Meeting of the European E-infrastructure Forum
Phone conference:
Dial-in numbers: +41227676000 (English, Main)
Access codes: 0150552 (Leader)
0160525 (Participant)
Leader site: https://audioconf.cern.ch/call/0150552
Participant site: https://audioconf.cern.ch/call/0160525
This session, on Infrastructure Tools and Services, covers a cross section of the emerging tools that are being created to make life easier for the VOs, as well as for individual users. The first talk, "A solution to distribute software packages at Grid sites using Squid" describes an alternative approach to making VO applications available at grid sites. The second talk, "Application Domain Accounting for EGI", focuses on the 'missing' functionality of the EGEE grid accounting systems: VO application-level accounting. The talk on "Site Status Board" gives an overview of the tool, how it is used by the LHC VOs, and how it could benefit other VOs. The penultimate talk, "Visual GRID Activity Monitoring in the Dashboard Framework", describes a Google Earth based monitoring application which visualizes grid activity and provides a very appealing tool for educational and public relations purposes. The final talk in this session, "Workflow repository, user specific monitor, and vulnerability analyzer in SEE-GRID", introduces some high-level services, which extend the gLite-based SEE-GRID infrastructure in order to ease several tasks of end-users and VO application developers.
The task to take advantage of grids can be a challenge for scientists with limited computational expertise. For this group of users, there is a need for more user-friendly points of interaction. Portals and Gateways provide an access-point which abstracts away technical details, and allows users to focus on their research; every scientist does not have to be a computer expert.
Grid portals have the advantage that there is no need for the user to install software locally, which significantly simplifies maintenance and sustainability. In fact, the user sometimes does not even know that the underlying resources are grids. For grids to have the largest impact, it is important to make resources available as widely as possible. Scientific gateways and portals have the potential to build more and larger user communities, open for the use of grids in more disciplines, and foster collaborative environments.
Portals can provide means to interact with, for example, grid middlewares and/or Web services, or be devoted to a scientific domain. In this session, we will hear about two general-purpose portal engines and two domain-oriented portals. In common, they have that they hide the sometimes complex technologies, delivers access and visually oriented means to interact with data and computational resources, and have extensible architecture.
An overview of the latest advances in security and several related mechanisms on Grid infrastructures will be given during the session. Developments on monitoring and administration of security related operations as well as user tools to better manage digital certificates and encryption of sensitive information will be presented. Several presentations during the poster session also cover and provide insight on new tools on credential management and proxy delegation.
The User Forum demonstration session traditionally provides the opportunity to mature research work and scientific activities, exposing highly interactive and visually appealing characteristics, to come and present their latest achievements. This year 20 demonstrations have been selected to be presented in two demo slots. For this purpose, the demonstrations are split in two groups each one scheduled for a different day. The first group of 10 demonstrations will be on display during the first slot on Monday afternoon, in parallel with the welcome cocktail, whereas the second group will be presented on Wednesday afternoon. Both sessions will be run in parallel with the poster sessions on display in the same area in the venue.
The demonstrations have been split into two logical groups based on their focus. Thus, on Monday the session will host demonstrations with more scientific focus; i.e. activities who will present scientific results achieved using a large scale Distributed Computing Infrastructures. On Wednesday, the interest will shift to more technical demonstrations, with the scheduled presentations focusing on advanced tools and technologies that facilitate the end-user/DCI interaction as well as on international projects and collaborations, which strive to extend and expand the current horizons of DCI infrastructure to novel technologies and paradigms. Some of these activities have been demonstrated in previous events, thus the attendees will have the opportunity to check upon their progress and be informed about latest results. Others, will be demonstrated for the first time.
Finally as with previous events, the best demonstrations will be selected form the EGEE External Advisory Committee and the event attendees. The best demos will be announced and awarded during the event’s closing plenary on Thursday.
The User Forum poster session has always been on of the most lively and vibrant parts of the event. We expect this year to be no exception. 40 posters have been accepted and will be presented during the two relevant sessions, on Monday and Wednesday afternoon, in parallel with the demonstration sessions. This year the poster session offers a mixture of scientific and technical presentations on a wide variety of subjects: Grid security, distributed programming development tools, infrastructure operations and recent progress of DCI exploitation by traditional as well as nascent user communities. The attendees will have the opportunity to closely interact with the poster presenters, get informed about their recent activities, exchange ideas and potentially establish new collaborations. They will also have the chance to vote for the best poster in display. The winner will be announced during the User Forum closing plenary on Thursday morning.
Life Sciences is a very active field of research using the EGEE infrastructure. Several EGEE related projects are also exploring the use of gLite middleware for bioinformatics and healthcare. The User Forum is a wonderful opportunity to get an overview of the present adoption of grids in the Life Sciences communities through the dedicated oral sessions session but also through the posters and demos exhibition. Complementary to the "medical imaging" session, the "bioinformatics and biomedicine" session programme reflects the variety of topics currently addressed on EGEE and its related projects in the field of life sciences.
The EGEE series of projects brought computational chemistry on a grid to a new level: from a small group of users to a second resource consumer just after High Energy Physics. Chemical applications on EGEE Grid cover a wide area ranging from quantum dynamics computations for small molecular systems through ab initio simulations up to molecular dynamics studies of huge molecular systems of biological and industrial importance.
The User Forum is an annual EGEE conference whose unique character descends from the fact that grid users can meet together with developers. This year dedicated oral talks and accompanying posters detail not only current development on the EGEE grid of the computational chemistry domain traditional subjects. Large part of the conference session is instead devoted to the rapid evolution of computational chemistry tools to the quickly approaching EGI era. Typical examples of this are web services enabling easy use of chemical software on the Grid or implementation of new techniques enabling computation of various energy derivatives – crucial for determination of many molecular properties.
Technologies such as clouds and virtualization are attracting a lot of interest in grid and e-science worlds. With respect to grid systems, they are often seen as complementary or as natural extensions, but sometimes as competitors. In this session, a number of talks will report experience in using cloud technology and services, as well as virtualization, in scientific applications. Other presentations present frameworks and tools to ease the integration of new technologies in the grid landscape. Overall, we will attempt to better understand the opportunities and potential pitfalls in adopting these technologies such that future architectures leverage this important pool knowledge acquired and shared by early adopters.
Life Sciences is a very active field of research using the EGEE infrastructure. Several EGEE related projects are also exploring the use of gLite middleware for bioinformatics and healthcare. The User Forum is a wonderful opportunity to get an overview of the present adoption of grids in the Life Sciences communities through the dedicated oral sessions session but also through the posters and demos exhibition. Complementary to the "medical imaging" session, the "bioinformatics and biomedicine" session programme reflects the variety of topics currently addressed on EGEE and its related projects in the field of life sciences.
The EGEE series of projects brought computational chemistry on a grid to a new level: from a small group of users to a second resource consumer just after High Energy Physics. Chemical applications on EGEE Grid cover a wide area ranging from quantum dynamics computations for small molecular systems through ab initio simulations up to molecular dynamics studies of huge molecular systems of biological and industrial importance.
The User Forum is an annual EGEE conference whose unique character descends from the fact that grid users can meet together with developers. This year dedicated oral talks and accompanying posters detail not only current development on the EGEE grid of the computational chemistry domain traditional subjects. Large part of the conference session is instead devoted to the rapid evolution of computational chemistry tools to the quickly approaching EGI era. Typical examples of this are web services enabling easy use of chemical software on the Grid or implementation of new techniques enabling computation of various energy derivatives – crucial for determination of many molecular properties.
The Earth Science (ES) community with its mosaic of disciplines and contributors (academia, industry and, national and international organization) provides a scientific basis for addressing social, research and industrial issues as it is shown in the abstract on ES applications of the ES virtual research community. Some crucial points are the existing large data repositories in data centers outside the Grid infrastructures and the fact that the earth science data are always referred at least to 3 coordinates, geographical location (latitude & longitude) and time, and in many cases to 4 coordinates as activities related with spatial data, such as applications from public sector e.g. cadastre, topography, census, traffic, all public information, civil protection related on flood, fire or earthquake, industry, research and so forth. Due to the large volume of data and their heterogeneity (resolution in the 4D, different formats) the ES community has developed tools in particular to access them, to exploit and integrate them.
This session reflects many aspects of this community. Its worldwide aspect is exhibited by abstracts from teams of 11 European countries and one from Taiwan, partner of the ES cluster. Several environmental and societal issues are addressed and they concern more specifically hydrology (Black Sea Catchment– EU project, EnviroGrids), meteorology, pollution, seismology, fire evolution (Portuguese funded project, Cross-Fire), fisheries and aquaculture with monitoring and risk management approaches. Porting applications is not enough to satisfy the requirements of end-users. Due to the complexity of the application, workflows have been developed and one example is given for the fisheries and aquaculture communities. Two abstracts concern the use, with Grid, of GIS components based on Web services and provided by OGC (Open Geospatial consortium). Their integration within a platform or gateway will be very useful for decision makers as well as all public. To address the issue of exploring large data sets, different data mining tools are commonly used in ES and have been applied in the framework of the European project, ADMIRE. Training platforms are a key point to introduce new end-users to the grid infrastructure and to demonstrate the powerfulness of an Grid environment, one example is shown with satellite earth observation data. Finally, after a decade of European Grid projects and effort of building the ES Grid community, critical issue is it sustainability and its structure to maintain and facilitate collaboration, expertise.
The European Strategy Forum on Research Infrastructures Roadmap states that Research Infrastructures “often require structured information systems related to data management, enabling information and communication. These include ICT-based infrastructures such as Grid, computing, software and middleware.” and continues with “e-Infrastructures are critical to all projects in this roadmap”.
A dialog has started between individual ESFRI projects and existing ICT-based infrastructures to understand how best they can make use of e-Infrastructures.
A session at EGEE09 (Barcelona, September 2009) saw 11 ESFRI projects outline their views and the e-infrastructure projects explained how they can help. From this session emerged the common wish to work closer together and elaborate better the e-infrastructure requirements for the future. Subsequently there have been a number of meetings organised by the EC and the ESFRI projects themselves that have advanced the understanding.
The e-infrastructure projects have jointly, via the European Einfrastructure Forum, made an initial survey of the requirements.
At this session we will check the status of the interaction, present a first analysis of the requirements and plan how to proceed for the future.
This will also be the opportunity for those ESFRI projects, that were not present at earlier events, to become aware of the developments and present their requirements.
The Earth Science (ES) community with its mosaic of disciplines and contributors (academia, industry and, national and international organization) provides a scientific basis for addressing social, research and industrial issues as it is shown in the abstract on ES applications of the ES virtual research community. Some crucial points are the existing large data repositories in data centers outside the Grid infrastructures and the fact that the earth science data are always referred at least to 3 coordinates, geographical location (latitude & longitude) and time, and in many cases to 4 coordinates as activities related with spatial data, such as applications from public sector e.g. cadastre, topography, census, traffic, all public information, civil protection related on flood, fire or earthquake, industry, research and so forth. Due to the large volume of data and their heterogeneity (resolution in the 4D, different formats) the ES community has developed tools in particular to access them, to exploit and integrate them.
This session reflects many aspects of this community. Its worldwide aspect is exhibited by abstracts from teams of 11 European countries and one from Taiwan, partner of the ES cluster. Several environmental and societal issues are addressed and they concern more specifically hydrology (Black Sea Catchment– EU project, EnviroGrids), meteorology, pollution, seismology, fire evolution (Portuguese funded project, Cross-Fire), fisheries and aquaculture with monitoring and risk management approaches. Porting applications is not enough to satisfy the requirements of end-users. Due to the complexity of the application, workflows have been developed and one example is given for the fisheries and aquaculture communities. Two abstracts concern the use, with Grid, of GIS components based on Web services and provided by OGC (Open Geospatial consortium). Their integration within a platform or gateway will be very useful for decision makers as well as all public. To address the issue of exploring large data sets, different data mining tools are commonly used in ES and have been applied in the framework of the European project, ADMIRE. Training platforms are a key point to introduce new end-users to the grid infrastructure and to demonstrate the powerfulness of an Grid environment, one example is shown with satellite earth observation data. Finally, after a decade of European Grid projects and effort of building the ES Grid community, critical issue is it sustainability and its structure to maintain and facilitate collaboration, expertise.
This section includes some medical imaging community contributions to the exploitation of the EGEE grid infrastructure. Applications to cardiac, brain and lung image analysis are presented. Emphasis is put on the domain services deployed on top of the core middleware to implement the applications and conduct experiments. In particular, workflow tools are extensively used to describe applications logic and provide a high level interface to the grid. Application-level reliability improvement mechanisms are also being described
Technologies such as clouds and virtualization are attracting a lot of interest in grid and e-science worlds. With respect to grid systems, they are often seen as complementary or as natural extensions, but sometimes as competitors. In this session, a number of talks will report experience in using cloud technology and services, as well as virtualization, in scientific applications. Other presentations present frameworks and tools to ease the integration of new technologies in the grid landscape. Overall, we will attempt to better understand the opportunities and potential pitfalls in adopting these technologies such that future architectures leverage this important pool knowledge acquired and shared by early adopters.
For the first time, an EGEE User Forum will feature a general Computer Science session. Indeed, many contributions come from Computer scientists that exploit the grid to run large-scale computations, for Machine Learning, Optimization, Game theory, and Complex networks. Phenomenology of the algorithms, theoretical results based on large experiments, and inter-disciplinary applications will be described, at various levels form mature tools to research-focused work. The Grid Observatory Cluster of EGEE-III will also present recent advances in exploration and analysis tools that are oriented towards the scientific view of grids. The session will be an opportunity to:
Fusion activities have overpassed the grid during the last period, since we implemented several complex workflows among applications that run on different architectures, including gird and High Performance Computers. During the session, the main achievements on application porting, as well as on complex workflows implementation on grids and HPCs will be presented.
Apart from EGEE, there exist the EUFORIA project that links the fusion, the grid and the HPC communities and allow the building of workflows among applications that explain different aspects of the physics involved in fusion reactors.
The High Energy Physics (HEP) community has been both an early adopter of grid technology as well as a driving force behind EGEE and other grid projects. The Worldwide LHC Computing Grid (WLCG) builds on the infrastructures established by these projects and has been successfully used for LHC data taking, processing and analysis.
The most important elements of the Grid infrastructure provided for the experiments will be presented during this session; the computing models of the experiments, the operation protocols used at the sites, and the end-user analysis infrastructures. In addition, other related communities are represented at this session such as Synchrotron Radiation Facilities. Therefore, the HEP session will be a forum where common aspects of Grid computing infrastructure used by different large communities will be discussed.
The EGEE User Forums have always provided an ideal framework to share experiences between Grid users, and to trigger collaborations between different clusters. The topics that will be presented and discussed during this session will encourage the continuation of existing collaborations and hopefully initiate new ones.
International grids cross national boundaries, spanning cultures, languages and technologies to create international resources and enable global science. With hundreds of grids running worldwide, there are many lessons to be learnt from international projects and collaborations, and this session brings together representatives of grids in Europe, Latin America, South Africa and the Asia-Pacific region. Key to European science in the future will be the European Strategy Forum on Research Infrastructures roadmap projects. This session explores integrating instrumentation with e-Infrastructures for the potential benefit of these projects, as well as presenting case studies of combining Virtual Research Environments (VREs) with grid technologies.
Dissemination activities such as publications, events, social media and community-building websites help to bring user communities together. This session gathers together best practices based on the lessons learnt during the EGEE project. Also explored are the requirements of experimental scientists to steer, control and monitor instruments and sensors remotely. A prototype system developed by DORII will be presented. The D4Science-II project provides a number of VREs to address the needs of the Fisheries and Aquaculture community. Case studies discussed include the Aquamaps VRE that generates species distribution maps, the ICIS VRE’s repository of statistical datasets and the FCPPS VRE, which provides country profile report templates.
SEE-GRID in South Eastern Europe will present improvements to the usability and services for its end users, including operational tools for monitoring, alerting, job tracking and security as well as application services such as advanced workflows, better data and file management and new applications platforms. EELA-2 in Latin America also presents its enhancements to the functionality of the gLite middleware, which has widened the number of potential applications and sped up the porting process.
The Nordic Data Grid Facility’s experiences in bringing on board a new user community, the materials science virtual organisation are also presented. The main goal of the project was to enable non-LHC scientists to run their jobs on ARC enabled resources. On a wider scale, the South African National Grid Initiative aims to deploy a production-quality regional e-Science infrastructure for all South African researchers. Benefits are already being seen in the areas of physics, geomatics and bioinformatics and, through collaboration with the HP/UNESCO project, the seeds of the first regional African grid initiative. EUAsiaGrid brings together researchers from the Asia-Pacific region, and presents its progress in building, maintaining and developing e-Infrastructure within the region, together with a roadmap towards a sustainable and persistent multinational digital platform.
Astronomy & Astrophysics community is in EGEE since 2004 with two pilot applications now in EGEE-III. When the project started in 2008, five funded and eight unfunded partners joined the A&A cluster contributing with challenging applications and use-cases. To support these research groups, a number of A&A VOs are now in place in EGEE-III.
The 5th User Forum is the last one before the end of EGEE-III and the advent of EGI. This A&A session therefore is a good occasion to deeply discuss and analyze the work done during these two years, the maturity achieved by the astronomical community with the Grid and the real perspectives for the continuation of the work undertaken in EGEE also in EGI. For this reason the featured application has been chosen as it will report about the whole activity carried out in the astrophysical cluster in these two years.
The remaining oral contributions will report about the progress with Grid-related activities by research groups that already contributed to the cluster for several projects, namely the LOFAR radio telescope, the PAU survey (study the dark energy and its evidences such as the accelerated expansion of the Universe), the simulated data of the Planck mission (production of simulated data and discovery of non-gaussianity signatures using spherical wavelets) and the computing Grid used for the purposes of the Cerenkov Telescope Array.
For the first time, an EGEE User Forum will feature a general Computer Science session. Indeed, many contributions come from Computer scientists that exploit the grid to run large-scale computations, for Machine Learning, Optimization, Game theory, and Complex networks. Phenomenology of the algorithms, theoretical results based on large experiments, and inter-disciplinary applications will be described, at various levels form mature tools to research-focused work. The Grid Observatory Cluster of EGEE-III will also present recent advances in exploration and analysis tools that are oriented towards the scientific view of grids. The session will be an opportunity to:
The High Energy Physics (HEP) community has been both an early adopter of grid technology as well as a driving force behind EGEE and other grid projects. The Worldwide LHC Computing Grid (WLCG) builds on the infrastructures established by these projects and has been successfully used for LHC data taking, processing and analysis.
The most important elements of the Grid infrastructure provided for the experiments will be presented during this session; the computing models of the experiments, the operation protocols used at the sites, and the end-user analysis infrastructures. In addition, other related communities are represented at this session such as Synchrotron Radiation Facilities. Therefore, the HEP session will be a forum where common aspects of Grid computing infrastructure used by different large communities will be discussed.
The EGEE User Forums have always provided an ideal framework to share experiences between Grid users, and to trigger collaborations between different clusters. The topics that will be presented and discussed during this session will encourage the continuation of existing collaborations and hopefully initiate new ones.
International grids cross national boundaries, spanning cultures, languages and technologies to create international resources and enable global science. With hundreds of grids running worldwide, there are many lessons to be learnt from international projects and collaborations, and this session brings together representatives of grids in Europe, Latin America, South Africa and the Asia-Pacific region. Key to European science in the future will be the European Strategy Forum on Research Infrastructures roadmap projects. This session explores integrating instrumentation with e-Infrastructures for the potential benefit of these projects, as well as presenting case studies of combining Virtual Research Environments (VREs) with grid technologies.
Dissemination activities such as publications, events, social media and community-building websites help to bring user communities together. This session gathers together best practices based on the lessons learnt during the EGEE project. Also explored are the requirements of experimental scientists to steer, control and monitor instruments and sensors remotely. A prototype system developed by DORII will be presented. The D4Science-II project provides a number of VREs to address the needs of the Fisheries and Aquaculture community. Case studies discussed include the Aquamaps VRE that generates species distribution maps, the ICIS VRE’s repository of statistical datasets and the FCPPS VRE, which provides country profile report templates.
SEE-GRID in South Eastern Europe will present improvements to the usability and services for its end users, including operational tools for monitoring, alerting, job tracking and security as well as application services such as advanced workflows, better data and file management and new applications platforms. EELA-2 in Latin America also presents its enhancements to the functionality of the gLite middleware, which has widened the number of potential applications and sped up the porting process.
The Nordic Data Grid Facility’s experiences in bringing on board a new user community, the materials science virtual organisation are also presented. The main goal of the project was to enable non-LHC scientists to run their jobs on ARC enabled resources. On a wider scale, the South African National Grid Initiative aims to deploy a production-quality regional e-Science infrastructure for all South African researchers. Benefits are already being seen in the areas of physics, geomatics and bioinformatics and, through collaboration with the HP/UNESCO project, the seeds of the first regional African grid initiative. EUAsiaGrid brings together researchers from the Asia-Pacific region, and presents its progress in building, maintaining and developing e-Infrastructure within the region, together with a roadmap towards a sustainable and persistent multinational digital platform.
The User Forum demonstration session traditionally provides the opportunity to mature research work and scientific activities, exposing highly interactive and visually appealing characteristics, to come and present their latest achievements. This year 20 demonstrations have been selected to be presented in two demo slots. For this purpose, the demonstrations are split in two groups each one scheduled for a different day. The first group of 10 demonstrations will be on display during the first slot on Monday afternoon, in parallel with the welcome cocktail, whereas the second group will be presented on Wednesday afternoon. Both sessions will be run in parallel with the poster sessions on display in the same area in the venue.
The demonstrations have been split into two logical groups based on their focus. Thus, on Monday the session will host demonstrations with more scientific focus; i.e. activities who will present scientific results achieved using a large scale Distributed Computing Infrastructures. On Wednesday, the interest will shift to more technical demonstrations, with the scheduled presentations focusing on advanced tools and technologies that facilitate the end-user/DCI interaction as well as on international projects and collaborations, which strive to extend and expand the current horizons of DCI infrastructure to novel technologies and paradigms. Some of these activities have been demonstrated in previous events, thus the attendees will have the opportunity to check upon their progress and be informed about latest results. Others, will be demonstrated for the first time.
Finally as with previous events, the best demonstrations will be selected form the EGEE External Advisory Committee and the event attendees. The best demos will be announced and awarded during the event’s closing plenary on Thursday.
This is the same poster session as in Monday. The same posters will be presented in parallel with Demo Session 2 this time. For a complete list of the posters see the Poster Session timetable for Monday evening.
With the availability of commodity Distributed Computing Infrastructures, scientists are confronted with the problem of finding the right abstractions and tools to hide the distribution and heterogeneity of the underlying system, in order to process their data effectively and efficiently. Different solutions are presented and discussed in this session, which will be closed by a presentation on the experiences and results of the ETICS project.
Data management is becoming one of the key issues for eInfrastructures. Not only are scientific instruments and simulations producing increasing amounts of data, this data needs to be made available to worldwide collaborators in an efficient, reliable, and secure manner. In this session we discuss several aspects of data management on eInfrastructures, from providing reliable access to storage, efficient data transfers between web services, to data centric applications and their workflows.
The session will focus on support to advanced users of the Grid in particular support to MPI parallel job execution and comlex workflows. In the first part of the session the activities of the MPI Task Force will be reported in the light of the recent work being carried out to improve the support at the site level for MPI execution. This will be followed by a report on the current level of support and open requests coming from the users of the MPI Working Group. Complex workflows involving both, serial and parallel jobs will be addressed in the final presentation.
Complete scientific analyses are complex, usually involving multiple stages and multiple applications. Users now routinely take advantage of tools to manage complete analysis workflows, including the bookkeeping, job execution, and data management. This session contains presentations of new or improved workflow tools along with information about how those tools facilitate scientific analyses.
The agenda provides time for questions and discussions. Participants should be prepared to share their own experiences with workflow managers and their needs regarding improvements.
An Introduction to gLite middleware training will be organised on Thursday 16 April 14-17.30 at the University of Uppsala. More information can be found here: http://indicobeta.cern.ch/conferenceDisplay.py?confId=73509
The purpose of this session is to provide an introduction on gLite middleware. The session will include an introductory presentation, followed by practical work for the attendees which will include submitting jobs to EGEE.
The presentation will introduce:
- The capabilities of the gLite services
- The process of getting access to an EGEE production VO and to the GILDA training VO
- The role of high level grid tools and where to find further information on them.
- The most important hands-on modules that are available on gLite services.
Please note that you can register to the training while registering to the conference!