In enterprise WiFi, a three-year old start-up called Mist claims to shaking up the economics of planning and optimizing corporate WLANs, in the same way that others are doing for cellular networks. Its approach moves the bulk of the network logic to the cloud, then uses open source big data tools to collect and analyze millions of data points, applying machine learning too. All this can then retune an enterprise or campus WiFi environment automatically and on the fly.
We talked to Jeff Aaron, VP of marketing at Mist, just as they opened for business in Europe last week, having landed some key accounts in the 18 months since they first went commercial in the US. Those US accounts include Amazon, Facebook and Mercedes Benz.
The company has two main product sets, targeting WiFi, and also Bluetooth Low Energy (BLE) for IoT applications. The latter claims to eliminate the complexity in implementing beacons to support location-based apps for retailers, health departments and hospitality suites, among others. It uses a patented dynamic BLE 16-antenna array which, when combined with machine learning in the cloud, gives location accuracy of below one meter with sub-second latency, using ‘virtual beacons’ that are calibrated automatically in real time.
A US pet store chain with 1,500 stores is using the BLE and WiFi systems together across its entire US operation, to enforce key metrics like time to connect, throughput and roaming; allow rapid guest access; and support capacity for hand scanners and printers.
Mist went up against Aerohive, Meraki and Aruba to win this particular retailer deal, and these are its main competitors. It can use access points from Cisco (which owns Meraki) as well as its own, with a layer of its own software running on them. “We don’t want to be in the hardware AP business,” Aaron insists.
Today the APs have to be bought from Mist, because it requires one or two adjustments to the Broadcom 802.11ac chips to accommodate the transfer of metadata into the cloud.
“We rewrote the control plane and can completely control the user experience, for instance guaranteeing sub-2 second connect time, or 10Mbps at each device. And if this is physically impossible to achieve, the AI in the cloud can recreate the problem and work out a strategy that will likely fix it and makes recommendations to the APs to change in real time,” Aaron continued. “It even offers the support team natural language processing to talk the virtual network assistant. It can even do prediction on a particular workload and tell you what you need to change in a configuration if it is not possible with the current one.”
This is somewhat analogous to in-home multi-access point WiFi, which uses client steering and band steering to get as close to the theoretical speed maximums by sharing load balancing workloads from different mobile clients, dynamically. These at present don’t use machine learning, but if ML converges with home multi-AP configurations, Multiuser-MIMO and reporting to the cloud, the home will have moved to almost precisely the same spot that enterprise WiFi has reached.
Until Cisco bought Meraki system, it used a local controller system to manage load balancing and roaming, but with improved broadband speeds this can now be shifted to the cloud, so enterprise, like consumer WiFi, runs on multiple APs locally and a cloud controlling app. “AI used like this has a potential applicability in the home space,” Aaron confirmed, and said the company was now working with Verizon, but mostly on enterprise systems.
Mist has been shipping for 18 months and has 300 customers, 30 of which are in the Fortune 500 and is looking at Europe for WiFi, applications for its virtual network assistant, BLE engagement and asset tracking and Aaron says there are lots more use cases where AI can work with WiFi.