[Tccc] FGCS Special Issue on Model-driven Provisioning of Application Services in Hybrid Computing Environments [Deadline extended to Feb 15, 2012]
Rajiv Ranjan
rranjans
Wed Jan 4 09:25:00 EST 2012
*Special Issue on***
*Model-driven Provisioning of Application Services in Hybrid Computing
Environments*
* *
*Future Generation Computing System*
*Editor-in-Chief: Peter Sloot*
**** Call for Papers ****
This special issue solicits papers that advance the fundamental
understanding, technologies, and concepts related to provisioning resources
(CPU, storage, and network) and applications over hybrid cloud computing
systems. The research advancement is in this area is important because such
large, heterogeneous, uncertain and evolving cloud systems are becoming
increasingly common, yet current provisioning methods do not scale well and
nor do they perform well under highly unpredictable conditions. If these
problems are resolved, then cloud-hosted applications will operate more
efficiently, with reduced financial and environmental costs, reduced
under-utilisation of resources, and better performance at times of
unpredictable workload.
Today, Small and Medium Business Enterprises (SMEs) and governments face
accelerated business change, more intense domestic and global competition
and increased IT demands. They try to meet new demands through rapid
implementation of innovative and inclusive business models while at the
same time lowering IT barriers to innovation and change. These demands call
for a more dynamic computing model that supports rapid innovation for
services and their delivery. *Cloud computing*, which can be an important
component of such a model, is a recent advance wherein IT-related
functionalities (e.g., CPU, applications, storage, etc.) are provided as a
virtualized service to consumers under a usage-based payment model. In a
Cloud computing model, consumers (SMEs, governments, universities) can
leverage virtualized services probably on the fly based on fluctuating
requirements and, in doing so, they avoid worry about infrastructure
details such as where these resources are hosted or how they are managed.
The new computing environment, buoyed by recent advances in the above
areas, has resulted in hybrid computing environments comprised of
virtualized services usage-based payment models, and networked devices. The
benefit of such an environment is efficiency and flexibility, through
creation of a more *dynamic computing enterprise*, where the supported
functionalities are no longer fixed or locked to the underlying
infrastructure. This offers tremendous automation opportunities in a
variety of computing domains including, but not limited to, e-Government,
e-Research, web hosting, and e-Business.
Provisioning means ?high-level management of computing, network, and
storage resources to allow them to effectively provide and deliver
application services to end-users?. The diversity and flexibility of the IT
functionalities (dynamically shrinking and growing computing systems)
offered by the evolving hybrid environments, combined with the magnitudes
and uncertainties of its components (workload, CPU, storage end-users,
etc.), pose difficult problems in effective provisioning and delivery of
application services. Computing systems managing hybrid environments must
deal with the highly transient behaviors of end-users (arrival pattern,
profile), virtualized services (CPU utilization, CPU availability, dataset
size, I/O and other QoS issues) and networks (bandwidth, disconnections),
all of which can be difficult to predict. The problem is further
complicated by ever-increasing scale, performance, energy saving and
security requirements. To counter these challenges, there is need to
develop analytical models for each component that operate as parts of
hybrid computing environments. These models will be important because they
allow adaptive system management by establishing useful relationships
between high-level performance targets (specified by operators) and
low-level control parameters and observables that system components can
control or monitor. Consequently, there is need to develop models for
predicting behaviour and performance of different types of applications
services and resources to adaptively transform service requests. Broad
range of analytical models and statistical curve-fitting techniques such as
multi-class queuing models and linear regression time series can be applied
for this purpose. These models will drive and possibly transform the input
to a service provisioner, which will improve the efficiency of the system.
Such improvements will better ensure the achievement of performance targets
(response time, throughput, fairness) and security concerns
(confidentiality, integrity and availability), while reducing costs due to
improved utilization of resources. It will be a major advancement in the
field to develop a robust and scalable system monitoring infrastructure to
collect real-time data and re-adjust these models dynamically with a
minimum of data and training time. We believe that these models and
techniques are critical for the design of stochastic provisioning
algorithms across large hybrid environments where resource availability is
uncertain.
* *
*Topics*
Areas of interest for this special issue include the following:
- Application behavior prediction models
- Dynamic learning technique for new application behavior adaptation
- Queuing theory based resource performance model solvers
- Application auto-scaling models
- Stochastic fault-tolerance and reliability models
- Decentralized networking models for scalable application health
monitoring and model training
- Energy-efficiency models for provisioning and migration of
applications
- Industrial and experimental infrastructure enabling hybrid
environments
- Innovative Scientific, Business, and Internet Service Applications
- Security, privacy and trust in hybrid environment
* *
*Schedule*
Submission due date: January 15, 2012 - Deadline extended to Feb 15, 2012
Notification of acceptance: March 15, 2012
Submission of final manuscript: May 15, 2012
Publication date: 1st/2nd Quarter, 2012 (Tentative)
*Submission & Major Guidelines*
The special issue invites original research papers that make significant
contributions to the state-of-the-art in ?model-driven provisioning of
application services in hybrid computing environments?. The papers must
not have been previously published or submitted for journal or conference
publications. However, the papers that have been previously published with
reputed conferences could be considered for publication in the special
issue if they are substantially revised from their earlier versions with at
least 30% new contents or results that comply with the copyright
regulations, if any.
Every submitted paper will receive at least three reviews. The
editorial review committee will include well known experts in the area of
Grid, Cloud, and Autonomic computing.
Selection and Evaluation Criteria:
- Significance to the readership of the journal
- Relevance to the special issue
- Originality of idea, technical contribution, and significance of the
presented results
- Quality, clarity, and readability of the written text
- Quality of references and related work
- Quality of research hypothesis, assertions, and conclusion
*Guest Editors*
*Dr. Rajiv Ranjan ? Corresponding Guest Editor*
Research Scientist, CSIRO ICT Center
Computer Science and Information Technology Building (108)
North Road, Australian National University, Acton, ACT, Australia
Email: rajiv.ranjan at csiro.au
* *
*Prof. Rajkumar Buyya*
CEO, Manjrasoft Pty Ltd, Melbourne, Australia
Director, Cloud Computing and Distributed Systems Laboratory
Department of computer science and software engineering
The University of Melbourne, Australia
Email: raj at csse.unimelb.edu.au
*Dr. Surya Nepal*
Principal Research Scientist, CSIRO ICT Center
Cnr Viemiera and Pembroke Roads
Marsfield, NSW 2122
Email: Surya.Nepal at csiro.au
More information about the TCCC
mailing list