Trend-based load balancer for a distributed Web system

The unexpected and continuous changes of the workload reaching any Internet-based service make really difficult to guarantee a balanced utilization of the server resources. In this paper, we propose a novel class of state-aware dispatching algorithms that take into account not only the present resource load but also the behavioral trend of the server load, that is, whether it is increasing, decreasing or oscillating. We apply one algorithm of this class to a multi-tier Web-based system and demonstrate that it is able to improve load balancing of the most critical server resources.