CS780-3 Lecture Notes

In Courtesy of Mengjun Xie

AboutNEESgrid will link earthquake researchers across the U.S. with leading-edge computing resources and research equipment, allowing collaborative teams (including remote participants) to plan, perform, and publish their experiments. NEESgrid, the systems integration component of the NEES project, uses the newest and fastest communications technologies to tie the NEES network together.

NEES Resources

Field Equipment

Laboratory Equipment

Remote Users

Remote Users: (K-12 Faculty and Students)

Instrumented Structures and Sites

Leading Edge Computation

Curated Data Repository

Laboratory Equipment

Global Connections

(FY 2005 – FY 2014)

(Faculty, Students, Practitioners) Simulation

Tools Repository

NEES

Network for Earthquake Engineering Simulation NEES is a distributed array of experimental sites, grid-

based data repositories, tool archives, and computational resources, all seamlessly linked (hopefully!)

NEES has four components: The consortium, which will run NEES after 2004 The consortium development (CD) builds the consortium The experimental sites, which provide data and content The systems integration (SI) effort, termed NEESgrid

Network drivers include telepresence, curated repositories, scalable HPC, experimental-numerical coupling, short- and long-term QoS issues.

NEES Network Stakeholders

Experimental Facilities Shake tables, centrifuges, wave tanks, field

sites

Resource providers Computers, software, storage, networks

End users Researchers, practicing engineers, students, …

Operational facilities NCSA/NEESgrid NEES Consortium in 2004

NEESgrid?

A coordinated and secure architecture/environment A modular and extensible environment with a customizable user interfaceProvides common tools that allow leveraging resources and experiencesGoal: the Cyber Infrastructure that will facilitate this next generation of experimentation/simulation in earthquake engineering

“A Distributed Virtual Laboratory for Advanced Earthquake Experimentation and Simulation.”

-- B. F. Spencer, Jr. (PI & Project Director)

NEESgrid?

Through the NEESgrid, researchers can: perform tele-observation and tele-operation

of experiments; publish to and make use of a curated data

repository using standardized markup; access computational resources and open-

source analytical tools; access collaborative tools for experiment

planning, execution, analysis, and publication.

Telepresence

Telepresence means the capability to participate remotely in experimental trials. There are two main categories:

Tele-observation: the ability to observe the experiment and capture trial data from a remote site

Tele-operation: the ability to interact with the experiment equipment from a remote site.

Collaboration and Visualization

The tasks of Collaboration and Visualization project include:

prototype a Grid-based collaborative environment; integrate support for visualization tools into the

collaborative environment; adapt the Comprehensive Collaborative Framework

(CHEF) for collaborative visualization applications and services; and

produce appropriate final documentation of the collaboration and visualization components of NEESgrid.

CHEF is a flexible web-based environment for remote collaboration.

Main Components

Tele-Control Services and APIs Tele-Observation and Data Visualization E-Notebook Streaming data services DAQ and related services Data and Metadata Services Remote Collaboration and Visualization tools

and services Core Grid Services, deployment efforts,

packaging Simulation Component

Progress

The task of designing and creating this infrastructure has been awarded to the NCSA at UIUC.

The components of the NEESgrid system will be completed by September, 2004, when management and operation of the NEES system will be turned over to a consortium of earthquake engineer researchers and practitioners.

PartnerNational Center for Supercomputing Applications

Randy Butler —Deployment, Operations, and SupportMark Marikos —ManagementJoe Futrelle —Data and Metadata

University of Illinois at Urbana-Champaign

Bill Spencer —ManagementDan Abrams —Community Building

Argonne National Laboratory

Nestor J. Zaluzec —TelepresenceIan Foster —System Configuration

Information Sciences Institute

Carl Kesselman —System Configuration

University of Southern California

Jean-Pierre Bardet —Integrated Demonstrations

School of Information, University of Michigan

Joseph Hardin —CollaborationTom Finholt —User Requirements

System Architecture

System Architecture

System Architecture

System Architecture

System Architecture

System Architecture

System Architecture

Pre-Experiment Collaboration

The remote user (RU) logs into the equipment site's NEESpop. After authentication, RU can access all granted NEESgrid resources through SSN.RU can, via CHEF, read and participate in discussions related to the equipment site, see a calendar, share documents, make announcements, and correspond with other researchers to plan an experiment.Through NEESpop, RU can also access and edit electronic lab notebooks hosted on the TPM.

Monitoring Network Status

RU contacts CHEF and requests a summary of the system's health and status.The CHEF server contacts a central NCSA server that monitors NEESgrid.Standard grid services (GIIS at NCSA, GRIS for other services) are continually collecting information on system connectivity and the availability of grid services such as GridFTP.The grid information is summarized and sent to RU's browser.

Setting Up the Experiment

Using a CHEF teamlet, the equipment specialist at the equipment site enters the metadata describing the configuration of the experimental setup.

The metadata repository on the NEESpop holds this configuration information, making it available for browsing by RUs.

The NEESpop metadata repository also sends configuration information to the DAQ system(s).

Subscribing to Trial Data Streams

RU contacts CHEF to browse available NEESgrid resources and discover what data will be available for streaming.A CHEF teamlet uses GIIS and GRIS to query and report features and availability of NEESgrid resources, as well as details of NEES equipment and available data streams.RU contacts the NEESpop and requests a subscription to several data streams.The NEESpop negotiates with the NSDS to broadcast the selected data streams.

Streaming Near-Real-Time Data

Instrument information is sent in real time from the DAQ system through a NSDS daemon to the NSDS.

Data is streamed by NSDS to the RU. An applet in the RU's browser displays the results.

Video services are managed through the TPM server and streamed to the RU via a separate video streaming server.

Ending the Trial

The DAQ equipment moves the trial data to a data repository hosted on the NEESpop.

The data is associated with appropriate metadata information, such as experiment ID, channel ID, and sensor type.

Analyzing the Trial Data

The trial data can now be browsed via CHEF.

The trial data and metadata can be downloaded to the RU via GridFTP service.

The RU can then use either standard software, such as MatLAB, or their own customized software to analyze the trial data.

Login Authentication

ChatCHEF Environment

E-NotebookCHEF Environment

Data ViewerCHEF Environment

NTCP DataCHEF Environment

NEESgrid Central RepositoryCHEF Environment

Summary

Characterizations of NEES project: A very specific application A wide range of resource sharing:

Raw data, experimental results, equipment, computation/software tools

Centralized controls, monitoring, and management.

Does this follow the three principles of Grid? Not really: it is subject to central control, not open source

software based.

But it is a successful model of grid applications.A Global and general grid is an ideal model, and may become realistic after many successful NEES projects.