EGEE-II

EGEE-II
Name	EGEE-II
Full name	Enabling Grids for E-sciencE II
Start date	2006
End date	2010
Coordinator	CERN
Partners	See Project Structure and Partners
Budget	Approximately €27 million (EU contribution)

EGEE-II EGEE-II was a European Commission–funded grid computing project that followed on from earlier initiatives to deliver a production-quality grid computing infrastructure for scientific communities, coordinated by CERN and involving partners including INFN, CNRS, DESY, and numerous universities such as University of Oxford and Imperial College London. It linked researchers across institutions such as European Organization for Nuclear Research facilities, national laboratories like FZJ, and research networks like GÉANT to support large-scale collaborations in fields including High Energy Physics, Bioinformatics, Earth observation, and Astrophysics. EGEE-II operated within the framework of projects funded under the European Commission's Framework Programme ecosystem, connecting regional initiatives such as DEISA and global efforts like Open Science Grid.

Overview

EGEE-II built on the foundations laid by EGEE-I and aimed to provide a robust operational grid service spanning production middleware deployments from partners such as ARC teams at Nordic Data Grid Facility and gLite developers from INFN, with coordination by CERN staff experienced from experiments like ATLAS and CMS. The project operated across national research organizations including CNRS, CEA, STFC, NIKHEF, and international collaborators such as TRIUMF and FNAL, integrating middleware work from groups like European Middleware Initiative contributors and relying on standards bodies including OGF and IETF.

Objectives and Scope

EGEE-II aimed to provide a sustainable production-quality grid infrastructure for scientific use, support multidisciplinary user communities such as BioMed, ENVIRONMENT, and HEP experiments, and foster interoperability with infrastructures including TeraGrid and Open Science Grid. Specific goals included operational support coordinated with regional projects like EUMEDGRID and SEEGRID, middleware evolution informed by partners such as SARA and FZJ, and outreach involving institutions like European Space Agency and European Molecular Biology Laboratory. The scope covered deployment across computing centers like CERN Tier-0, national tier centers such as GridKa and KIT, and integration with data repositories hosted by organizations like EMBL-EBI.

Project Structure and Partners

Governance was coordinated by CERN with partner contributions from national research organizations and universities including INFN, CNRS, DESY, FZJ, NIKHEF, CETA-CIEMAT, SARA, CERN IT, TRIUMF, FNAL, University of Cambridge, University of Edinburgh, University of Oxford, Imperial College London, University of Amsterdam, University of Manchester, University of Pisa, University of Padua, University of Bologna, University of Rome Tor Vergata, University of Warsaw, Jülich Research Centre, CEA, STFC, KTH Royal Institute of Technology, ETH Zurich, EPFL, TU Berlin, Politecnico di Milano, NCSA, PNNL, Argonne National Laboratory, Lawrence Berkeley National Laboratory, Rutherford Appleton Laboratory, and others. The consortium included middleware developers from groups associated with gLite, ARC, and UNICORE, operations teams from regional grids like Nordugrid, and application champions from domains represented by ATLAS, CMS, LHCb, ALICE, LIGO Scientific Collaboration, Human Genome Project-related institutions, and environmental modeling centers such as ECMWF.

Technology and Infrastructure

EGEE-II deployed production middleware stacks based on gLite components developed by partners including INFN and integrated security solutions using credentials interoperable with systems promoted by IGTF and Shibboleth. The infrastructure leveraged compute resources at sites like GridKa, storage elements maintained by CERN Storage teams, and data management services influenced by projects such as DataGrid and dCache work from DESY. Networking relied on research backbones like GÉANT and national research networks such as SURFnet and RENATER for high-throughput data transfers supporting experiments including ATLAS and CMS. Monitoring and operations used tools developed by Nagios communities and site certification practices aligned with OGF best practices.

Major Activities and Applications

Major activities included operating a 24x7 grid service used by communities such as High Energy Physics experiments ATLAS, CMS, LHCb, and ALICE for distributed analysis, supporting Bioinformatics workflows at EMBL-EBI and Sanger Institute, enabling Earth observation processing for agencies like ESA, and facilitating simulations for Climate modeling centers like ECMWF. EGEE-II ran application support and outreach with use cases from collaborations including LIGO, CERN Neutrinos to Gran Sasso (CNGS), Biomedical Virtual Organization efforts, and computational chemistry groups at University of Cambridge. It organized events with participants from PRACE discussions, training through TERN-style schools, and interoperability tests with Open Science Grid and TeraGrid teams such as NCSA and Argonne National Laboratory.

Funding and Timeline

EGEE-II was funded by the European Commission under the Framework Programme 6 continuation mechanisms with co-funding from participating institutions including CERN and national agencies such as INFN and CNRS. The project ran approximately from 2006 to 2010, following EGEE-I and preceding projects like the EGEE-III phase and the European Grid Initiative movement that contributed to the formation of the European Grid Infrastructure (EGI). Budget contributions came from EU grants and in-kind support from partners including national ministries, research councils like EPSRC and ANR, and computing centers such as FZJ and CERN IT.

Impact and Legacy

EGEE-II accelerated adoption of distributed computing across communities associated with Large Hadron Collider experiments ATLAS and CMS, informed middleware consolidation efforts leading to EGI operations, and influenced standards discussions at OGF and identity frameworks through IGTF. Its operational models and community support practices fed into successor infrastructures such as EGI and partnerships with Open Grid Forum participants, and its collaborations with international grids like Open Science Grid strengthened transatlantic science links involving Fermilab and Brookhaven National Laboratory. Many partner institutions including CERN, INFN, DESY, EMBL-EBI, and ECMWF incorporated lessons from EGEE-II into long-term computing strategies and multinational projects such as PRACE and HPC centers at national labs.

Category:Grid computing projects