The delay time-based server selection algorithm for energy-efficient redundant execution of processes

It is critical to discuss how to realise not only fault-tolerant but also energy-efficient server cluster systems. In this paper, we propose the redundant delay time based (RDTB) algorithm to select multiple servers for redundantly and energy-efficiently performing application processes. In the RDTB algorithm, it is not necessary to collect a state of every replica to estimate the energy consumption of servers. We evaluate the RDTB algorithm compared with the basic round-robin (RR) and redundant power consumption laxity-based (RPCLB) algorithms. From the evaluation, the total energy consumption of homogeneous and heterogeneous clusters in the RDTB algorithm can be maximally reduced to 36% and 19% of the RR algorithm, respectively. The number of messages exchanged between a load balancer and servers in the RDTB algorithm can be maximally reduced to 90% of the RPCLB algorithm. Therefore, the RDTB algorithm is more useful than the RR and RPCLB algorithms for real environment.