Replica Placement Energy-efficient Strategy Based On Storage Of Cloud Computing

People’s daily increasing demands of high performance computing and huge storage space was satisfied by cloud computing environment, which is good-scalability, high –reliability and high-availability. The data redundancy caused by the design principle of the distributed file system, this not only caused low utilization problems, but further exacerbate the cloud computing problem of high energy consumption.The dissertation studies the architecture of the distributed file system, and the two different data management skills of static data placement and dynamic data placement were analyzed and compared. A replica placement dynamic management energy-efficient strategy and a block clustering placement energy-efficient strategy based on the characteristics of the user visiting was put forward. For the replica placement dynamic management energy-efficient strategy, transforming the study of the characteristics of the user visiting into the calculation block visit temperature, DataNode actively apply for sleeping so as to achieve the goal of energy saving according to the overall access temperature of nodes. The unnecessary data node could be sleep in order to reduce the energy consumption. For the block clustering placement energy-efficient strategy, the vector of the visiting feature on data block was built to depict the behavior of the random block accessing. K-means algorithm was adopted to do the clustering calculation within the two different scopes. The data blocks were migrated according to the clustering calculation results when the system load is low. The strategy could be suitable for the different circumstance that has the requests for the energy consumption and utilization, according to set the distance parameters between clustering. The experiment shows that after adopting this strategy, the server response time is well. The mathematical analyses prove that the efficiency of energy saving of two strategies is better than other energy saving strategies; energy consumption reduced by 31-37%.