Modelling of Cloud Computing by Using the Queuing System with Impatient Requests

Cloud computing is an innovative technology which enables remote users to indicate resources through the Internet services. The concept of big data evolves, and service popularity grows dramatically, so it has become critical to allocate resources better and to maintain high efficiency. One of the new approaches to this technology is a division of the requests into subtasks with parallel execution of servers. In this paper such models are considered, but also the systems with impatient clients are modeled. To estimate quality of model’s performance we have calculated blocking probability, probability of immediate service and mean response time by using a queuing theory. The estimations have been obtained by numerical and simulation experiments and as a result, a comparative analysis of the calculations have been demonstrated.