Kenga, Derdus M.Omwenga, Vincent O.Ogao, Patrick J.2022-12-262022-12-262019Kenga, D. M., Omwenga, V. O., & Ogao, P. J. (2019). Autonomous virtual machine sizing and resource usage prediction for efficient resource utilization in multi-tenant public cloud. Int. J. Inf. Technol. Comput. Sci.(IJITCS), 11(5), 11-22. DOI: 10.5815/ijitcs.2019.05.0210.5815/ijitcs.2019.05.02https://nru.uncst.go.ug/handle/123456789/6541In recent years, the use of cloud computing has increased exponentially to satisfy computing needs in both big and small organizations. However, the high amounts of power consumed by cloud data centres have raised concern. A major cause of power wastage in cloud computing is inefficient utilization of computing resources. In Infrastructure as a Service, the inefficiency is caused when users request for more resources for virtual machines than is required. In this paper, we propose a technique for automatic virtual machine sizing and resource usage prediction using neural networks, for multi tenant Infrastructure as a Service cloud service model. The proposed technique aims at reducing energy wastage in data centres by efficient resource utilization. An evaluation of our technique on CloudSim Plus cloud simulator and WEKA shows that effective VM sizing not only achieves energy savings but also reduces the cost of using cloud services from a customer perspective.enCloud computingVirtual machine sizingIaaS cloudMulti tenant public cloudEnergy efficiencyCloudSim plusNeural networksArticle