On Utility Driven Deployment in a Distributed Environment

Abstract

By harnessing the computational power of distributed heterogeneous resources, it is possible to build a large scale integrated system so that a centralized program is partitioned and distributed across those resources in a way that maximizes the system's overall utility. However, building such a system is a staggering challenge because of the associated complexities. This paper proposes a self-managing distributed system ADE, that incorporates autonomic entities to handle the complexities associated with distribution, coordination and efficient execution of program components. The proposed approach models a centralized application in terms of an application graph consisting application components and then deploys the application components across the underlying hierarchically organized distributed resources so that all constraints and requirements are satisfied and the system's overall utility is maximized. Then, based on the observations obtained by the monitoring of the system resources, ADE redeploys the application graph to maintain maximized system utilization in spite of the dynamism and uncertainty involved in the system