An energy-aware load balancing algorithm to perform computation type application processes in a cluster of servers
Tomoya Enokido, Dilawaer Doulikun, Makoto Takizawa · International Journal of Web and Grid Services · 2017
A cluster of servers is getting scalable and widely used in various types of applications. It is critical to reduce the electric energy consumed by servers in a cluster to realise eco society. In this paper, we newly propose an improved delay time based (IDTB) algorithm to reduce the total electric energy consumption of a cluster and to more efficiently utilise the computation resources for performing application processes in a cluster. In the IDTB algorithm, a load balancer estimates the state of each server just by using responses from processes and without additionally communicating with servers to collect states of the servers. We evaluate the IDTB algorithm compared with the basic round-robin (RR), improved power consumption laxity based (IPCLB), and delay time based (DTB) algorithms. We show the total electric energy consumption of a cluster and response time of each process can be reduced in the IDTB algorithm.