A Generalized Petri Net-based Modeling Framework for Service Reliability Evaluation and Management of Cloud Data Centers

Abstract A cloud data center is a critical infrastructure whose service reliability is relevant for service delivery. Constituting the carrier of service for cloud computing, the IT architecture of a cloud data center plays an important role, since it directly relates to service reliability. However, most existing research focuses only on the connectivity of the IT architecture and on service considering only the processing procedure. In order to bridge the gap between the existing works and reality, a hierarchical colored generalized stochastic petri net is proposed to evaluate the service reliability by Monte Carlo simulation, which comprehensively considers the connectivity and performance of the IT architecture and the dynamic of service delivery. The modeling and simulation framework is applied to the cloud data center of an insurance company and cost-effective strategies are found to support the configuration, operation and maintenance of the cloud data center.