Depending upon the type of service and its scope, throughput is calculated. You can do it on the basis of response time (e.g, for VM migration, service provisioning, resource allocation, etc.).

Hi, I heard we can use NS2 for cloud environment.. In Cloudsim also u can calculate but better you use NS2

CloudSim supports VM provisioning at two levels: first, at the host level and second, at the VM level. At the host level, it is possible to specify how much of the overall processing power of each core will be assigned to each VM. At the VM level, the VM assigns a fixed amount of the available processing power to the individual application services (task units) that are hosted within its execution engine.

And at each level, CloudSim implements the time-shared and space-shared provisioning policies.

So, you have to decide which provision you want to use to calculate your throughput.

Plus there is an inbuilt functionalites in Cloudsim to check the throughput based on the above parameters.

I approve the last answer of Johnson Thoudam. To well understand time-shared and space-policies, i recommend to you to read this paper "Bi-objective decision support system for task-scheduling based on genetic algorithm in cloud computing"

https://www.researchgate.net/publication/318577679_Bi-objective_decision_support_system_for_task-scheduling_based_on_genetic_algorithm_in_cloud_computing?_iepl%5BviewId%5D=1qp1vHiWsCvQwqLXyolEKQBK&_iepl%5BprofilePublicationItemVariant%5D=default&_iepl%5Bcontexts%5D%5B0%5D=prfpi&_iepl%5BtargetEntityId%5D=PB%3A318577679&_iepl%5BinteractionType%5D=publicationTitle