云计算系统中能量有效的数据摆放算法和节点调度策略

Energy Efficient Data Placement Algorithm and Node-Scheduling Policies in Cloud Computing Systems

云计算环境中数据中心能耗问题已经引起广泛关注,从绿色节能的角度考虑如何摆放云平台中的数据、如何调度云平台中的节点,成为非常重要的问题.现有的节点调度策略并不能在云计算平台环境中获得理想的节能效果.提出了一种启发式的动态数据摆放算法以及两种适用于云计算环境的节点调度优化策略.在保证任务请求满足预期执行效果的前提下,通过数据摆放算法和节点调度优化策略减少云平台消耗的能量.使用Cloudsim模拟了私有云环境,通过数据共享机制在资源池中进行数据块的动态摆放,开启最少的节点来覆盖最多的数据块,由此达到节能目的.将节点覆盖数据块的问题抽象为带权重的集合覆盖问题,使用贪心算法进行求解.通过实验测试了数据摆放方法和节点调度方法的节能效果,实验结果验证了数据摆放方法和节点调度方法的有效性.

With the rise of cloud computing,it is important to save energy consumed by cloud systems.How to place data and how to schedule the nodes in the cloud platform has become a very important issue from the view of the energy-saving.However,existing node-scheduling policies can't save significant amount of energy for the cloud computing platforms.This paper proposes a heuristic data placement method and two node scheduling algorithms for cloud platforms to save energy with guaranteed service level.Cloudsim is adopted to simulate a private cloud system,where data block is dynamically placed in the resource pool by data sharing mechanism.Energy-saving effect is achieved by turning on minimum nodes to cover maximum data blocks.Especially,the problem of covering data block with computing nodes is abstracted as a set cover problem,and we use a greedy algorithm to solve this problem.This approach is practical to any cloud computing infrastructure.Finally,the data placement method and node scheduling algorithms proposed in this paper are verified by experiments.