北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2017, Vol. 40 ›› Issue (s1): 53-57.doi: 10.13190/j.jbupt.2017.s.012

• 论文 • 上一篇    下一篇

大规模云资源可靠性评价模型

朱晓宁1, 孙斌1, 朱春鸽2   

  1. 1. 北京邮电大学 信息安全中心, 北京 100876;
    2. 国家计算机网络应急技术处理协调中心, 北京 100029
  • 收稿日期:2016-05-12 出版日期:2017-09-28 发布日期:2017-09-28
  • 作者简介:朱晓宁(1983-),男,博士生,E-mail:xiaoning158@bupt.edu.cn;孙斌(1967-),女,副教授.
  • 基金资助:
    国家242信息安全计划项目(2015A136);国家自然科学基金项目(61502048)

Reliability Evaluation Model of Large Scale Cloud Resources

ZHU Xiao-ning1, SUN Bin1, ZHU Chun-ge2   

  1. 1. Information Security Center, Beijing University of Posts and Telecommunications, Beijing 100876, China;
    2. National Computer Network Emergency Response Technical Team/Coordination Center, Beijing 100029, China
  • Received:2016-05-12 Online:2017-09-28 Published:2017-09-28

摘要: 针对互联网计算资源数量大、类型多、随机性强、稳定性相对较差等特点,提出一种基于朴素贝叶斯分类的iVCE云平台资源可靠性评价算法. 通过对计算资源的特征提取,离散化处理后,使用概率估计方法对资源的状态做出实时的评价. 在iVCE平台的实际运行效果表明,平台资源可靠性评价通过引入朴素贝叶斯算法,在评价的准确性方面提升了20%以上,通过参数优化算法的准确率同样好于同类其他同类算法2%以上,满足了实际生产的需求.

关键词: iVCE, 云计算, 资源评价

Abstract: The computing resources of the Internet has a large number, type, strong randomness, more stability are relatively poor, a kind of based on naive bayesian classification virtual computing environment(iVCE)[1-2] cloud platform reliability evaluation algorithm is put forward. After the feature extraction of computing resources, the method of probability estimation is used to estimate the state of the resources in real time. Had indicated in the actual operation of the iVCE platform, platform resource reliability evaluation by using naive Bayesian algorithm, in evaluation of the accuracy of a 20% increase over and through the parameter optimization algorithm accuracy was also better than similar to several other algorithms above 2%. Meet the needs of the actual production.

Key words: virtual computing environment, cloud computing, resource evaluation

中图分类号: