Research Onenery Efficient Data Placementalgorithmand Node-Scheduling Policies In Cloud Computing Systems

In recent years, with the continuous development of information technology,the explosive growthof data is very high.Massive data change the current operatingmode of the computer, a large number of data-intensive applications have sprung up.At the same time people on the demand for information processing capacity is alsoincreasing, the developmemt of computing resources and computing power israpidly, but people are also facing an increasingly serious potential threat, globalenergy consumption used to compute is growing,which means that more and moreenergy is consumed in the computational demands.With the rise of cloud computing,it is important to save energy consumed by cloud systems. How to place data andhow to schedule the nodes in the cloud platform has become a very important issuefrom the view of the energy-saving. However, existing node-scheduling policiescan’t save significant amount of energy for the cloud computing platforms. Thispaper proposes a heuristic data placement method and two node schedulingalgorithms for cloud platforms for saving energy with guaranteed servicelevel.Cloudsim is adopted to simulate a private cloud system, where data block isdynamically placed in the resource pool by data sharing mechanism.Energy-savingeffect is achieved by turning on minimum nodes to cover maximum data blocks.Especially, the problem of covering data block with computing nodes is abstractedas a set cover problem, and we use a greedy algorithm to solve this problem.Thisapproach is practical to any cloud computing infrastructure. Finally, the dataplacement method and node scheduling algorithms proposedin this paper areverified by experiments.