Business Innovation Homepage > IT Optimization

The concept of grid computing isn’t new, but the technology has garnered attention as organizations look for more efficient ways to use computing resources and rely more heavily on processing power to run a variety of business applications.

With grid computing, organizations can take advantage of high-capacity computing by leveraging distributed systems that are connected by networks. Grid computing involves on-demand provisioning of resources, computing resource sharing among different user organizations, and the use of open standards and protocols. It also enables organizations to efficiently make use of unused computing resources.

The idea of grid computing evolved from the massive computational needs of scientific organizations and government labs, which realized they could share computing resources to meet their common goals. A number of business applications are seen as suitable for grid computing, and vendors such as IBM, Hewlett-Packard and Sun Microsystems are offering grid-related products and services.

But grid computing is in the relatively early stages of development, and standards are still being developed based on the work of major vendors. One such specification is the Open Grid Services Architecture (OGSA), a standard for grid computing environments based on Web services.

An organization called the Global Grid Forum, which consists of vendors, developers and users, is attempting to create global standards for grid computing. Another group, the Organization for the Advancement of Structured Information Standards (OASIS), is working on best practices and guidelines for grid technologies.

Because the technology is still new and standards are uncertain, experts say there’s some risk with deploying grid computing. Other possible concerns are that some applications might not run well on a grid, and moving capacity from one grid system to another might prove problematic.

Furthermore—as with any kind of distributed or shared computing environment—there are potential security issues. Organizations must be comfortable with the fact that their data might be running on a shared system.

On the other hand, the benefits of the technology are compelling. Grid computing is highly scalable, so organizations could leverage computing capacity based on their current needs. The high throughput levels offered enable businesses to process information and conduct transactions more quickly. And organizations can take advantage of a grid to collaborate with business partners on a major initiative like new product design and development.

IBM offers grid computing packages tailored to five key business areas across nine industries. For example, IBM Grid Solution for Data Intensive Computing has components including IBM BladeCenter configured with four blades, a Linux operating system, and grid middleware that enables application scheduling, dynamic resource allocation and resource sharing. IBM’s WebSphere DataStage provides data integration across multiple data sources.

Another offering, IBM Grid and Grow for Actuarial Analysis, is a suite of solutions that address performance and data issues facing actuaries who use applications for life, pension and annuity insurance analysis. The grid elements include the IBM eServer BladeCenter with a choice of seven blades, Windows Server operating system and a services package. Other IBM grid offerings are aimed at the financial services and health care industries.

Hewlett-Packard is “grid-enabling” all of its products that connect to a network, including handheld devices, desktop computers and server blades. The company says all of its devices will be able connect with and serve as resources on a grid. To prepare the products for a grid environment, HP is implementing grid middleware. It’s using the Globus Toolkit, an open source grid implementation standard, on all its servers running HP-UX, Linux and Tru64 UNIX.

HP also has developed HP StorageWorks Grid, a virtualized, standards-based architecture for making data a shared resource on a network. And the company offers grid consulting services designed to help organizations design, deploy and manage a grid implementation.

Sun provides a grid service that enables organizations to easily increase or scale back computing resources as needed. The service, called Sun Grid, provides organizations with access to computing power at Sun’s data centers via the Internet.

Click here for more IT Optimization articles