What is a Dynamic Baseline?

A dynamic baseline uses AI to establish a network connectivity and performance baseline without relying on generic default threshold values. The baseline is then automatically adjusted based on network and user/IoT device behavior.

AI-powered dynamic baselines explained

Dynamic baselines use AI and machine learning (ML) on network data to establish what’s normal for that network (a “baseline”). The baseline dynamically self-adjusts to minimize false negatives and positives.
  • Instead of using default thresholds that can be set artificially low, a dynamic baseline provides near real-time visibility per site based on real Wi-Fi, wired, and WAN activity.
  • Each network device and endpoint client provide telemetry that helps understand what is working and where there is room for optimization.
  • AI and ML are then used to identify where a network device, endpoint client, user, or app/service may be having a problem and why.
AI-powered baseline

Why dynamic baselines?

In a traditional environment, IT relies on keeping the network running and delivering the best experience possible by gut feel and setting alert thresholds for individual items. AI and automation are changing the game. Here’s why dynamic baselines are important:

  • Static thresholds are unable to provide the visibility needed to identify problems in distributed and changing environments.
  • Due to a network’s dynamic nature, automation is the only viable way to monitor and identify anomalies.

The advantages of dynamic baselines

Imagine deploying a network today and using the same thresholds as every other environment—big and small—on which to base your network’s performance. Do pre-defined thresholds account for devices roaming or the number of IoT devices in the environment? Or the number and type of APs and class of switches used?

Dynamic baselines offer:

  • Automation that collects data directly from your environment.
  • An easy way to see how individual locations are performing over time.
  • Visibility into how similar sites compare to each other (e.g., stores, classrooms, remote offices) as well as to comparable 3rd party sites (e.g., cloud-enabled peer comparisons).

Automated Experience Level Agreements to eliminate manual setting and adjustment of service level thresholds based on artificial levels.

What is the difference between Experience Level Agreements and Service Level Agreements?

Experience Level Agreements offer more granular, automated benefits compared to traditional Service Level Agreements or Service Level Expectations, including:

AttributeAI-powered dynamic baselinesTraditional SLAs / SLEs
Thresholds and alertsAutomatically and dynamically set as an environment changes.Set and adjusted manually with dependency on generic defaults.
Real-time baselines per locationIncludedNo—uses pre-defined, default threshold values.
Multi-dimensional data pointsIncluded, with the ability to offer outcomes (root cause, remediation, etc.).No—requires stringing together data points & manual troubleshooting.
Peer comparisonsIncluded, with optimization benefits.No
FocusUser-centric valueTechnology-centric process measurement.

Ready to get started?