Stochastic Modeling and Performance Analysis of Energy-Aware Cloud Data Center Based on Dynamic Scalable Stochastic Petri Net

Abstract

The characteristics of cloud computing, such as large-scale, dynamics, heterogeneity and diversity, present a range of challenges for the study on modeling and performance evaluation on cloud data centers. Performance evaluation not only finds out an appropriate trade-off between cost-benefit and quality of service (QoS) based on service level agreement (SLA), but also investigates the influence of virtualization technology. In this paper, we propose an Energy-Aware Optimization (EAO) algorithm with considering energy consumption, resource diversity and virtual machine migration. In addition, we construct a stochastic model for Energy-Aware Migration-Enabled Cloud (EAMEC) data centers by introducing Dynamic Scalable Stochastic Petri Net (DSSPN). Several performance parameters are defined to evaluate task backlogs, throughput, reject rate, utilization, and energy consumption under different runtime and machines. Finally, we use a tool called SPNP to simulate analytical solutions of these parameters. The analysis results show that DSSPN is applicable to model and evaluate complex cloud systems, and can help to optimize the performance of EAMEC data centers.