Research on Network Security Protection of Application-Oriented Supercomputing Center Based on Multi-Level Defense and Moderate Principle

Author:

Yang Boxiong,Yu Ying,Wang Zeyu,Li Shelei,Xiao Heng,Gao Hualing,Liang Zhiyong,Zhou Xue

Abstract

Abstract High Performance Computing (HPC), also known as Supercomputing, is widely applied in various fields, which have the advantage of high processing capability and mass storage. Various open business services bring great threat to the network and data security of HPC cluster. This paper proposes a feasible scheme to realize supercomputing information security through multi-layer defense and overheads control according to the experience of operation, management and maintenance of Supercomputer Center for many years. First, this paper puts forward the principle of moderate risk, and gives the principles of design and the implementation for the security protection of Supercomputing Center. Second, this paper presents a security system architecture in coordination with deep collaborative defense. Finally, this paper designs a 4-layer protection scheme on account of the latest network security solutions and the operation and maintenance characteristic of our own supercomputer. Experiments on multi-level defense and overheads control show that the designed scheme takes into account the cost and network security, and obtain prospective results., which is especially suitable for the network security protection of small-scale or medium-scale high-performance computing cluster for engineering application.

Publisher

IOP Publishing

Subject

General Physics and Astronomy

Reference31 articles.

1. Autonomous security mechanisms for high-performance computing systems: review and analysis;Hou;Adaptive Autonomous Secure Cyber Systems,2020

2. A security analysis method for supercomputing users’ behavior;Zhu;CSCloud,2017

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3