Dynamic Wireless Traffic Rerouting via ML Mobility Path Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless networks face frequent roaming failures due to environmental changes and client device mobility, leading to connectivity issues and disruptions in user experience.
Innovation Solution
A machine learning-based system that analyzes mobility paths in wireless networks, computes mobility path failure metrics, and triggers reroutes to alternate paths with lower failure metrics, reducing roaming failures and enhancing user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If client devices roam between access points based on signal quality, then connection quality is improved, but roaming failures increase due to environmental changes and mobility
Solution Approach 1:
The system performs preliminary analysis of mobility paths using historical roaming data and machine learning models to identify failure-prone paths before actual roaming occurs. This allows the network to proactively reroute clients away from paths likely to fail, rather than reacting after failures occur.
Solution Approach 2:
The system implements a feedback loop where roaming failure data is continuously collected, analyzed by machine learning models, and used to update mobility path metrics. These updated metrics then influence future roaming decisions, creating a closed-loop system that learns from past failures and improves over time.
2Ease of operation
If traditional roaming protocols are used, then network simplicity is maintained, but user experience deteriorates due to connectivity disruptions
Solution Approach 1:
The system introduces a network assurance service as an intermediary layer between traditional roaming protocols and client devices. This service analyzes mobility paths and provides routing guidance without requiring changes to standard roaming protocols or client device behavior, thus improving user experience while maintaining protocol compatibility.
Solution Approach 2:
The system segments the roaming decision-making process into two parts: traditional signal-quality-based decisions remain at the client level, while the new machine learning-based mobility path analysis operates as a separate network-level service. This segmentation allows enhanced functionality without complicating the fundamental roaming mechanism.
3Reliability
If machine learning-based mobility path analysis is implemented, then roaming failures are reduced, but computational resources and system complexity increase
Solution Approach 1:
The system applies machine learning-based analysis selectively to identify only the most critical failure-prone paths rather than analyzing all possible roaming paths. This partial action approach provides sufficient improvement in reliability while limiting computational overhead to what is necessary for the most impactful interventions.
Data Source
AI summary
In one embodiment, a service receives data indicative of roaming failures along mobility paths in a network. The mobility paths represent ordered series of wireless access points via which wireless clients have accessed the network over time. The service uses, based on the data indicative of the roaming failures, a machine learning-based model to associate mobility path failure metrics with portions of the mobility paths. The service identifies, for a first mobility path, an alternate mobility path that has a lower mobility path failure metric than that of the first mobility path. The service triggers a mobility path reroute for a particular client device in the network on the first mobility path to the alternate mobility path.