A Performance Comparison of Load Balancing Algorithms for Cloud Computing

Cloud service providers such as Amazon Web Services (AWS), Microsoft Azure, and Google Cloud Platform (GCP) have seen exponential growth over the past few years as more companies are shifting their operations to the Cloud. As Cloud serves multiple clients and users simultaneously, it is important but challenging to estimate the performance of load balancing mechanisms for the tasks running on the Cloud. This research has investigated First Come First Served (FCFS), Shortest Job First (SJF) and Least Connection (LC) load balancing algorithms using CloudSim framework and realistic models for Cloud platform e.g. AWS, task etc. The simulation results show that the task execution time for space-shared scheduling policy is closer to the theoretical time than that of time-shared scheduling. Furthermore, it has been observed that LC performs better than SJF and FCFS at lower load.