Workload characterization, controller design and performance evaluation for cloud capacity autoscaling
Ahmed Ali-Eldin Hassan · 2015
This thesis studies cloud capacity auto-scaling, or how to provision and release re-sources to a service running in the cloud based on its actual demand using an auto-matic controller. As the performance of server systems depends on the system design, the system implementation, and the workloads the system is subjected to, we focus on these aspects with respect to designing auto-scaling algorithms. Towards this goal, we design and implement two auto-scaling algorithms for cloud infrastructures. The algorithms predict the future load for an application running in the cloud. We discuss the different approaches to designing an auto-scaler combining reactive and proactive control methods, and to be able to handle long running requests, e.g., tasks running for longer than the actuation interval, in a cloud. We compare the performance of our algorithms with state-of-the-art auto-scalers and evaluate the controllers ’ perfor-mance with a set of workloads. As any controller is designed with an assumption on the operating conditions and system dynamics, the performance of an auto-scaler varies with different workloads.