Formally Modeling and Analyzing the Adaptive Resource Management for Cloud Applications

Abstract

Cloud computing has attracted much interest recently from both industry and academic. However, it is a challenge to enforce resource manages for those applications especially in voluntary-resource cloud due to the heterogeneous and highly dynamic environment. To address this emerging, important problem, we propose a method to model and analyze adaptive resource management for cloud applications. First, resource management process is abstracted as meta-object by using the reflection mechanism, which includes the state assessment, online monitoring, format checking and adaptive recovery. Second, Petri nets are used to construct the base layer model, meta layer model, meta-object protocol and other components, thus forming the resource management model. Third, the operational semantics and related theories of Petri nets help establish the correctness of our proposed method. We have also performed a case study and several simulations to evaluate our proposed approach. Results show that it can help reveal the structural and behavioral characteristics of cloud computing, and manage the resources in cloud application more efficiently.