Hybrid differential evolution algorithm combined with heuristic correction and chaotic search for online energy-efficient optimization of server cluster
Issue title: Applications of intelligent & fuzzy theory in engineering technologies and applied science
Abstract: Server cluster has been widely used to improve the performance of various servers. How to optimize the deployment of each server in a cluster so as to minimize cluster’s power consumption while satisfying load capacity requirement is an urgent problem to be resolved. In this paper, we first formulate a typical energy-efficient optimization problem of server cluster as a constrained MIP (Mixed Integer Programming) problem. Then, aimed at the traits of the problem, we propose a hybrid DE (Differential Evolution) algorithm combined with heuristic correction and chaotic search to solve the problem. We introduce a correction operation to traditional DE algorithm, which bases on greedy idea to correct the individuals that do not satisfy constraints. Besides, we generate the initial population based on chaotic sequence so as to enhance population diversity, and implement chaotic search around the best individual of each generation so as to improve solving accuracy and accelerate convergence speed. The algorithm has high solving efficiency and can run online even when applied in large-scale server clusters. Simulation results verify the feasibility and effectiveness of the algorithm.
