Many of today's scientific discoveries require extreme-scale data-intensive applications driven by very high levels of computational processing. E-science is a term often used to describe scientific research and discovery which involves international collaboration and one or more of the following characteristics; i) very large data sets, terabytes, petabytes, etc. ii) high-end computing resources, teraflops, super computers, cluster computing, etc., iii) remote instrumentation and sensors for data collection; and iv) powerful visualization tools for analysis. E-science scale research and engineering exists across the whole spectrum of disciplines: high energy physics, biology, environmental science, engineering and based on different scientific modes including remote sensor data collection, simulation and modeling based analysis, and remote instrumentation, just to name a few. The explosive growth of scientific data and its geographic distribution have rapidly overwhelmed our ability to manage, move, store, and analyze it. Wide-area networks connecting instruments, data archives, and simulation facilities have lacked the bandwidth and performance required to enable next-generation scientific discovery and support mission-critical, on-demand simulations.
These new applications coupled with Grid toolkits represent a paradigm shift in how applications interact with the network and Grid middleware. Applications. usage of the network often requires a near-real-time, or even real-time, information feedback loop on the available resources and intelligent decisions on how best to take advantage of these resources.
Grid computing requires specialized control planes with several unique attributes: i) application/user initiated optical end-to-end connection; ii) interaction with Grid resource performance and availability information; iii) interaction with Grid middleware for the coordination of compute resources with network resources; iv) interaction with higher layer protocols like transport layer. This requires researchers to take a step back and re-think the required behavior of the network within a Grid environment.
This single-track two-day workshop will provide researchers and technologists with a focused, highly interactive opportunity to present and discuss leading research, development and future directions in networks that are ideally suited to data-intensive grid applications. The second day will be devoted to international Grid networks and specific optical control plane research. Authors are invited to submit unpublished full papers for consideration.
The GridNets 2005 workshop will focus on research issues and challenges as well as lessons learned from experience. Topics of interest include and are not limited to:
Paper Submission Deadline: June 15, 2005
- New concepts and requirements to shape the design of eScience and Research
- Integration of advanced optical networking technologies and architectures (OPS, OBS) for the Grid environment
- Coordination of network resources with other Grid resources (CPU, Storage)
- Layer interactions: optical layer with higher layer protocols
- Grid advanced resource reservation
- Self-healing Grid networks
- Traffic characteristics and performance analysis
- New architectures and technologies that address grid requirements
- Experience on production-level optical network infrastructures
- Middleware design and grid layer integration issues for accessing and managing
- Routing and scheduling for dynamic bandwidth control
- Monitoring, provisioning, brokering of network resources
- New multi-service frameworks and models
- End-to-end application level control of network resource
- Novel data transport protocols designed for new application services
- Data replication and multicasting strategies and protocols
- Fault-tolerance, protection, security, and scalability issues related to connecting large
number of sites
- Network cost, performance, and incentive issues
Paper Acceptance Notification: August 1, 2005
Final paper submission: August 13, 2005