Improving of EPCLB Algorithm for Reducing the Overhead of a Load Balancer

In information systems, it is critical to reduce the total electrical power consumption of computers and networks in order to realize digital ecosystems. In the extended power consumption laxity-based (EPCLB) algorithm, a server is selected in a set of possible servers so as to not only satisfy deadline constraint but also reduce the total power consumption of servers in general types of applications. However, each time a load balancer receives a new request, the load balancer has to collect the state on computation and transmission laxities of processes and traffic in each server and estimate the power consumption to perform the request. Since the state of each server might be changed during estimation, it is difficult to correctly estimate the power consumption. In this paper, we improve the EPCLB algorithm so that the total power consumption of servers and the communication overhead of a load balancer can be reduced. We evaluate the improved EPCLB (IEPCLB) algorithm in terms of the power consumption of servers and the communication overhead of a load balancer compared with the EPCLB and round-robin (RR) algorithms.