基于Hopfield神经网络的云存储负载均衡策略

doi:10.11772/j.issn.1001-9081.2017.08.2214

计算机应用 ›› 2017, Vol. 37 ›› Issue (8): 2214-2217.DOI: 10.11772/j.issn.1001-9081.2017.08.2214

基于Hopfield神经网络的云存储负载均衡策略

李强^1,2, 刘晓峰³

1. 太原理工大学财经学院, 太原 030024;
2. 山西省财政税务专科学校信息学院, 太原 030024;
3. 太原理工大学大数据学院, 太原 030024

收稿日期:2017-01-18 修回日期:2017-03-10 发布日期:2017-08-12 出版日期:2017-08-10
通讯作者: 刘晓峰
作者简介:李强(1980-),男,山西太原人,副教授,高级工程师,硕士,CCF会员,主要研究方向:Hopfield神经网络;刘晓峰(1979-),男,山西怀仁人,讲师,博士,主要研究方向:Hopfield神经网络。
基金资助:
国家自然科学基金资助项目（61502330）；山西省高等学校科技创新项目（20161131）；山西省软科学计划研究项目（2016041008-5）。

Load balancing strategy of cloud storage based on Hopfield neural network

LI Qiang^1,2, LIU Xiaofeng³

1. College of Finance and Economics, Taiyuan University of Technology, Taiyuan Shanxi 030024, China;
2. College of Information, Shanxi Finance and Taxation College, Taiyuan Shanxi 030024, China;
3. College of Data Science, Taiyuan University of Technology, Taiyuan Shanxi 030024, China

Received:2017-01-18 Revised:2017-03-10 Online:2017-08-12 Published:2017-08-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61502330),the Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi (20161131),the Project of Soft Science Plan of Shanxi Province (2016041008-5).

摘要/Abstract

摘要： 针对当前Hadoop存储效率不高，且副本故障后恢复成本较高的问题，提出一种基于Hopfield神经网络（HNN）的存储策略。为了实现系统整体性能的提升，首先分析影响存储效率的资源特征；然后建立资源约束模型，设计Hopfield能量函数，并化简该能量函数；最后，通过标准用例Wordcount测试，分析8个节点的平均利用率，并与三个常用算法包括基于资源的动态调用算法、基于能耗的算法和Hadoop默认存储策略进行性能和资源利用方面的比较。实验表明，与对比算法相比，基于HNN的存储策略在效率上分别平均提升15.63%、32.92%和55.92%。因此，该方法在应用中可以更好地实现资源负载平衡，将有助于改善Hadoop的存储能力，并可以加快检索。

关键词: 云存储, Hadoop, Hadoop分布式文件系统, 副本策略, 负载均衡

Abstract: Focusing on the shortcoming of low storage efficiency and high recovery cost after copy failure of the current Hadoop, Hopfield Neural Network (HNN) was used to improve the overall performance. Firstly, the resource characteristics that affect the storage efficiency were analyzed. Secondly, the resource constraint model was established, the Hopfield energy function was designed and simplified. Finally, the average utilization rate of 8 nodes was analyzed by using the standard test case Wordcount, and the performance and resource utilization of the proposed strategy were compared with three typical algorithms including dynamic resource allocation algorithm, energy-efficient algorithm and Hadoop default storage strategy, and the comparison results showed that the average efficiency of the storage strategy based on HNN was promoted by 15.63%, 32.92% and 55.92% respectively. The results indicate that the proposed algorithm can realize the resource load balancing, help to improve the storage capacity of Hadoop, and speed up the retrieval.

Key words: cloud storage, Hadoop, Hadoop Distributed File System (HDFS), replica strategy, load balancing

中图分类号:

TP393.027

李强, 刘晓峰. 基于Hopfield神经网络的云存储负载均衡策略[J]. 计算机应用, 2017, 37(8): 2214-2217.

LI Qiang, LIU Xiaofeng. Load balancing strategy of cloud storage based on Hopfield neural network[J]. Journal of Computer Applications, 2017, 37(8): 2214-2217.

参考文献

[1] BORTHAKUR D. Hadoop[EB/OL].[2011-06-15]. http://lucene.apache.org/hadoop.
[2] BONVIN N, PAPAIOANNOU T G, ABERER K. A self-organized, fault-tolerant and scalable replication scheme for cloud storage[C]//SoCC' 10:Proceedings of the 1st ACM Symposium on Cloud Computing. New York:ACM, 2010:205-216.
[3] WEI Q, VEERAVALLI B, GONG B, et al. CDRM:a cost-effective dynamic replication management scheme for cloud storage cluster[C]//CLUSTER' 10:Proceedings of the 2010 IEEE International Conference on Cluster Computing. Washington, DC:IEEE Computer Society, 2010:188-196.
[4] RUAN X, XIE J, DING Z, et al. Improving MapReduce performance through data placement in heterogeneous Hadoop clusters[C]//Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, Workshops and Phd Forum. Washington, DC:IEEE Computer Society, 2010:1-9.
[5] WANG Z, LI T, XIONG N, et al. A novel dynamic network data replication scheme based on historical access record and proactive deletion[J]. The Journal of Supercomputing, 2012, 62(1):227-250.
[6] 周敬利,周正达.改进的云存储系统数据分布策略[J].计算机应用,2012,32(2):309-312. (ZHOU J L, ZHOU Z D. Improved data distribution strategy for cloud storage system[J]. Journal of Computer Applications, 2012, 32(2):309-312.)
[7] 林伟伟.一种改进的Hadoop数据放置策略[J].华南理工大学学报(自然科学版),2012,40(1):152-153. (LIN W W. An improved data placement strategy for Hadoop[J]. Journal of South China University of Technology (Natural Science Edition), 2012, 40(1):153-158.)
[8] 张兴.基于Hadoop的云存储平台的研究与实现[D].成都:电子科技大学,2013:22-38. (ZHANG X. Research and Implementation of cloud storage plateform based on Hadoop[D]. Chengdu:University of Electronic Science and Technology of China, 2013:22-38.)
[9] 付雄,贡晓杰,王汝传.云存储系统中基于分簇的数据复制策略[J].计算机工程与科学,2014,36(12):2296-2304. (FU X G, GONG X J, WANG R C. A cluster based data replication strategy in cloud storage systems[J]. Computer Engineering & Science, 2014, 36(12):2296-2304.)
[10] 李强,刘晓峰,贺静.基于语音特征的情感分类[J].小型微型计算机系统,2016,37(2):385-388. (LI Q, LIU X F, HE J. Sentiment classification based on voice features[J]. Journal of Chinese Computer Systems, 2016, 37(2):385-388.)
[11] 王万良,吴启迪,徐新黎.基于Hopfield神经网络的作业车间生产调度方法[J].自动化学报,2002,28(5):838-844. (WANG W L, WU Q D, XU X L. Hopfield neural network approach for job-shop scheduling problems[J]. Acta Automatica Sinica, 2002, 28(5):838-844.)
[12] 王秀利,吴惕华.一种求解多处理器作业调度的Hopfield神经网络方法[J].系统工程与电子技术,2002,24(8):13-16. (WANG X L, WU T H. Scheduling multiprocessor job using Hopfield neural network[J]. Systems Engineering and Electronics, 2002, 24(8):13-16.)
[13] HOPFIELD J J, TANK D W. Neural computation of decision in optimization problems[J]. Biological Cybernetics, 1985, 52(3):141-152.

[1]	张明, 付乐, 王海峰. 面向边缘计算的并发数据流接转控制模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3876-3883.
[2]	孙亚男, 吴杰宏, 石峻岭, 高利军. 改进自组织映射的多无人机协同任务分配方法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1551-1556.
[3]	谢振杰, 付伟. 基于可审计多副本的云存储差错副本恢复机制[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1102-1108.
[4]	龙运波, 唐聃. 分布式存储中基于局部修复码的负载均衡方法[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 767-775.
[5]	杨力, 陈建廷, 向阳. 基于HBase的工业时序大数据分布式存储性能优化策略[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 759-766.
[6]	高旗, 吕娜, 缪竞成. 基于负载均衡的无线虚拟网络映射算法[J]. 《计算机应用》唯一官方网站, 2022, 42(10): 3148-3153.
[7]	许红亮, 杨桂芹, 蒋占军. 基于软件定义网络的数据中心自适应多路径负载均衡算法[J]. 计算机应用, 2021, 41(4): 1160-1164.
[8]	杨翎, 姜春茂. 基于三支决策的虚拟机节能迁移策略[J]. 计算机应用, 2021, 41(4): 990-998.
[9]	李秀艳, 刘明曦, 史闻博, 董国芳. 面向资源受限用户的高效动态数据审计方案[J]. 计算机应用, 2021, 41(2): 422-432.
[10]	唐鑫, 周琳娜. 基于响应模糊化的抗附加块攻击云数据安全去重方法[J]. 计算机应用, 2020, 40(4): 1085-1090.
[11]	李翠, 陈庆奎. 基于DPDK并行通信的动态监控模型[J]. 《计算机应用》唯一官方网站, 2020, 40(2): 335-341.
[12]	付伟, 顾晨阳, 高强. 基于属性加密的多用户共享ORAM方案[J]. 《计算机应用》唯一官方网站, 2020, 40(2): 497-502.
[13]	董聪, 张晓, 程文迪, 石佳. 基于新型存储器件的分布式文件系统性能优化[J]. 计算机应用, 2020, 40(12): 3594-3603.
[14]	王海勇, 彭垚, 郭凯璇. 云存储中基于代理重加密的CP-ABE访问控制方案[J]. 计算机应用, 2019, 39(9): 2611-2616.
[15]	柳玉东, 王绪安, 涂广升, 王涵. 全生命周期的云外包数据安全审计协议[J]. 计算机应用, 2019, 39(7): 1954-1958.

基于Hopfield神经网络的云存储负载均衡策略

Load balancing strategy of cloud storage based on Hopfield neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics