Intelligent Automated Diagnosis of Client Device Bottlenecks in Private Clouds
This work addresses network troubleshooting for private cloud administrators, but it appears incremental as it applies existing machine learning methods to a specific domain.
The paper tackles the problem of diagnosing client device bottlenecks in private clouds by presenting an automated system that uses TCP packet traces and SVM classifiers, achieving 98% diagnostic accuracy in experiments.
We present an automated solution for rapid diagnosis of client device problems in private cloud environments: the Intelligent Automated Client Diagnostic (IACD) system. Clients are diagnosed with the aid of Transmission Control Protocol (TCP) packet traces, by (i) observation of anomalous artifacts occurring as a result of each fault and (ii) subsequent use of the inference capabilities of soft-margin Support Vector Machine (SVM) classifiers. The IACD system features a modular design and is extendible to new faults, with detection capability unaffected by the TCP variant used at the client. Experimental evaluation of the IACD system in a controlled environment demonstrated an overall diagnostic accuracy of 98%.