A Redundant Power Consumption Laxity-Based (RPCLB) Algorithm for Computation Type Applications

In energy-aware information systems, it is critical to discuss how to select a server for each request from clients in order to not only achieve performance objectives but also reduce the total power consumption of a system. In addition, application requests have to be reliably performed in presence of server faults. In our previous studies, the improved power consumption laxity based (IPCLB) algorithm to select a server is proposed so that the total power consumption in a cluster of servers can be reduced. Here, if a server stops while a request from a client is performed, the client cannot receive a reply of the request and might be suspended. In this paper, we consider the redundant execution of an application process on multiple servers in order to increase the reliability and availability. We propose the redundant power consumption laxity-based (RPCLB) algorithm to select multiple servers for redundantly performing an application process so that not only the total power consumption in a cluster of servers can be reduced but also processes can be reliably performed in presence of server faults. We evaluate the RPCLB algorithm in terms of the total power consumption of servers and the execution time of processes compared with the basic round-robin (RR) algorithm.