Delivering cloud services with QoS requirements: Business opportunities, architectural solutions and energy-saving aspects

摘要

The flexible and pay-as-you-go computing capabilities offered by Cloud infrastructures are nowadays very attractive, and widely adopted by many organizations and enterprises. In particular this is true for those having periodical or variable tasks to execute, and, choose to not or cannot afford the expenses of buying and managing computing facilities or software packages, that should remain underutilized for most of the time. For their ability to couple the scalability offered by public service providers, with the wider Quality of Service (QoS) provisions and ad-hoc customizations provided by private Clouds, Hybrid Clouds (HC) seem a particularly appealing solution for customers requiring something more than the mere availability of the service. The paper firstly introduces a Cloud brokering system leveraging on a promising architectural approach, based on the use of a gateway toolkit. This approach provides noticeably advantages, both to customers and to Cloud Brokers (CB), for its ability to hide all the intricacies related to the management of powerful, but often complex and heterogeneous infrastructures like the Qoud. Moreover such approach, through customized interfaces, facilitates customers in accessing Cloud resources thus easing the tailored deployment and execution of their applications and workflows. The major contribution of this work is given by the analysis of a set of brokering strategies for Hybrid Clouds, implemented by a brokering algorithm, aimed at the execution of various applications subject to different user requirements and computational conditions. With the objective of firstly maximize both user satisfaction and CB's revenues the algorithm also pursues profit increases through the reduction of energy costs by adopting energy saving mechanisms. A simulation model is used to evaluate performance, and the results show that differences among strategies depend on type and size of system loads and that the use of turn on and off techniques greatly improves energy savings at low and medium load rates thus indirectly increasing CB revenues without diminishing customers' satisfaction.