首页> 外文会议>2018 3rd International Conference on Computer and Communication Systems >Secured and High Performance Distributed Big Data Storage in Cloud Systems
【24h】

Secured and High Performance Distributed Big Data Storage in Cloud Systems

机译:云系统中安全的高性能分布式大数据存储

获取原文
获取原文并翻译 | 示例

摘要

Big Data Security and privacy are key concerns for cloud computing. At the initial stage, security was not considered for processing Big Data because of insufficient research and adequate security technology. Now researchers have to think new ways for cloud storage and Big Data security to overcome exiting security challenges of Big Data storage. For rapid Big Data processing, encryption is often considered as a big obstacle as clear data processing is much faster than encrypted data. But for cloud system, encrypted data processing is not a big deal because of massive processing power of cloud systems. So encryption will not be an obstacle and degrade the performance to process encrypted Big Data at cloud. There is a big challenge now to store and provide security in small chunk in cloud system and also key management. This paper provides novel approach for Big Data security over cloud namely Secured and High Performance Distributed Big Data Storage (SH-DBDS) model. Data will be split and uploaded for distributed cloud storage system. Single split data will be worthless until and unless joined with the other parts of the data. In this paper, an algorithm has been provided to split and join the data. Experimentation is performed with different data sets (10MB-1GB) at local system and AWS cloud and performance is measured. Evaluation is done considering the security and performance of Big Data.
机译:大数据安全性和隐私是云计算的关键问题。在最初阶段,由于研究不足和适当的安全技术,因此未考虑将安全性用于处理大数据。现在,研究人员必须思考云存储和大数据安全性的新方法,以克服大数据存储面临的安全挑战。对于快速的大数据处理,加密通常被视为一大障碍,因为清晰的数据处理比加密的数据要快得多。但是对于云系统而言,由于云系统具有强大的处理能力,因此加密数据处理并不重要。因此,加密不会成为障碍,并且不会降低在云上处理加密大数据的性能。现在,在云系统中的小块中以及密钥管理中存储和提供安全性是一个巨大的挑战。本文提供了一种基于云的大数据安全性的新颖方法,即安全和高性能分布式大数据存储(SH-DBDS)模型。数据将被拆分并上传到分布式云存储系统。直到并且除非与数据的其他部分合并,否则单个拆分数据将一文不值。在本文中,提供了一种算法来拆分和合并数据。在本地系统和AWS云上对不同的数据集(10MB-1GB)进行了实验,并评估了性能。考虑大数据的安全性和性能进行评估。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号