Papers by Keyword: Data Placement

Abstract: Although hard disk drives have been popular over several decades, there still exists the deficiency because of their slow speeds and high power consumptions. By contrast, flash-based solid state disks exhibit good performance and low power consumption. However, the limited lifetimes become a fatal flaw of solid state disks. In order to take full advantage of hard disk drives and solid state disks, we design a hybrid storage system to make them work in a complementary manner. Further, we propose a data placement scheme for this system to determine the data placement on the underlying solid state disks or hard disk drives based on the data access statistics. Experiment results show that the lifetime of solid state disks and the response time of the system can be significantly improved compared with the alone storage media.

Abstract: Cloud computing is a typical network computing model.Large-scale network applications based on cloud computing presents the characteristics and trends of distributed, heterogeneous data-intensive.Smart grid is a complex system running a real-time online.It is a data-intensive applications.How to effectively integrate multiple data centers in the smart grid and let them work together in the cloud computing environment is a question.And how to make rational distribution of data in the smart grid is also a question.Therefore, we propose a global placement strategy based on genetic algorithm.And we give the data placement scheme for solving on data-intensive applications.Through simulation software CloudSim, we conducted simulation experiments and analyzed the effectiveness of the program.

Abstract: The massive data in Data centers network will be frequently accessed massive datasets for cloud services, which will lead to some new requirements and becomes an important issue for interconnection topology and data management in cloud computing. According to the cost-effective, the paper proposes a new interconnection network MyHeawood for cloud computing. MyHeawood is constructed by small switches and servers with dual-port NIC according to recursive method. The data placement strategy in MyHeawood is a hashing algorithm based on the family of hash functions. MyHeawood uses three replicas strategy base on master copy, which is allocated in different sub layer to improve the reliability of data.

Abstract: The application of high-speed railway data, which is an important component of China's transportation science data sharing, has embodied the typical characteristics of data-intensive computing. A reasonable and effective data placement strategy is needed to deploy and execute data-intensive applications in the cloud computing environment. Study results of current data placement approaches have been analyzed and compared in this paper. Combining the semi-definite programming algorithm with the dynamic interval mapping algorithm, a hierarchical structure data placement strategy is proposed. The semi-definite programming algorithm is suitable for the placement of files with various replications, ensuring that different replications of a file are placed on different storage devices. And the dynamic interval mapping algorithm could guarantee better self-adaptability of the data storage system. It has been proved both by theoretical analysis and experiment demonstration that a hierarchical data placement strategy could guarantee the self-adaptability, data reliability and high-speed data access for large-scale networks.

Abstract: Data-Intensive applications in power systems often perform complex computations which always involve large amount of datasets. In a distributed environment, an application may needs several datasets located in different data centers which faces two challenges including the high cost of data movements between data centers and data dependencies within the same data centers. In this paper, a data placement strategy among and within data centers in a cloud environment is proposed. Datasets are placed in different centers by a clustering scheme based on the data dependencies. And within the center, data is partitioned and replicated using consistent hashing. Simulations show that the algorithm can effectively reduce the cost of data movements and perform a evenly data distribution.