AI Node Failure Prediction and Ticket Triage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network monitoring systems rely on manual and reactive approaches for identifying and addressing faults, leading to inefficiencies in maintenance and repair, particularly due to the complexity of integrated communications technologies and the lack of a unified view of network element alarms and ticket events.
Innovation Solution
A system that uses artificial intelligence to predict faults by monitoring network nodes, generating network analytical records, and creating tickets for predicted failures, leveraging historical ticket data to derive predictive actions and differentiate between self-healable and non-self-healable tickets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual and reactive approaches are used for fault identification and repair, then service engineers can perform repairs based on personal experience, but network downtime increases and maintenance efficiency decreases
Solution Approach 1:
The system performs preliminary actions by predicting node failures before they occur using machine learning models that analyze historical data and current node status. This enables proactive maintenance scheduling, allowing repairs to be performed during planned maintenance windows rather than causing unexpected network downtime.
Solution Approach 2:
The system implements continuous feedback loops where node performance data, alarm events, and repair outcomes are continuously collected and fed back into the prediction models. This feedback mechanism improves prediction accuracy over time and enables dynamic adjustment of maintenance strategies to minimize network downtime.
2Adaptability or versatility
If integrated communications technologies are merged into a single data backbone network, then service concentration improves, but system complexity increases making management and maintenance more difficult
Solution Approach 1:
The system segments the complex integrated network into individual node entities, each with its own prediction model and maintenance profile. This segmentation allows the system to manage complexity by treating each node independently while still providing unified oversight of the entire network through centralized prediction and ticketing.
Solution Approach 2:
The patent introduces an intermediary layer consisting of the prediction system and ticketing platform that sits between the complex integrated network and the maintenance operations. This intermediary translates complex network states into actionable predictions and standardized repair tickets, simplifying the management interface.
3Ease of operation
If reactive repair actions are performed after failure events, then service engineers respond to actual problems, but preventive maintenance capability is lost and repair response time increases
Solution Approach 1:
The system generates repair tickets and schedules maintenance actions before failures occur based on predicted failure probabilities. This preliminary action enables maintenance teams to prepare in advance, having spare parts ready and technicians scheduled, significantly reducing actual repair response time when issues arise.
Solution Approach 2:
The system provides self-service capabilities by automatically generating diagnostic information, prediction results, and repair recommendations that guide service engineers through the repair process. This reduces the time engineers need to spend on diagnostics and enables faster, more consistent repair actions.
Data Source
AI summary
Embodiments provide for prediction and mitigation of network faults. Information associated network nodes may be compiled and used to generate network analytical records (NARs). A first model may be executed against the NARs to predict faults associated with one or more nodes of the network. Tickets are generated for predicted faults and stored in a ticket database. The tickets may be analyzed to predict executable actions to mitigate the faults associated with each ticket. To analyze the tickets, ticket data may be compiled and used to generate ticket analytical records (TARs). A second model may be executed against the TARs predict actions to resolve the predicted faults. The predicted actions may be executed to mitigate the impact that the faults have on the network, which may include preventing the faults entirely (e.g., via preventative maintenance) or minimizing the impact of the faults via use of the predicted actions.