Abstract
Special Issue: Quality of Service in Grid and Cloud 2015 Anne James and Norlaily Yaacob Coventry University, UK Guest Editorial This special issue focusses on Quality of Service in Grid and Cloud. It follows a special section on the same topic published in the journal of Future Generation Computer Systems in 2012 [1]. We thought it would be interesting once more to draw together high-quality work in this field. A special open call was therefore issued for papers addressing quality of service in Grid and Cloud which ultimately resulted in eleven selected papers which we see in our special issue. In our 2011 special section, we noted four sub-themes emerging from the papers submitted. These were the sub-themes of autonomy or adaptability; managing service discovery and composition; improved scheduling and congestion handling techniques; and finally empowerment of users. For this 2015 special issue we have categorised the contributions into four sub-themes: business and user oriented systems; virtual machine management; search and discovery; and distributed processing and performance. Emerging areas since the last special issue are therefore virtual machine management and distributed processing and performance. The special issue begins with the sub-theme of business and user oriented systems where we have four papers. The first paper is by Alkhanak, Lee and Khana [2] who provide a detailed review on work flow scheduling (WFS). Their aim is to help researchers select appropriate cost-aware WFS approaches from various available alternatives. A taxonomy is produced by analysing the cost-aware relevant challenges of cloud-computing WFS classified on Quality of Service (QoS) performance, system functionality and system architecture. Albodour, James and Yaccob [3] provide the second paper which addresses how business users can take advantage of Grid computing. The authors describe the Business Grid Quality of Service (BGQoS) model focussing on QoS capability and flexibility. An experimental evaluation of the model is presented. The behaviour and performance of the separate operations and components within BGQoS are considered and an investigation and comparison between the different operations and their effect on the full model is given. The third paper is this sub-theme is provided by Chen et al. [4]. The authors address the area of consensus on QoS of cloud services. A new agenda based approach which facilitates the process of multi-issue negotiation between service consumer and service provider is described. The construction of a common preference sequence of issues and a co-evolutionary negotiation model based on the result of preference ordering are introduced and to illustrate the approach, a case study is presented. Mohamed et al. [5], in the final paper of this sub-theme, address the management of elasticity of business processes with the aim of providing fitting QoS. They propose a holistic approach that allows dynamic addition of autonomic management facilities to Cloud resources, based on the Open Cloud Computing Interface (OCCI) standard and on duplication and consolidation mechanisms. The next sub-theme is virtual machine management where we have three papers. The first paper is by Ding et al. [6] who consider energy efficient scheduling of virtual machines in the context of deadline constraints. The paper proposes an energy efficient scheduling algorithm, EEVS which can handle heterogeneous physical machines and dynamic voltages. The algorithm is based on scheduling periods and optimal performance-power ratio. The simulation results show that the proposed scheduling. algorithm achieves over 20% reduction of energy and 8% increase of processing capacity in the best cases. Xu et al. [7] provide the next paper in this sub-theme. The authors address management of virtual machine images in infrastructure-as-a-service contexts. The research analyses varying requirements, such as performance, storage, image size and management and considers potential tradeoffs among them. It proposes a zone-based model to balance the requirements well. The evaluation shows that, the solution improves IO performance by more than 100% in general and has similar or less storage consumption and management cost than other models. In the final paper of this sub-theme, Rao and Thiligram [8] present a consolidation approach to virtual machine positioning which reduces residual resource fragmentation. The proposed heuristics based server consolidation approach performs residual resource defragmentation along with reducing the number of active physical machines in cloud data centres. Search and discovery is the subject of the third sub-theme of our special issue and we have two papers in this sub-theme. In the first paper Liu et al.[9] state that metadata search performance has become
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.