"The overall goal of the project is to 'bake' security into existing Cloud services and business models. With technologies developed in this project, we hope Cloud customers will be able to purchase, manage and optimize the security of their Cloud applications with simple mouse clicks and in a pay-per-use fashion", stated Tian Lan, assistant professor in the Department of Electrical and Computer Engineering and principal investigator for the grant.
Most providers offer cloud computing services on a "one-size-fits-all" model that provides the same levels of availability and reliability - two major aspects of data security - to all customers. However, the current levels may be inadequate for some customers who need greater availability or security and are willing to pay for it, or too expensive for customers who don't need and don't want to pay for the standard level of reliability and availability. And, as Cloud computing becomes more pervasive, customer demand for flexible plans will increase.
By constructing realistic models and developing algorithms to optimize resource allocation and pricing, Dr. Lan, Professor Suresh Subramaniam, and Assistant Professor Howie Huang expect to advance Cloud computing and provide more choice for customers.
"It's all about how the Cloud provider can allocate its resources to satisfy the customers' needs", Dr. Huang stated. "But, this is really a win-win situation for both Cloud providers and Cloud consumers. From the Cloud providers' perspective, this becomes a service they can sell, and they can make more revenue from it. From the consumers' perspective, they have more choice."
The three faculty members joined forces on the project, combining their areas of expertise in networking, optimization, algorithm development and Cloud systems and architecture. Their complementary theoretical and systems experience is providing a unique approach to the challenge of improving Cloud computing availability and reliability.
"As far as we know, we're the only ones conducting this research to provide differentiated reliability to different customers", Dr. Subramaniam stated. Once the team publishes its results, providers such as AT&T, Amazon, Google or others would be free to use the algorithm in their data centres.