Daleel: Simplifying Cloud Instance Selection Using Machine Learning
This addresses the challenge of cloud instance selection for customers with specific constraints and requirements, but it appears incremental as it applies existing ML techniques to a known bottleneck.
The paper tackles the problem of selecting optimal cloud instances by developing an adaptive deployment policy using machine learning to match customer demands with service offerings, resulting in an experimental study based on extensive job executions on a major public cloud.
Decision making in cloud environments is quite challenging due to the diversity in service offerings and pricing models, especially considering that the cloud market is an incredibly fast moving one. In addition, there are no hard and fast rules, each customer has a specific set of constraints (e.g. budget) and application requirements (e.g. minimum computational resources). Machine learning can help address some of the complicated decisions by carrying out customer-specific analytics to determine the most suitable instance type(s) and the most opportune time for starting or migrating instances. We employ machine learning techniques to develop an adaptive deployment policy, providing an optimal match between the customer demands and the available cloud service offerings. We provide an experimental study based on extensive set of job executions over a major public cloud infrastructure.