Neural Network Based Classification of Virtual Machines in IaaS

Machine Learning algorithms are being widely used to make intelligent systems. In Cloud Computing, issues like server consolidation, load balancing and virtual machine to physical machine mapping have been addressed using clustering analysis which is unsupervised learning. It is important that Cloud Service Providers address these challenges in order to provide enhanced user experience and superlative Quality of Service. Neural Networks, which fall under supervised learning algorithms, have emerged tremendously and are used in different areas such as Bio-Informatics, Pattern Recognition and Classification. Using Neural Networks and Back Propagation Algorithm, this work classifies different types of virtual machines that are providing heterogeneous services. Further, the technique is compared to K-means Clustering Algorithm which groups similar types of virtual machines into several clusters. The objective of this work is to form labeled clusters of virtual machines with the help of Neural Networks based on their types and loads and perform server consolidation. The proposed work achieves higher performance in terms of number of virtual machine samples correctly classified, as compared to K-Means Clustering algorithm. Migrating dissimilar virtual machines onto a single physical host improved machine utilization with the trade-off of slight increase in response time of the machines.