Virtual machines (VM) on a Cloud platform can be influenced by a variety of factors which can lead to decreased performance\nand downtime, affecting the reliability of the Cloud platform. Traditional anomaly detection algorithms and strategies for Cloud\nplatforms have some flaws in their accuracy of detection, detection speed, and adaptability. In this paper, a dynamic and adaptive\nanomaly detection algorithm based on Self-Organizing Maps (SOM) for virtual machines is proposed. A unified modeling method\nbased on SOM to detect the machine performance within the detection region is presented, which avoids the cost of modeling\na single virtual machine and enhances the detection speed and reliability of large-scale virtual machines in Cloud platform. The\nimportant parameters that affect the modeling speed are optimized in the SOM process to significantly improve the accuracy of the\nSOM modeling and therefore the anomaly detection accuracy of the virtual machine.
Loading....