Grid

about grid| Biogrid | HEPgrig | Chemgrid | Earthgrid


About Grid 

The idea of computational and data grid is often explained using the electric power grid example. The electric power grid delivers electric power in a distributed and standardised way. You can use any device that has a standard plug if you are able to connect it to the electric power grid through a standard socket.

In the famous book "The Grid" Ian Foster and Carl Kesselman have explained: "The current status of computation is analogous in some respects to that of electricity around 1910. At that time, electric power generation was possible, and new devices were being devised that depended on electric power, but the need for each user to build and operate a new generator hindered use. The truly revolutionary development was not, in fact, electricity, but the electric power grid and the associated transmission and distribution technologies".

For the scientist the process is looking as follows:
1. The user submits his request, specifying the kind of application he wants to use, the operating system and providing input data.
2. The Grid finds and allocates suitable resources (computing systems, storage facilities) to satisfy the user's request.
3. The Grid monitors request processing and send messages about the status of the fulfilment of the request.
4. Finally, The Grid notifies the user when the results are available and presents them.
As the example shows, the user doesn't have to know which resources he/she is using and where they are. They just get computing power and storage space from the Grid through a standard interface.

Therefore, the Grid delivers computational power on the basis of who needs the power, rather than where the power is located. You can run your job on many computers at once, and choose the machines that best suit your job.

There are great number various grid projects in the world, concerning many areas of sceintific research (space investigation, biology, High Energy Physics, climat research, medical research, mathematic, chemistry, and so on). European DataGrid (EDG) is one of these projects.

DataGrid

European DataGrid is a project funded by the European Union that aims to enable access to geographically distributed computing power and storage facilities belonging to different institutions. It provides the necessary resources to process huge amounts of data coming from scientific experiments in three different disciplines: high energy phisics, biology and earth observasion.

1. Biology
There is an increasing need today for remote medical data access and processing. The DataGrid project's biology testbed is providing the platform for the development of new algorithms on data mining, databases, code management, graphical interface tools. It is facilitating the sharing of genomic and medical imaging databases for the benefit of international cooperation and health care.

2. High Energy Phisics
One of the main goals for High Energy Physics is to answer longstanding questions about the fundamental particles of matter and the forces acting between them. In particular the goal is to explain why some particles are much heavier than others, and why particles have mass at all.
CERN is building the Large Hadron Collider (LHC), the most powerful particle accelerator in the world for investigating so called " Higgs field". It will generate huge ammount (petabytes) of data.
The DataGrid Project is providing the solution for storing and processing this data. A multi-tiered, hierarchical computing model will be adopted to share data and computing power among multiple institutions.

3. Earth Observation
The European Space Agency downloads from satellites for about 100 Gigabytes of raw images per day. For example, only OMI (Ozone Monitoring Instrument) satellite sends 3624 Mbyte per 100 minutes. It requires tremendous ammount of computational resources for data processing which could be provided by EDG. The analysis of atmospheric ozone data has been selected as a specific testbed for the DataGrid.