Wireless Transaction Failure Detection Using Sequential Event Rules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless communication networks, particularly during the transition to 5G, face challenges such as limited coverage areas, higher deployment costs, and slow rollout, which can be exacerbated by complex network architectures and the need for improved transaction failure detection and alerting mechanisms.
Innovation Solution
A method involving sequential rule mining and generative models is employed to derive and enhance rules for generating alerts in communication networks, utilizing a first rule set from sequential mining and a second set from a generative model to predict network function transaction events, thereby identifying causality and reducing troubleshooting delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used in wireless communication networks, then deployment costs are reduced, but detection precision of network failures and troubleshooting time are worsened
Solution Approach 1:
The system performs preliminary actions by proactively detecting network failures through sequential rule mining and generative models before they propagate. The anomaly detection system continuously monitors network function transactions and identifies potential issues early, enabling preventive maintenance and reducing overall troubleshooting time.
Solution Approach 2:
The patent replaces traditional mechanical monitoring systems with AI-based intelligent detection systems. Generative models and sequential rule mining algorithms substitute conventional threshold-based monitoring, enabling the system to learn complex failure patterns and detect anomalies with higher precision without requiring manual configuration of monitoring parameters.
2Productivity
If complex network architectures are implemented to support 5G, then network performance is improved, but device complexity and detection difficulty increase
Solution Approach 1:
The system segments the complex 5G network architecture into manageable components by analyzing network function transactions individually. Each network function (NF) and its transactions are treated as discrete units that can be monitored and analyzed separately, making the overall complex system detectable and manageable through modular anomaly detection.
Solution Approach 2:
The patent introduces an intermediary anomaly detection system that sits between the complex network architecture and the monitoring process. This intermediary layer translates complex network transactions into analyzable patterns using sequential rule mining and generative models, simplifying the detection process without requiring changes to the underlying complex network infrastructure.
3Measurement precision
If AI-based anomaly detection systems are deployed, then detection precision is improved, but use of energy and computational resources increase
Solution Approach 1:
The system applies partial action by focusing computational resources only on detecting specific anomaly patterns rather than analyzing all network transactions equally. Sequential rule mining identifies critical failure patterns, and generative models generate only relevant anomaly scenarios, reducing unnecessary computational energy consumption while maintaining high detection precision for critical failures.
Data Source
AI summary
A processing system may obtain a plurality of sequences of network function transaction events, each sequence comprising a plurality of network function transaction events in a communication network. The processing system may next apply the plurality of sequences as inputs to a sequential rule mining module implemented by the processing system to obtain a first rule set comprising at least a first rule, where the first rule indicates that a consequent network function transaction event follows an antecedent comprising one or more prior network function transaction events, and may apply the plurality of sequences as inputs to a generative model to obtain a second rule set. The processing system may then identify that the first rule is contained in the first and second rule sets, and may add the first rule to a set of active rules for generating alerts in the communication network, in response.