Call for Papers
Special Issue on Performance Modeling and Analytics for Clouds

Aim & Scope
Cloud computing have progressed rapidly in recent years since it can provide real-time, on-demand, self-provisioned services to business users on an as-needed basis, including IaaS (Infrastructure as a Service), PaaS (Platform as a Service) and SaaS (Software as a Service). On the back end, cloud computing requires highly efficient and transparent multiplexing of complex networking, storage, and computing resources that optimally are configured to provide performance guarantees. Therefore, clouds should be able to automatically balance workloads during peak periods and non-peak periods based on performance-energy-cost tradeoffing.

Moreover, in virtualized clouds, it is difficult to accurately model virtualized systems in order to analyze performance issues. The cloud paradigm comes up with complexities and multifaceted problems associated with correctly measuring, modeling and analyzing the performance aspects of clouds. These new performance related challenges may comprise, sometimes even deteriorate the efficiency, logical or physical transparency of cloud services, quality of isolation, fairness among virtualized systems, quality of synthetic services, scalability of the composition of virtualized services and of the management mechanisms for cloud centers and their operation patterns.

Considering these performance issues, traditional modeling methods that were developed for physical machine based systems do not seamlessly work in clouds. Alternatively, clouds require new modeling methodologies, analytics, simulation techniques, and updated benchmarks.

The goal of the proposed Journal of Information Science and Engineering(JISE) special issue is to provide a forum to address the performance modeling and analytics of clouds including theory and practice in industry and academia. This special issue cordially welcomes innovative, state-of-the-art and/or work-in-progress research on modeling and analytics of clouds, including algorithms, performance measurement, analytic modeling, simulation, performance engineering, benchmark design, and run-time performance management techniques. Relevant research topics for this proposed special issue include, but are not limited to, the following ones:

Topics
  • User models and workload characterization in Clouds
  • Performance metrics for adaptation and dynamics in Clouds
  • Resource provisioning, modeling and scheduling in Clouds
  • I/O and network performance modeling
  • Performance isolation and fairness among multiple virtual systems
  • Scalability, robustness and resilience of Clouds
  • Quality of Service in Clouds
  • Engineering techniques for cloud services deployment and combination
  • Power/energy efficiency
  • Security Issues and its performance evaluation
  • Performance verification and validation
  • Experiences, performance and reliability of running scientific applications in clouds
  • Performance simulation techniques and benchmarks in Clouds


  • Submission Guidelines
    Besides normal submissions, the revised version of the best papers selected from the IEEE Workshop on Performance Aspects of Cloud and Service Virtualization (IEEE CloudPerf 2012) In Conjunction With IEEE SERVICES/ICWS/SCC/CLOUD2012 will be invited to be submitted to this special issue. The revised version must have at least 40% difference from the conference paper. Electronic paper submissions are sent to
    Lchen@mail.ntust.edu.tw. A template of submitted paper can be found at http://www.iis.sinica.edu.tw/page/jise/FILE/standard-new.doc.

    Important Dates
  • Submission Deadline: July 31, 2012
  • Acceptance Notification: September 30, 2012
  • Final Manuscript Due: November 1, 2012
  • Publication Date: May 2013 (Tentative)


  • Guest Editors