Wi-Fi and Wireless LANs are ubiquitous in today’s businesses and are also used extensively by consumers in their homes. In most cases, the expectations by users about their Wi-Fi is for it to perform well. If there is an occasional problem with either their performance or the ability to connect, they will call their IT support or service provider to correct the issue.
While this is acceptable for these types of users, this situation is simply not acceptable for industrial, medical or large business critical applications. For these types of applications, Wi-Fi is mission critical, it must work all the time and optimized for the performance needed by the application.
In these mission critical network environments, Wireless LANs are probably the most dynamic that IT teams have ever had to manage. New devices are introduced constantly, with no signs of easing up. The growth and variety of Wi-Fi-enabled devices and applications is exponential, i.e., there are already the more mobile devices than people on Earth. From point-of-sale devices to scanners, RFID systems, video conferencing systems, VoIP systems, industrial sensors, and robots the “Internet of Things” makes for exponentially more complex networking environments than ever before.
This constantly changing RF environment, coupled with typical end-user problems with Wi-Fi connectivity and performance, puts a heavy burden on IT teams as troubleshooting involves cryptic commands and hundreds or thousands of settings to navigate. All told, current solutions require deep technical know-how to control access, prevent misuse, implement end-to-end security and optimize performance.
The solution to this significant problem is to use artificial intelligence (AI) to manage and control the Wi-Fi network. KodaCloud has over four years’ experience in doing this for over 150 companies across North America. At the core of the KodaCloud eNOC AI Wi-Fi solution is a machine learning-based engine that runs patent-pending predictive analytics technology. The engine learns the typical characteristics or behaviors of devices, environment, and the network that impacts a Wireless LAN’s performance.
To access the same level of intelligence solely from a team of humans would be virtually impossible. Statistical data or real-time information is communicated to the cloud, while the customer’s data and content remain untouched. Once in the cloud, this information is processed in the ML Engine, in real-time as network performance indicators. The information is organized, processed, and translated into solutions that trigger specific actions or actionable alerts, or automatically optimize and heal the network. By correlating the wide variety of data that can be gathered, the system quickly learns to identify issues with device compatibility, interoperability, access, use/misuse, and network security – as well as gaps in coverage or capacity in the network.
The algorithm and process used by the KodaCloud AI can be visualized as a constant circle of monitoring, detection, root cause analysis, correction and threshold updating as per the diagram below.
With this power at hand, mission critical Wi-Fi networks can be managed at machine speed and issues based on connectivity or performance can be “fixed” without IT intervention and as the solution is constantly monitoring trends many issues can be resolved long before they are end user or end device affecting.
KodaCloud’s AI based eNOC service provides advanced WLAN Quality of Experience (QoE) current and historical trend monitoring and alarming. Per device QoE analysis includes deviation from expected AP-Device RF link traffic rate performance levels, anomalies in device network attachment behavior, security/LAN related device authorization abnormalities. The eNOC service will automatically provide root cause analysis for any end device impacting QoE issues and formulate mitigation recommendations.
Some of the QoE intelligent analytics capabilities include:
- Intuitive visualization of current and historical device QoE state for each location.
- Historical recording of all device KPIs and WLAN attachment events for each location.
- Auto-correlation of KPIs grouped in common device QoE root causes.
- Analysis of actual 802.11 physical layer data rates behavior for each device. Deviation from expected values given measured site RF parameters.
- Analysis of Device and AP rate adaption abnormalities causing spread of data rate selection.
- Analysis of Wi-Fi frame integrity failure and impact on actual available traffic capacity to each client devices at any given time.
- Analysis of dynamic sharing of channels by the onsite devices, neighbor WLAN networks and non-Wi-Fi devices.
- Analysis of coverage issues affecting end users.
- Analysis of temporal noise impairments affecting end users.
- Analysis of hidden node situation causing client link impairments.
- Analysis of authentication failures and specific Wi-Fi capabilities mismatch.
- Misalignment of device firmware baseline.
- Restart of specific APs or radios.
- Re-configuration of WLAN IP networking servers.
- Capacity increase with specific location AP addition and/or traffic rate, load balancing setting changes.
- Adjustment of WLAN controllers RRM parameters.
- Band specific configuration optimization.