基于贝叶斯模型的云服务服务质量预测

doi:10.11772/j.issn.1001-9081.2016.04.0914

计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 914-917.DOI: 10.11772/j.issn.1001-9081.2016.04.0914

基于贝叶斯模型的云服务服务质量预测

陈伟, 陈继明

江苏大学计算机科学与通信工程学院, 江苏镇江 212013

收稿日期:2015-09-21 修回日期:2015-12-07 出版日期:2016-04-10 发布日期:2016-04-08
通讯作者: 陈伟
作者简介:陈伟(1990-),男,江苏盐城人,硕士研究生,主要研究方向:云计算服务质量、服务质量预测; 陈继明(1977-),男,江苏镇江人,副教授,博士,主要研究方向:分布式系统、数据库。

Cloud service QoS prediction method based on Bayesian model

CHEN Wei, CHEN Jiming

School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang Jiangsu 212013, China

Received:2015-09-21 Revised:2015-12-07 Online:2016-04-10 Published:2016-04-08

摘要/Abstract

摘要： 针对如何分配一个未来一段时间内满足QoS要求的云服务和感知可能将要发生的QoS违规的问题,提出一种基于时间序列预测方法的云服务QoS预测方法。该预测方法利用改进的贝叶斯常均值(IBCM)模型,能够准确地预测云服务未来一段时间内的QoS状态。实验通过搭建Hadoop集群模拟云平台并收集了响应时间和吞吐量两种QoS属性的数据作为预测对象,实验结果表明:相比自回归积分滑动平均(ARIMA)模型和贝叶斯常均值折扣模型等时间序列预测方法,基于改进的贝叶斯常均值模型的云服务QoS预测方法的平方和误差(SSE)、平均绝对误差(MAE)、均方误差(MSE)和和平均绝对百分比误差(MAPE)均比前两者小一个数量级,因此具有更高的预测精度;同时预测结果对比图说明提出的预测方法具有更好的拟合效果。

关键词: 云服务, 服务质量, 贝叶斯模型, 预测

Abstract: For Quality of Service (QoS) guarantee of cloud service areas, a cloud service QoS prediction method based on time series prediction was proposed to select an appropriate cloud service which met QoS requirements of cloud user and perceive QoS violation may occur. The improved Bayesian constant mean model was used to predict QoS of cloud service accurately. In the experiment, a Hadoop system was established to simulate cloud computing and a lot of QoS data of response time and throughput were collected as predicted object. The experimental result shows that compared with Bayesian constant mean discount model and Autoregressive Integrated Moving Average (ARIMA) model, the proposed prediction method based on improved Bayesian constant mean model is one order of magnitude smaller than the previous methods in Square Sum Error (SSE), Mean Absolute Error (MAE), Mean Squared Error (MSE) and Mean Absolut Percentage Error (MAPE), so it has higher accuracy; and the comparison of prediction accuracy illustrate that the proposed method also has better fitting effect.

Key words: cloud service, Quality of Service (QoS), Bayesian constant mean model, prediction

中图分类号:

TP301

陈伟, 陈继明. 基于贝叶斯模型的云服务服务质量预测[J]. 计算机应用, 2016, 36(4): 914-917.

CHEN Wei, CHEN Jiming. Cloud service QoS prediction method based on Bayesian model[J]. Journal of Computer Applications, 2016, 36(4): 914-917.

参考文献

[1] Wikipedia. Cloud computing[EB/OL].[2015-02-10].https://en.wikipedia.org/wiki/Cloud_computing.
[2] TANG B, TANG M. Bayesian model-based prediction of service level agreement violations for cloud services[C]//TASE 2014:Proceedings of the 2014 Theoretical Aspects of Software Engineering Conference. Piscataway, NJ:IEEE, 2014:170-176.
[3] ASGHAR A, KAZEM P, PEDRAM H, et al. A Bayesian network based QoS model for grid service composition[J]. Expert Systems with Applications, 2015, 42(20):6828-6843.
[4] YU C, HUANG L. A Web Service QoS Prediction Approach Based on Time and Location-aware Collaborative Filtering[M]. Berlin:Springer, 2014:218-226.
[5] QIU W, ZHENG Z, WANG X, et al. Reputation-aware QoS value prediction of Web services[C]//Proceedings of the 2013 IEEE 10th International Conference on Services Computing. Piscataway, NJ:IEEE, 2013, 43:41-48.
[6] TONG J, HAIHONG E, SONG M, et al. Web service QoS prediction under sparse data via local link prediction[C]//Proceedings of the 2013 IEEE 10th International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing. Piscataway, NJ:IEEE, 2013:2285-2290.
[7] ZHENG Z, WU X, ZHANG Y, et al. QoS ranking prediction for cloud services[J]. IEEE Transactions on Parallel and Distributed Systems, 2013, 24(6):1213-1222.
[8] FREY S, LUTHHJE C, REICH C, et al. Cloud QoS scaling by fuzzy logic[C]//Proceedings of the 2014 IEEE International Conference on Cloud Engineering. Piscataway, NJ:IEEE, 2014:343-348.
[9] LIU Z, ZONG P, XIAO X, et al. Reliable Web service composition based on QoS dynamic prediction[J]. Soft Computing, 2015, 19(5):1409-1425.
[10] SANZO P D, MOLFESE F M, RUGHETTI D, et al. Providing transaction class-based QoS in in-memory data grids via machine learning[C]//NCCA 2014:Proceedings of the 2014 IEEE 3rd Symposium on Network Cloud Computing and Applications. Piscataway, NJ:IEEE, 2014, 16:46-53.
[11] XIA Y, LV J, ZHOU M, et al. A time series and reduction based model for QoS prediction of service ontologies[C]//ICNSC 2014:Proceedings of the 2014 IEEE 11th International Conference on Networking, Sensing and Control. Piscataway, NJ:IEEE, 2014:501-506.
[12] LI J, LUO X, XIA Y, et al. A time series and reduction-based model for modeling and QoS prediction of service compositions[J]. Concurrency and Computation:Practice & Experience, 2013, 27(1):146-167.
[13] 华哲邦, 李萌, 赵俊峰, 等.基于时间序列分析的Web Service QoS预测方法[J].计算机科学与探索, 2013, 7(3):218-226.(HUA Z B, LI M, ZHAO J F, et al. Web service QoS prediction method based on time series analysis[J]. Journal of Frontiers of Computer Science and Technology, 2013, 7(3):218-226.)
[14] NOURIKHAH H, AKBARI M, KALANTARI M. Modeling and predicting measured response time of cloud-based Web services using long-memory time series[J]. The Journal of Supercomputing, 2014, 71(2):673-696.
[15] WU Q, ZHANG M, ZHENG R, et al. A QoS-satisfied prediction model for cloud-service composition based on a hidden Markov model[J]. Mathematical Problems in Engineering, 2013, 2013:Article ID 387083.
[16] 卢艳红. 贝叶斯常均值模型状态误差方差Wt的改进及在能源预测中的应用[D].上海:华东理工大学, 2013:25-27.(LU Y H. Bayesian constant mean model state error variance Wt improved and application in the energy prediction[D]. Shanghai:East China University of Science and Technology, 2013:25-27.)

基于贝叶斯模型的云服务服务质量预测

Cloud service QoS prediction method based on Bayesian model

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

[1]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[2]	蔡彪, 李蕊岑, 吴媛媛. 相似性特征对链路预测的影响与增强[J]. 计算机应用, 2021, 41(9): 2569-2577.
[3]	安鑫, 杨海娇, 李建华, 任福继. 热安全约束下异构多核系统动态映射方法[J]. 计算机应用, 2021, 41(9): 2631-2638.
[4]	丁尹, 桑楠, 李晓瑜, 吴飞舟. 基于循环神经网络的电信行业容量数据预测方法[J]. 计算机应用, 2021, 41(8): 2373-2378.
[5]	武维, 李泽平, 杨华蔚, 林川, 王忠德. 融合内容特征和时序信息的深度注意力视频流行度预测模型[J]. 计算机应用, 2021, 41(7): 1878-1884.
[6]	周烁, 仇润鹤, 唐旻俊. 基于禁忌搜索和Q-learning的CR-NOMA系统的功率分配算法[J]. 计算机应用, 2021, 41(7): 2026-2032.
[7]	张元钧, 张曦煌. 基于图卷积与长短期记忆网络的动态网络表示学习模型[J]. 计算机应用, 2021, 41(7): 1857-1864.
[8]	李洋莹, 陈智军, 张子豪, 游兰. 基于改进Elman神经网络的制糖企业原糖需求预测模型[J]. 计算机应用, 2021, 41(7): 2113-2120.
[9]	赵秋云, 魏乐, 舒红平. 面向制造任务的云制造虚拟车间构造方法[J]. 计算机应用, 2021, 41(7): 2003-2011.
[10]	李旭娟, 皮建勇, 黄飞翔, 贾海朋. 基于自生成深度神经网络的4D航迹预测[J]. 计算机应用, 2021, 41(5): 1492-1499.
[11]	徐国保, 陈媛晓, 王骥. 基于图卷积网络的药物靶标关联预测算法[J]. 计算机应用, 2021, 41(5): 1522-1526.
[12]	倪水平, 李慧芳. 基于一维卷积神经网络与长短期记忆网络结合的电池荷电状态预测方法[J]. 计算机应用, 2021, 41(5): 1514-1521.
[13]	余东昌, 赵文芳, 聂凯, 张舸. 基于LightGBM算法的能见度预测模型[J]. 计算机应用, 2021, 41(4): 1035-1041.
[14]	张欣环, 刘宏杰, 施俊庆, 毛程远, 孟国连. 基于时空特征向量的长短期记忆人工神经网络的城市公交旅行时间预测[J]. 计算机应用, 2021, 41(3): 875-880.
[15]	冉家敏, 倪志伟, 彭鹏, 朱旭辉. 考虑空间众包工作者服务质量的任务分配策略及其萤火虫群优化算法求解[J]. 计算机应用, 2021, 41(3): 794-802.