Adaptive Solutions to Resource Provisioning and Task Allocation Problems for Cloud Computing




Desmarais, Ronald J.

Journal Title

Journal ISSN

Volume Title



With the emergence of the cloud computing paradigm, we can now provide dynamic resource provisioning at unprecedented levels of scalability. This flexibility constitutes a rich environment for researchers to experiment with new designs. Such experimental novel designs can take advantage of adaptation, controllability, self- configuration, and scheduling techniques to provide improved resource utilization while achieving service level agreements. This dissertation uses control and scheduling theories to develop new designs to improve resource utilization and service level agreement satisfaction. We optimize resource provisioning using the Cutting Stock problem formulation and control theory within feedback frameworks. We introduce a model-based method of control to manipulate the scheduling problem’s formulation model to achieve desired results. We also present a control based method using Kalman filters for admission control. Finally, we present two case studies — the Yakkit media social application and the Rigi Cloud testbed for deploying virtual ma- chine experiments. The results of our investigations demonstrate that our approaches and techniques can optimize resource utilization, decrease service level agreement violations, and provide scheduling guarantees.



Adaptive, Cloud, Scheduling, Control, Provisioning, Resource Management