University of Reims Champagne Ardenne
Improving resource provisioning of heterogeneous cloud infrastructures is an important research challenge. The wide diversity of cloud-based applications and customers with different QoS requirements has recently exhibited the weaknesses of current provisioning systems. Today's cloud infrastructures provide provisioning systems that dynamically adapt the computational power of applications by adding or releasing resources. Unfortunately, these scaling systems are fairly limited: They restrict themselves to a single type of resource; they are unable to fulfill QoS requirements in face of spiky workload and they offer the same QoS level to all their customers, independent of customer preferences such as different levels of service availability and performance.