QoS-Aware, Cost-Efficient Selection of Cloud Data Centers

Abstract

Cloud computing is increasingly used to deliver multimedia services with stringent Quality of Service (QoS) requirements, rather than simple infrastructure. Due to these requirements, the QoS-aware, cost-efficient selection of data centers arises as a new research challenge. In our ongoing work, we examine the corresponding Cloud Data Center Selection Problem and propose an exact optimization approach. A brief evaluation indicates that the proposed approach is primarily suited for small problem instances due to its high computational complexity, and hence highlights the need for the development of heuristic optimization approaches.

Setting Priorities - A Heuristic Approach for Cloud Data Center Selection

“…For the resource allocation to different user clusters, the overall service demands of all user clusters and the QoS requirements must be matched by corresponding guarantees. In our former work, we referred to this problem as Cloud Data Center Selection Problem (CDCSP) (Hans et al, 2013).…”

“…The presented mathematical model is part of our former work (Hans et al, 2013). For the model several formal notations are required.…”

“…As stated earlier, the described model constitutes an Integer Program (IP) and was published as Cloud Data Center Selection Problem (Hans et al, 2013). Such IPs can be solved using off-the-shelf algorithms, such as branch-and-bound (Domschke and Drexl, 2004).…”

“…According to our former work (Hans et al, 2013), the problem instance generation was based on the 2010 United States census 3 . Thereby we set the service demands and different cost parameters according the population of a randomly selected county and its median income.…”

Cost-efficient Capacitation of Cloud Data Centers for QoS-aware Multimedia Service Provision

“…Accordingly, in the work at hand, we examine how cloud data centers can be appropriately selected and capacitated in order to serve QoS-aware multimedia services. In our previous work (Hans et al, 2013), we have addressed the selection of cloud data centers for single service types and time-invariant service demands. The work at hand expands our past research through the consideration of multiple service types, as well as fluctuating service demands, and also regards the resulting distinction between variable costs for operation and reservation of cloud infrastructure.…”