Desktop Grid Environment for Evolution Strategies using Grid Task Scheduling Algorithm RR

Abstract

This paper empirically investigates the effect of Desktop Grid Environment on the computational cost of Evolution Strategies (ES). Especially, for task scheduling, List Scheduling with Round-robin order Replication (RR) is adopted to reduce waiting time due to synchronization in ES. Computer simulations are conducted which compare with the loss energy of theoretical maximum value and an actual maximum measurement on Desktop Grid Environment for ES. Results on RR prove that the loss energy of an actual maximum measurement is less than that of theoretical maximum value. Moreover, RR can reduce the synchronous waiting time and improve parallel efficiency in comparison with Work Queue algorithm.