Accelerated computation of the genetic algorithm for energy-efficient virtual machine placement in data centers

Abstract Energy efficiency is a critical issue in the management and operation of cloud data centers, which form backbone computing. Virtual machine (VM) placement has significant impact on energy-efficiency improvement for virtualized centers. Among various methods to solve VM-placement problem, genetic algorithm (GA) been well accepted quality its solution. However, GA also computationally demanding, particularly computation fitness function. This limits application large-scale systems or specific scenarios where fast solution good required. Our analysis this paper reveals that execution time standard mostly consumed Therefore, designs structure extended from previous study reduce complexity quadratic linear one with respect input size problem. Incorporating structure, an alternative function proposed number instructions significantly, further improving execution-time performance GA. Experimental studies show our approach achieves 11 times acceleration energy-efficient VM centers about 1500 physical machines size.