Adaptive Resource Management for Service Workflows in Cloud Environments

Abstract

Cloud computing enables the on-demand provisioning of virtualized resources to its hosted applications and services to satisfy their fluctuating resource needs. As business processes and scientific jobs become more intricate, traditional reactive resource management method is not able to meet the new requirements. In this paper, we investigate the problem of dynamically managing virtualized resources for service workflows in a cloud environment. An adaptive algorithm is proposed that makes resource management decisions based on predictive results and high level user specified thresholds. The algorithm is also able to coordinate resources among the component services of a workflow so that unnecessary resource allocations and terminations can be avoided. We use simulations on synthetic workload data to evaluate and demonstrate the effectiveness of the algorithm.