D-Grid
The D-Grid Initiative is a Grid Initiative in the Federal Republic of Germany.
Generally
D-Grid is to help build the goal, a sustainable grid computing infrastructure for research and development in both the academic and the industrial area in Germany. The construction phase has been funded since 1 September 2005 by the Federal Ministry of Education and Research (BMBF ) by means of several bidding rounds with more than 70 million euros. As part of this support more than 20 projects have been initiated in which to participate more than 100 German research institutions. Furthermore, it was found laying down special measures computing and storage infrastructure to ensure a smooth transition to a Grid operating without disturbing the current infrastructure offering.
The D-Grid projects can be divided into groups based services, Higher Grid services, academic disciplines and commercial users.
Basic services
Under basic services means a range of services that are essential for the viability of a grid. These include the provision of grid middleware and the establishment of an operational concept, the security aspects and the formation of virtual organizations (VO) covers. These basic services are provided by the D-Grid Integration Project (DGI 1: Sept. 2005 - Aug. 2007; DGI 2: - December 2010 Jan. 2008 ) provided. To respond to new demands from users, so-called Gap projects were further adapted to develop the special basic services available and will work closely with the integration project.
Higher services
Higher Grid services relate requirements made for the operation of a Grid are not necessary, but can not be used by only one discipline. Examples of these services are services for resource management, for the establishment and monitoring of Service Level Agreements ( SLA) or for data storage. Projects that develop these services, ensure that the services are based on the basic services and can be easily integrated from different disciplines.
Academic Disciplines
In many scientific disciplines, large data sets are used, which are made available to all scientists of one discipline are available. Due to the spatial distribution of the scientists using a grid structure is inevitable. To promote the use of Grid projects in the fields of astronomy, high energy physics, climate science, medicine, engineering and the humanities have been established. Within these projects, discipline-specific Grid services are developed. The respective projects will lay the foundation for discipline- oriented grid structures that support as all scholars in the various discipline in the use of the grid.
Commercial users
While large corporations with several often globally dispersed locations often set up their own enterprise grid, this is often not possible for smaller companies. Although these businesses need increasingly access to IT resources, but the acquisition and operation of these resources are connected to them too expensive, especially as the need arises in batches and not continuously. The grid with independent service and resource providers is a promising alternative for such smaller companies if the services are tailored to the needs of the company. In related projects such services are to be developed in cooperation with companies.
Examples of projects
Below are some projects of the D- Grid initiative are described in more detail:
AstroGrid- D
In AstroGrid -D ( also German Astronomy Community Grid, GACG ) work together a total of 13 scientific institutions in the fields of astronomy and computer science and high-performance data centers. The main objective is the integration of the research institutes in Germany in a uniform grid-based infrastructure to support distributed, collaborative work. Existing hardware and software resources, inter alia, astronomical data archives and robotic telescopes in the participating research institutes, should be integrated.
AstroGrid- D supports the standards of the International Virtual Observatory Alliance ( IVOA ) and works with international Grid projects. The management of the AstroGrid- D is located at the Astrophysical Institute Potsdam ( AIP).
C3 -Grid
In Collaborative Climate Community Data and Processing Grid, called C3 -Grid, there is a composite of climate researchers. This project is concerned not only with the climate research, but also with the interactions of the climate system with socio -economic systems. In climate research, the behavior of the Earth system is complex models simulated. The arising model data is collected in addition to the continuously arriving observational data of meteorological services in archives in various locations. For an extensive ( global and regional ) analysis of these data, it is necessary to link them together and archives to work in the C3 -Grid. Exists also through the analysis and storage of satellite data in climate research an ever becomes greater need for storage space and computing capacity. The ability to store the resulting data in a grid and to analyze, is to support the work of climate scientists and their cooperation. The management of the C3 -Grid is with the Alfred Wegener Institute for Polar and Marine Research ( AWI) in Bremerhaven.
D-Grid IaaS
At the beginning of Grid Computing proprietary implementations were for the different Grid middlewares, inter alia, developed in the areas of authorization, monitoring and scheduling. Only in recent years there is a trend towards standardization and harmonization of grid middlewares. A similar, but accelerated development befalls the cloud computing. Cloud computing offers, it can be both for IaaS, SaaS or PaaS but also to. However, the term cloud computing is often associated only with Amazon's EC2 offering.
Until now, access to the D-Grid resources across the three D-Grid established Grid middlewares gLite, Globus Toolkit and UNICORE. This middleware originally developed for an academic clientele and bring a largely non- intuitive usability with it. Especially in the production of small and medium-sized companies as new customers, the associated complexity deters and is reduced by the EC2 offering. The filling of the fourth middleware column of the D -Grid is to take place by a Compute Cloud middleware, the eCloud Manager. This already supported in the current version, the control of VMware, Xen and Hyper-V to give D -Grid resource providers remain free to choose their virtualization environment.
On the D-Grid IaaS project, the Robotics Research Institute at the Technical University of Dortmund and the fluid Operations AG are involved.
GDI -Grid
The Spatial Data Infrastructure Grid is a consortium of universities and companies a project to Hinführung existing spatial data infrastructures on grid technologies. The partially very computationally complex processes and algorithms that are used by geoscientists for modeling and simulation will benefit from the national grid infrastructure, by computing and storage resources are used locally. First, frequently repeated Prozessierungsaufgaben should be outsourced (such as tessellation ) in grid processes. In addition to the very large amount of data in spatial data infrastructures (eg, DGM, maps and metadata catalogs) be as decentralized as possible and accessible to all beneficiaries in the framework of the applicable license agreement.
The concatenation of different processing steps to illustrative application models is demonstrated by three example scenarios:
- In a scenario of the flooding simulation disasters such as the Elbe flood are simulated by combining grid technologies and GDI.
- The propagation of traffic noise on the road network of a city and its impact on the surrounding residential and commercial areas is the subject of a second simulation dar.
- A third scenario is to provide emergency personnel with a way to create disaster a dynamic path planning, which means the traditional vehicle navigation around a grid- based calculation and consideration of obstacles to be extended (eg by fallen trees or debris ).
The GDI -Grid project is led by the Regional Computing Centre for Lower Saxony ( RRZN ) of the University of Hannover.
HEP -Grid
The HEP community -Grid, or short- HEP -Grid, the German High Energy Physics Grid. The management of this project is located at the German Electron Synchrotron ( DESY) in Hamburg, it will work nine German institutes and universities and a number of associated partners.
The main objective of HEP- Grid is to improve data analysis in high-energy physics through the effective utilization of distributed and networked storage and computing resources. The planned developments are important additions to the used Grid software from the project Enabling Grids for E- sciencE ( EGEE ) and LHC Computing Grid ( LCG). They are an important contribution to the data analysis of current and future large-scale experiments such as the Large Hadron Collider ( LHC) at CERN or at the planned International Linear Collider ( ILC).
The community project PortalU is an association in the field of engineering sciences. PortalU allows grid- based applications and efficient use of shared computing and software resources for engineering projects. As part of this project is to create a grid environment for engineering and scientific applications. The flexible use of Grid technologies are combined modeling, simulation and optimization expertise, as well as the sharing of resources can be efficiently possible.
Five different types of applications ( foundry technology, transformation, groundwater flow and transport, turbine simulation and interaction of fluid and structural mechanics) to be processed by way of example, to cover the three main areas of computationally intensive engineering applications (coupled multiscale problems, coupled multidisciplinary problems, and distributed simulation -based optimization ). In particular, adaptive and scalable process models and grid-based runtime environments for these purposes are developed.
Engineering Scientific Research is inherently application-and industrienah. The support virtual prototyping and optimization of engineering science processes is therefore a focus of the project. The line of PortalU lies with the High Performance Computing Center (HLRS ) of the University of Stuttgart.
MediGRID
In the joint project MediGRID, renowned research institutions have medicine, bioinformatics and health sciences together in the fields as a consortium to develop a Grid middleware integration platform and it fitting end eScience services for biomedical science. The further integration of a number of associated partners from industry, utilities and research institutions, the project on a broad stakeholder base.
For the project, a modular division of tasks was chosen: In the four methodological project modules (middleware, ontology tools, resources, fusion and eScience ) the relevant consortium partners will gradually develop a grid infrastructure. They take into account in particular the requirements of Grid users from the field of biomedicine, which are worked out examples in the three application-oriented project modules ( Biomedical computer science, image processing, Clinical Research).
SuGI
SuGI - Sustainable Grid Infrastructure - Gap is a project of the D-Grid initiative, with the goal of grid computing to bear in the area and there to make usable. The project is aimed at the large number of small and medium-sized data centers at universities and companies not previously or use the grid technology to a small extent. They are supported in the provision of grid resources and services.
About the construction of a scaled training infrastructure ( SuGI training portal ), technical assistance with the installation and operation of the middleware and the development and evaluation of legal and organizational structures makes SuGI a lasting contribution to the development of a Grid Platform for e-Science in Germany.
Text Grid
Although e-Science and Grid technologies concepts originate from the natural sciences and medicine, there are also wide areas of application in the humanities and the arts. Text Grid is the first humanities Grid project in Germany, and thus participates together with other e -Humanities initiatives of the first hour of " gridification " the humanities.
Text grid delivers in this way contribute to the text-based research. A grid -enabled Workbench enables the Community philological processing, analysis, annotation, editing and publication of scientific texts. Grid technologies connect the existing text archives, and - inspired by approaches and development opportunities for Semantic Grid - combine their resources, such as corpora, dictionaries and reference tools with each other. The open for further projects interfaces enable synergies with other initiatives in the scientific text data processing as well as a rationalization of academic work including through streamlined access to primary sources and tools.
In text grid following specific scientific and technical partners cooperate: the SUB Göttingen (project management ), the Institute for German Language, the Max Planck Digital Library, the University of Trier, University of Applied Sciences Worms, Paderborn University, the Technical University of Kaiserslautern, the Ludwig- Maximilians- University of Munich, the University of Würzburg and the company DAASI International GmbH.
WISENT
WISENT is the knowledge network energy meteorology - a BMBF-funded e-Science project for information technology optimized collaboration of organizations engaged in research and development in energy meteorology. The focus is on renewable energies that depend particularly challenged by the weather.
The partners in WISENT are the German Aerospace Center (DLR ), the University of Oldenburg, Oldenburg Research and Development Institute of computer science tools and systems ( OFFIS ) and meteocontrol.
With the construction of the funded by the Helmholtz Virtual Institute of Energy Meteorology ( vIEM ) is an institutional base created in the IT sector now be complemented by innovative grid-based techniques for accessing distributed and often very heterogeneous resources and distributed processing necessary makes. Feature of the work in vIEM is the sharing and processing of large data sets (on the order of many terabytes), for which no sufficiently powerful tools and services are currently available. The parallel processing of the data represents a promising approach for these problems
ValueGrids
ValueGrids designed and developed an integrated approach to service level management in value networks. This provider of software -as- a-Service will be put in a position, the sustainable use of the D-Grid infrastructure.
The cooperation partners of ValueGrids are: SAP AG ( coordination), the Conemis AG, IBM Germany Research & Development GmbH, Albert- Ludwigs- University of Freiburg and Karlsruhe Institute of Technology.