期刊名称：Journal of King Saud University @?C Computer and Information Sciences
印刷版ISSN：1319-1578
出版年度：2022
卷号：34
期号：6
页码：3136-3150
语种：English
出版社：Elsevier
摘要：Cloud computing represents one of major innovations in Information Technology (IT). It is a model for enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources. Elasticity is one of the most important characteristic in the cloud. Due to the enormous amounts of energy consumed by a cloud, it becomes difficult to build an elasticity system that satisfies all the requirements that might arise during its lifetime. Different approaches are proposed to address the energy-efficiency in the modelling of elasticity system at multiple layers of cloud services. Most of the existing approaches measure the overall hardware energy consumption, instead of the energy consumption of the software. Understanding how energy is consumed by cloud with elastic scaling mechanism is a key for managing better energy efficient software. This work proposes an architecture for modelling elasticity and energy-efficiency in the application layer. This architecture combines both the characteristics of adaptation (with Autonomic Computing) and variability (with Feature Model) into a single solution. The feature model considers the variability in the structural modelling and the behaviour one. We show the feasibility of the proposed approach by analysing the smart university applications associated with the Znn.com scenario.
