Embed Size (px)
Citation preview
Co-ordination & Harmonisation of Advanced e-Infrastructures for Research and Education Data Sharing
Research Infrastructures – Proposal n. 306819
Research Communities, Data Repositories and Science Gateways
EUMEDCONNECT3 Meeting, Amman – 16 June 2013
Federico Ruggieri, INFN/GARR ([email protected])
Outline
The CHAIN-REDS project Research Communities The CHAIN-REDS Knowledge Base The Science Gateways Summary and conclusions
Regional Grid infrastructures
CNGrid
NKN & Garuda
EUAsiaGrid
SAGrid & SANREN
GISELA
3
Status
Co-ordination & Harmonisation of Advanced e-Infrastructures for Research and Education Data Sharing
Research Infrastructures – Support Action Grant Agreement n. 306819 Total Costs of € 2.3 M Max. EC contribution: € 1.52 M Start date: 1 December 2012 Duration: 30 Months
4
Partners and roles
5
INFN (IT) – Coordinator CIEMAT (ES) – WP4 Leader GRNET (GR) – WP3 Leader CESNET (CZ) – WP5 Leader UBUNTUNET (MW) – Africa CLARA (UR) – Latin America IHEP (CN) – China ASREN (DE) – Arab States SIGMA-ORIONIS (FR) – WP2 Leader C-DAC (IN) – India (Amendment)
Action lines (1/2)
Distributed Computing Infrastructure DCI
• Provide ongoing support of the DCI road-map for intercontinental DCI collaboration, specified within the CHAIN project
Regional Operation Centres ROC
• Support stability of existing and emerging Regional Operation Centres. Cooperate with other projects & initiatives (e.g. AfricaConnect, TEIN3) to support the development of eInfrastructures and key VRCs in Africa, Asia, Latin America and the Middle-east
Clouds for Research and Education Cloud
• Support for coordination of Cloud developments for Research & Education with other regions (e.g. China, India, Latin America)
Action lines (2/2)
Infrastructures and Repositories Data
• Extend the CHAIN Knowledge Base with information on Data Infrastructures: collecting issues, best practices and identifying data repositories of direct interest for VRCs Support the study of data infrastructures for a target subset of VRCs (e.g. Agricolture, Climate Change, Health, Biomedicine, etc.)
Science Gateways SG
• Promote the usage of Science Gateways as a means for attracting new communities and promote the use of eInfrastructures for every researcher
Federations of Identity Providers IDF
• Foster the creation of Identity Federations in cooperation with Certification Authorities; promote and coordinate their usage. Support integration of different AA approaches
VRCs addressed by the first CHAIN project
Several Virtual Research Communities in different domains have been contacted: Agriculture, Biomedicine, Climate Change, Digital Cultural Heritage, Health, High Energy Physics, Life Sciences, Seismology, Weather Forecast
MoUs signed with 6 VRCs Support for new VRCs: jModelTest, Seismology,
Climate Change, Agriculture Many applications demonstrated in the Worldwide
Interoperability Test with the Science Gateway
New VRCs addressed
Agriculture (agINFRA project)
Open Geospatial Consortium (EarthServer)
EUDAT
The CHAIN Knowledge Base (www.chain-project.eu/knowledge-base)
RREN(s) NREN NGI CA(s) Ident. Fed(s) ROC(s) Grid site(s) Application(s)
Largest e-Infrastructure related knowledge base. Information both from the survey and other sources for more than half of the countries of the world
CHAIN-REDS program for Data Infrastructures
Identify standards to easily gather and access both Open Access Document Repositories (OADRs) and Data Repositories (DRs)
Build a demonstrator to easy visualise and access OADRs and DRs (both geo-views and tab-views)
Correlate OADRs and DRs to create linked data and discover new knowledge through semantic enrichment of metadata
Promote Data Infrastructure standards and identify new OADRs and DRs from regions addressed by the project (Africa, Middle-East and Gulf Region, Latin America, China, India, Far-East Asia)
Populate the demonstrator with these new repositories, add them to the semantic enrichment tool, and set-up at least two use-cases from different domains
Open Access Document Repositories (OADRs)
• ∼2,500 repos • >33 M docs
Open Access Document Repositories (OADRs)
14
Data Repositories (DRs)
• >500 repos • Lots of data !
Data Repositories (DRs)
17
Extending the CHAIN-REDS KB with KLIOS
Linked data semantic search
Semantic enrichment Metadata harvesting
Multi-layered architecture
OA
DR
s
Dat
a R
epos
. OAI-PMH OAI-PMH
Harvester (running on grid/cloud)
Linked-data search engine
Semantic-web enrichment
End-points
Harvester (running on grid/cloud)
Multi-layered architecture
20
Linked data semantic search (www.chain-project.eu/linked-data)
....... Science
Gatew
ay
App. 1 App. 2 App. N
Embedded Applications Administrator Power User Basic User
Users from different
organisations having different
roles and privileges
Promote the Science Gateway model
Standard-based middleware-independent
Grid Engine
21
Europe, Africa, Asia Pacific, Latin America
Brasil China
India
The agINFRA Science Gateway
22
http://aginfra-sg.ct.infn.it/
WebGIS based ISIS
23
DECIDE Science Gateway (www.eu-decide.eu)
Africa Grid Science Gateway (http://sgw.africa-grid.org/
Science Gateways and clouds – The MyCloud service
26
Powered by:
27
The CHAIN-REDS Cloud Interoperability Demo
VM Market Place MyCloud
Basic VM1
Basic VM2
VRC1 VM1 VRC1
VM2
VRC2 VM1 VRC2
VM2
Node of cloud m/w 1 on site X
Node of cloud m/w 2 on site Y
Node of cloud m/w 3 on site Z
Standards to be used
28
OCCI (http://occi-wg.org): For remote management of cloud computing infrastructure
CDMI (http://www.snia.org/cdmi): For cloud data management
Clouds and Grids
Grid has been conceived as a resource sharing infrastructure Grids provide High Throuput Computing that fits many
applications Clouds have a clear business model that allowed companies to
provide services on the market Virtualisation and elastic computing are needed by several
scientific domains (e.g. interactive and web based applications) Clouds and Grids can cohexist in the Research & Education
domain provided that the strenghts of both can be merged
29
R&E Clouds
Cloud infrastructure for R&E should be based on Open SW & Standards
Financial: Public institutions are frequently receiving projects’ driven funding.
Difficult to fund long term contracts with Cloud providers
Technical: Resource sharing is an issue if institutions get services from
different providers. Building securely across several administrative domains is difficult: Federation of Clouds is still not a reality
Long term preservation of data has still many issues to be addressed (e.g. what happens to the data after the project end ?)
Requirements of scientists evolve and new technical challenges appear that will push for innovation
30
GARR-X & GARR-X Progress
Next Generation Network GARR-X Access to HTC, HPC, Grid &
Cloud Computing, Storage
GARR-X Progress for the South of Italy Grant of 46.5 M€ recently approved
by the Ministry of Education and Research
10-100 Gbps fiber connectivity
New cloud and storage infrastructure for R&E: 6.000 Cores, 6 PB storage
31
Summary and conclusions The first usage of SG in several projects is very encouraging Data Infrastructures are becoming an essential component of e-
Infrastructures Next years’ biggest challenge will be to uniquely correlate scientific
papers with data used to write them with applications used to analyse them so to be able to go across the knowledge path both ways
Semantic-web and linked-data technologies can play a major role in this context and CHAIN-REDS aims to promote these standards in the targeted regions
OADRs’ and DRs’ managers/owners in are welcome to contact me to share their data within the CHAIN Knowledge Base (both in Africa and Latin America this is already happening)
CHAIN-REDS is also looking forward to receiving feedbacks from all interested organisations on the Knowledge Base and the semantic search service
Co-ordination & Harmonisation of Advanced e-Infrastructures for Research and Education Data Sharing
Research Infrastructures – Proposal n. 306819
Questions ?
