Abstract
The Cloud computing is a rapidly emerging distributed system paradigm that offers a huge amount of IT resources as utility services at a reduced cost and flexible schemes. The key of such flexibility is an efficient load balancer that offers better management and utilization of virtualized underlying cloud infrastructures. However, most of the existing load balancers in cloud computing are based on either centralized or fully distributed architectures while the idea of harnessing multiple load balancers in a hierarchical structure to improve the sever load and job response time is still under studied. Therefore, this paper, aims at bridging this gap by providing a comparative study between the three load balancing architectures in cloud computing: centralized, decentralized and hierarchical load balancers. The experimental results suggest that the hierarchical architecture for load balancers best suits the public cloud environment and call for further research to test whether these results can be generalized for other types of clouds.