AI Server Diagnosis and Remote Incident Resolution in Data Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of diagnosing and addressing network failures and performance degradations in data centers is prone to human error and requires significant manual effort, leading to inefficiencies and increased operational costs.
Innovation Solution
An AI-driven system automatically generates trouble tickets, collects system event logs, and provides AI diagnosis results to remotely resolve incidents, reducing the need for manual intervention and accelerating the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual processes are used for diagnosing network failures and performance degradations, then human judgment and flexibility are maintained, but the process is prone to human error, requires significant manual effort, and increases operational costs
Solution Approach 1:
The system enables self-service through automated AI-driven diagnosis that performs fault detection, root cause analysis, and resolution actions without requiring manual intervention from operators. The automated trouble ticket generation and execution of resolution actions allow the system to service itself, eliminating manual effort while maintaining high diagnosis accuracy through AI models.
Solution Approach 2:
The patent replaces the mechanical manual process with an AI-based automated system. The AI engine analyzes event logs, patterns, and system data to diagnose failures and execute resolutions, substituting human cognitive and manual operations with automated intelligent processing, thereby reducing manual effort while maintaining or improving diagnosis reliability.
2Measurement precision
If manual troubleshooting processes are used, then detailed human analysis can be applied, but the process consumes considerable time and accelerates operational costs
Solution Approach 1:
The system performs preliminary actions by pre-defining resolution actions associated with fault patterns and proactively collecting and pre-processing event logs. When a failure occurs, the AI engine can immediately match against pre-existing patterns and execute pre-planned resolutions, eliminating the time-consuming manual analysis phase and significantly reducing troubleshooting time while maintaining high detection accuracy.
Solution Approach 2:
The automated system provides continuous monitoring and immediate response without interruption. The AI engine continuously analyzes event logs and triggers automated resolution actions as soon as fault conditions are detected, eliminating the discontinuous manual troubleshooting process where operators must manually investigate, consult, and execute fixes, thereby reducing overall troubleshooting time.
3Reliability
If vendors are involved in investigating incidents through problem tickets, then specialized expertise is brought in, but the process consumes considerable time and increases operational overhead
Solution Approach 1:
The system performs self-service by autonomously diagnosing incidents and executing resolution actions without requiring vendor intervention. The AI engine independently analyzes fault conditions, determines root causes, and implements fixes, eliminating the time-consuming process of creating problem tickets, vendor investigation, and coordinated resolution, while maintaining high resolution quality through sophisticated AI models.
Solution Approach 2:
The patent changes the fundamental parameter of incident resolution from human-mediated to automated AI-driven. By transforming the resolution process from manual vendor investigation to automated AI analysis and execution, the system maintains the quality of incident resolution while dramatically improving resolution speed and eliminating operational overhead.
4Productivity
If automated alarm filtering is implemented, then the process of identifying fault sources is accelerated, but the complexity of the system increases
Solution Approach 1:
The AI engine serves as an intermediary layer between the monitoring system and the resolution system. It receives raw alarm data, event logs, and system information, processes them through AI analysis, and outputs structured diagnostic results and resolution actions. This intermediary approach simplifies the overall system architecture by centralizing intelligence in one component rather than distributing complex logic throughout the system.
Data Source
AI summary
A trouble ticket associated with an incident is automatically triggered. A task is initiated to collect system event logs from one or more servers based on the trouble ticket. A system document is obtained that includes an event list. The event list and the system event logs are provided to an Artificial Intelligence (AI) engine for analysis. An AI diagnosis result is generated by the AI engine. The AI diagnosis result is received from the AI engine. A remote action is executed to resolve the incident based on the AI Diagnosis Result. Action result logs are obtained in response to executing the remote action. A result document is generated that includes a result of the executing the remote action. The result document is provided to the AI engine for training a model used by the AI engine to generate the AI diagnosis result.