中文摘要：

Many distributed clouds which try to integrate the advantages of centralized clouds and distributed systems have been studied in recent years.Traditional cloud simulators focus on large scale data centers with virtualized servers,and cannot meet the needs of distributed cloud simulations.This paper introduces a generalized and extensible simulation framework,named MCloudSim,which is used for modeling and simulating distributed clouds.MCloudSim has the following characteristics;(1)the overlay protocol in MCloudSim can be freely replaced without affecting the function of other modules;(2) a Petri net workflow theory based task model is proposed to simulate distributed tasks;(3) a distributed cloud can be easily built by assembling and expanding the basic resource entities provided by MCloudSim.Finally,simulation results of scenarios with a 3-tier central-controlled distributed cloud and a P2 P based cloud prove that MCloudSim has high efficiency and satisfies performance in supporting large scale experiments and different distributed clouds.

英文摘要：

Many distributed clouds which try to integrate the advantages of centralized clouds and distributed systems have been studied in recent years. Traditional cloud simulators focus on large scale data centers with virtualized servers, and cannot meet the needs of distributed cloud simulations. This paper introduces a generalized and extensible simulation framework, named MCloudSim, which is used for modeling and simulating distributed clouds. MCloudSim has the following characteristics： （ 1 ） the overlay protocol in MCloudSim can be freely replaced without affecting the function of other modules; （2） a Petri net workflow theory based task model is proposed to simulate distributed tasks; （3） a distributed cloud can be easily built by assembling and expanding the basic resource entities provided by MCloudSim. Finally, simulation results of scenarios with a 3-tier central-controlled distributed cloud and a P2P based cloud prove that MCloudSim has high efficiency and satisfies performance in supporting large scale experiments and different distributed clouds.