WAN Issue Prediction via Service Provider Connection Swapping Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network management systems struggle to distinguish between Wide Area Network (WAN) issues and service provider issues as the root cause of network access server (NAS) devices continuously swapping between different service providers in WiFi-only networks.
Innovation Solution
A network management system (NMS) that obtains connection event data for NAS devices, detects connection swaps between different service providers, and predicts a WAN issue based on the number of swaps satisfying a threshold, generating a notification for administrators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the NMS monitors connection events of NAS devices to detect service provider swapping, then the ability to identify network issues is improved, but the complexity of the monitoring system increases
Solution Approach 1:
The patent segments the monitoring system into distinct functional modules: a connection event data obtaining module, a connection swap detecting module, and a WAN issue predicting module. Each module handles a specific aspect of the monitoring process, making the overall system more manageable and maintainable while achieving precise issue identification through coordinated operation of these specialized components
Solution Approach 2:
The system performs preliminary actions by obtaining and analyzing connection event data before a WAN issue fully manifests. By detecting connection swaps between service providers in advance and predicting potential WAN issues proactively, the system enables early intervention and troubleshooting, improving identification accuracy without requiring complex real-time analysis infrastructure
2Loss of information
If the NMS uses WiFi-only data from AP devices to infer WAN issues, then the visibility into the WAN is improved for WiFi-only networks, but the reliability of the inference may deteriorate due to lack of direct WAN visibility
Solution Approach 1:
The patent uses connection event data from service providers as an intermediary indicator to infer WAN status. Instead of directly monitoring WAN parameters, the system observes the health and stability of service provider connections to NAS devices, using these connection events as indirect but reliable signals of WAN issues. This intermediary approach maintains inference reliability by focusing on observable connection behaviors that directly reflect WAN performance
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring connection event data and comparing it against expected patterns. When connection swaps between service providers are detected, the system analyzes the frequency and pattern of these swaps to confirm WAN issues, creating a feedback loop that validates inferences against actual network behavior, thereby maintaining high reliability despite using indirect WiFi-only data
3Measurement precision
If the NMS detects a high number of connection swaps to predict WAN issues, then the accuracy of WAN issue prediction is improved, but the false alarm rate may increase
Solution Approach 1:
The patent employs parameter changes by analyzing multiple aspects of connection swap behavior rather than relying on a single threshold. The system examines the frequency of swaps, the specific service providers involved, the timing patterns, and the duration of connection sessions. By changing and comparing multiple parameters simultaneously, the system achieves high prediction accuracy while filtering out false alarms that would result from simple threshold-based detection
Data Source
AI summary
Techniques are described for predicting a wide area network (WAN) issue based on detection of service provider connection swapping. A cloud-based network management system (NMS) obtains connection event data for one or more network access server (NAS) devices at a site, where each event included in the connection event data comprises a connection or disconnection event of a connection session provided by a service provider. The NMS detects a number of connection swaps in the connection event data over a time window, where a connection swap includes a change from a first connection session provided by a first service provider to a second connection session provided by a second service provider. Based on the detected number of connection swaps satisfying a threshold, the NMS predicts a root cause of the connection swaps as a WAN issue and generates a notification of the predicted root cause of the connection swaps.