of requests with incredible success rates, such as “What is wrong with Jon’s iPhone?”, “How is the Access Point in the conference room doing?” and “How many devices are having throughput issues?”. With tens of thousands of Access Points already feeding the Mist AI engine (and growing), Mist has a big lead on the competition with the best knowledge graphs for Wi-Fi.
- Anomaly detection with deep learning. The latest version of Marvis uses deep learning to
identify and correlate items, events or other observations that do not
conform to expected patterns and predict future events based on the
sequence of past states. By leveraging the industry’s most advanced
data science algorithms, Mist detects and reports anomalies with almost
zero false positives.
The Mist Learning WLAN is 100% API driven, enabling workflows (e.g. help desk tickets and notifications) to be automatically kicked off when anomaly thresholds are triggered. This helps IT staff get ahead of problems and fix them before users even know they exist.
- AI-driven Radio Resource Management (RRM). Innovation in RRM, which is the system level management
of radio resources, has been stagnant in WLANs for the past fifteen
years. It is constrained by incomplete data and lacks insight into
the user experience – i.e. did the RRM change make things better or worse
for the Wi-Fi user? This all changes with Mist, who is the first and
only vendor to use AI to create “self-healing” WLANs with quantifiable RRM
benefits.
The Mist Wi-Fi Assurance Service is constantly collecting RF information like coverage, capacity, throughput and performance on a per user basis, then using deep learning to understand the data and make automated changes based on real-time requirements. Customizable Wi-Fi service levels measure the impact of these changes so that the user experience is always optimized. For the first time ever, the wireless network can detect RF issues, learn from them, automatically make the changes using AI and then measure the results as quantifiable end user benefits.
- WAN Service Level Expectations (SLEs). Mist is the only vendor with customizable Wi-Fi service
levels. These SLEs, which are part of the Mist Wi-Fi Assurance
service, have traditionally covered key metrics like Capacity, Coverage,
Throughout, Latency, AP uptime and Roaming. Now the Mist platform
also lets IT administrators set, monitor, and enforce SLEs for Wide Area
Network (WAN) performance. With this new SLE, customers can easily
determine if WAN latency, jitter and/or packet loss are having an adverse
impact on the user experience, when these problems are occurring, if they
are likely to happen in the future and how best to address them for an
optimal user experience.
Mist recently announced that it is working with leading vendors like VMware and Juniper to create a seamless experience from the WLAN to the WAN. Now Mist customers looking for more insight into how WAN performance relates to the Wi-Fi user experience can leverage the joint solutions for end-to-end visibility and automation.
Availability
The above features are available today and come standard with the appropriate Mist
subscription service(s) for new and existing customers.
1 Gartner ‘Automation and AI Will Slash Access Layer Downtime and the Reliance on Network Administrators,’ by Tim Zimmerman, Vivek Bhalla, November 30, 2017
Source: Mist media announcement
