摘要
任务调度时的服务器能耗是云计算系统动态能耗的重要组成部分。目前云计算带来的巨大能耗已经成为制约云计算发展的技术瓶颈,因此节约能源和提高能源利用率是实现绿色云计算系统的重要基础。为实现减少能耗和缩短任务执行时间的绿色云计算目标,将遗传算法和蚁群算法相结合,提出了一种动态融合的任务调度算法。该算法利用遗传算法全局搜索查找能力强的优点寻找任务调度的较优解,并将该较优解转化为蚁群的初始信息素值,再通过蚁群算法的蚁群信息交流和正反馈机制寻找任务调度问题的最优解,以有效降低云计算数据中心和计算中心的能耗。仿真实验结果表明,所提出的任务调度算法显著降低了云计算系统计算的运行时间和总能耗。
The energy generated by the server during the scheduling system is an important part of the dynamic energy consumption of the cloud computing system and the huge energy consumption of the cloud computing has become the technical bottleneck which restricts the development of cloud computing. Therefore, saving energy and improving energy efficiency is an important foundation to achieve green cloud computing system. To achieve the goal of reducing energy consumption and shortening the task execution time of the green cloud computing, an energy-efficient scheduling algorithm based on genetic algorithm and ant colony algorithm has been proposed, which takes advantage of the strong global search ability of genetic algorithm to find the optimal solution of the scheduling problem, then converts it to the initial pheromone of ant colony optimization algorithm. After information communication and positive feedback, the global optimal solution of the task scheduling problem has been found out to effectively reduce the energy consumption in cloud computing center and calculating center. Simulation results show that the proposed algorithm has significantly reduced the task execution time and the total ener- gy consumption.
出处
《计算机技术与发展》
2017年第8期92-96,共5页
Computer Technology and Development
基金
江苏省自然科学基金项目(BK20130882)
关键词
绿色云计算
节能
任务调度
GCA
green cloud computing
energy saving
task scheduling
GCA