Diagnosing client faults using SVM-based intelligent inference from TCP packet traces
This work addresses network troubleshooting for IT professionals by enabling rapid, client-agnostic fault diagnosis, though it is incremental as it applies existing SVM methods to a specific domain.
The paper tackled the problem of diagnosing client device faults causing network performance issues by using SVM-based inference from TCP packet traces, achieving 98% accuracy in identifying client faults in healthy links.
We present the Intelligent Automated Client Diagnostic (IACD) system, which only relies on inference from Transmission Control Protocol (TCP) packet traces for rapid diagnosis of client device problems that cause network performance issues. Using soft-margin Support Vector Machine (SVM) classifiers, the system (i) distinguishes link problems from client problems, and (ii) identifies characteristics unique to client faults to report the root cause of the client device problem. Experimental evaluation demonstrated the capability of the IACD system to distinguish between faulty and healthy links and to diagnose the client faults with 98% accuracy in healthy links. The system can perform fault diagnosis independent of the client's specific TCP implementation, enabling diagnosis capability on diverse range of client computers.