A State-Space Approach for Service-oriented SLA Translation

Abstract

Interaction among components leads to the complication of a service system. In order to satisfy the consults between users and service providers to get the relation between upper targets and lower objectives, Services Level Agreement (SLA) translation is introduced. Previous works often introduce a state-space approach for devices in SLA translation. But little work has been carried out in extending the SLA translation towards the service composition. In this paper, based on the state-space Formulation to model the complex service system, we present a service component framework to optimize resource allocations. In particular, we propose a clustering analysis method, which effectively reduces the analyzing cost, to integrate the variables of service composition. We characterize and analyze the service component to obtain the ranges of their variables meeting SLA, which can be used to conduct resource allocations optimization. A comprehensive set of experiments is finally carried out to demonstrate the effectiveness and efficiency of our proposed approach.