Grid computing (or the use of a computational grid) is applying the resources of many computers in a network to a single problem at the same time – usually to a scientific or technical problem that requires a great number of computer processing cycles or access to large amounts of data. A well-known example of grid computing in the public domain is the ongoing SETI (Search for Extraterrestrial Intelligence) @Home project in which thousands of people are sharing the unused processor cycles of their PCs in the vast search for signs of “rational” signals from outer space. According to John Patrick, IBM’s vice-president for Internet strategies, “the next big thing will be grid computing.”

Grid computing requires the use of software that can divide and farm out pieces of a program to as many as several thousand computers. Grid computing can be thought of as distributed and large-scale cluster computing and as a form of network-distributed parallel processing. It can be confined to the network of computer workstations within a corporation or it can be a public collaboration (in which case it is also sometimes known as a form of peer-to-peer computing).

A number of corporations, professional groups, university consortiums, and other groups have developed or are developing frameworks and software for managing grid computing projects. The European Community (EU) is sponsoring a project for a grid for high-energy physics, earth observation, and biology applications. In the United States, the National Technology Grid is prototyping a computational grid for infrastructure and an access grid for people. Sun Microsystems offers Grid Engine software. Described as a distributed resource management (DRM) tool, Grid Engine allows engineers at companies like Sony and Synopsys to pool the computer cycles on up to 80 workstations at a time. (At this scale, grid computing can be seen as a more extreme case of load balancing.)

Grid computing appears to be a promising trend for three reasons: (1) its ability to make more cost-effective use of a given amount of computer resources, (2) as a way to solve problems that can’t be approached without an enormous amount of computing power, and (3) because it suggests that the resources of many computers can be cooperatively and perhaps synergistically harnessed and managed as a collaboration toward a common objective. In some grid computing systems, the computers may collaborate rather than being directed by one managing computer. One likely area for the use of grid computing will be pervasive computing applications – those in which computers pervade our environment without our necessary awareness.

How does it work?

Grids use a layer of middleware to communicate with and manipulate heterogeneous hardware and data sets. In some fields—astronomy, for example—hardware cannot reasonably be moved and is prohibitively expensive to replicate on other sites. In other instances, databases vital to research projects cannot be duplicated and transferred to other sites. Grids overcome these logistical obstacles and open the tools of research to distant faculty and students. A grid might coordinate scientific instruments in one country with a database in another and processors in a third. From a user’s perspective, these resources function as a single system—differences in platform and location become invisible.

On a typical college or university campus, many computers sit idle much of the time. A grid can provide significant processing power for users with extraordinary needs. Animation software, for instance, which is used by students in the arts, architecture, and other departments, eats up vast amounts of processor capacity. An industrial design class might use resource-intensive software to render highly detailed three-dimensional images. In both cases, a campus grid slashes the amount of time it takes students to work with these applications. All of this happens not from additional capacity but through the efficient use of existing power.

Why is it significant?

Grids make research projects possible that formerly were impractical or unfeasible due to the physical location of vital resources. Using a grid, researchers in Great Britain, for example, can conduct research that relies on databases across Europe, instrumentation in Japan, and computational power in the United States. Making resources available in this way exposes students to the tools of the profession, facilitating new possibilities for research and instruction, particularly at the undergraduate level.

Although speeds and capacities of processors continue to increase, resource-intensive applications are proliferating as well. At many institutions, certain campus users face ongoing shortages of computational power, even as large numbers of computers are under-used. With grids, programs previously hindered by constraints on computing power become possible.

What are the downsides?

Being able to access distant IT assets—and have them function seamlessly with tools on different platforms—can be a boon to researchers, but it presents real security concerns to organizations responsible for those resources. An institution that makes its IT assets available to researchers or students on other campuses and in other countries must be confident that its involvement does not expose those assets to unnecessary risks. Similarly, directors of research projects will be reluctant to take advantage of the opportunities of a grid without assurances that the integrity of the project, its data, and its participants will be protected.

Another challenge facing grids is the complexity in building middle-ware structures that can knit together collections of resources to work as a unit across network connections that often span oceans and continents. Scheduling the availability of IT resources connected to a grid can also present new challenges to organizations that manage those resources. Increasing standardization of protocols addresses some of the difficulty in creating smoothly functioning grids, but, by their nature, grids that can provide unprecedented access to facilities and tools involve a high level of complexity.

Where is it going?

Because the number of functioning grids is relatively small, it may take time for the higher education community to capitalize on the opportunities that grids can provide and the feasibility of such projects. As the number and capacity of high-speed networks increase, however, particularly those catering to the research community and higher education, new opportunities will arise to combine IT assets in ways that expose students to the tools and applications relevant to their studies and to dramatically reduce the amount of time required to process data-intensive jobs. Further, as grids become more widespread and easier to use, increasing numbers and kinds of IT resources will be included on grids. We may also start to see more grid tie-ins for desktop applications. While there are obvious advantages to solving a complex genetic problem using grid computing, being able to harness spare computing cycles to manipulate an image in Photoshop or create a virtual world in a simulation may be some of the first implementations of grids.

What are the implications for teaching and learning?

Higher education stands to reap significant benefits from grid computing by creating environments that expose students to the “tools of the trade” in a wide range of disciplines. Rather than using mock or historical data from an observatory in South America, for example, a grid could let students on other continents actually use those facilities and collect their own data. Learning experiences become far richer, providing opportunities that otherwise would be impossible or would require travel. The access that grid computing offers to particular resources can allow institutions to deepen, and in some cases broaden, the scope of their educational programs.

Grid computing encourages partnerships among higher education institutions and research centers. Because they bring together unique tools in novel groupings, grids have the potential to incorporate technology into disciplines with traditionally lower involvement with IT, including the humanities, social sciences, and the arts. Grids can leverage previous investments in hardware and infrastructure to provide processing power and other technology capabilities to campus constituents who need them. This reallocation of institutional resources is especially beneficial for applications with high demands for processing and storage, such as modeling, animations, digital video production, or biomedical studies.

The Grid Computing Information Centre

The Grid Computing Information Centre (GRID Infoware: http://www.gridcomputing.com) aims to promote the development and advancement of technologies that provide seamless and scalable access to wide-area distributed resources. Computational Grids enable the sharing, selection, and aggregation of a wide variety of geographically distributed computational resources (such as supercomputers, compute clusters, storage systems, data sources, instruments, people) and presents them as a single, unified resource for solving large-scale compute and data intensive computing applications (e.g. molecular modeling for drug design, brain activity analysis, and high energy physics). This idea is analogous to electric power network (grid) where power generators are distributed, but the users are able to access electric power without bothering about the source of energy and its location.

References:

[1] Rayburn. 7 Things You Should Know About Grid Computing. www.educause.edu/eli.  January 2006.

[2]   Buyya, Rajkumar. Grid Computing Info Center (GRID Infoware). http://www.gridcomputing.com. Accessed November 2010.

[3]   Anonym. What is Grid Computing?. www.whatis.com. September 28, 2001.