Analysis of Various Clustering Algorithm on Job Events Data of Google Cloud Tracelog

Abstract: The term Workload is defined as “the amount of work assigned to or done by a client, workgroup, server or system in a given time period” and consists of two components user and task. Analysis of cloud jobs and user benefits both providers and researchers as it enables a more in-depth understanding of the system. In this paper I am using clustering techniques available in WEKA tool to perform analysis. The data is taken from google cloud trace.

Keywords: Analysis, Cloud Computing, Cluster, Workload, WEKA Tool