基于ARIMA-RNN组合模型的云服务器老化预测方法

孟海宁; 童新宇; 石月开; 朱磊; 冯锴; 黑新宏

doi:10.11959/j.issn.1000-436x.2021015

您当前的位置：

首页 >

文章列表页 >

基于ARIMA-RNN组合模型的云服务器老化预测方法

学术通信 | 更新时间：2024-06-05

- 基于ARIMA-RNN组合模型的云服务器老化预测方法
- Cloud server aging prediction method based on hybrid model of auto-regressive integrated moving average and recurrent neural network
- 通信学报 2021年42卷第1期页码：163-171
- 作者机构：
  
  1. 西安理工大学计算机科学与工程学院，陕西西安 710048
  2. 陕西省网络计算与安全技术重点实验室，陕西西安 710048
- 作者简介：
  
  [ "孟海宁（1979- ），女，内蒙古乌海人，博士，西安理工大学副教授、硕士生导师，主要研究方向为云计算系统可靠性评估。" ]
  [ "童新宇（1996- ），男，陕西西安人，西安理工大学硕士生，主要研究方向为云计算系统性能预测。" ]
  [ "石月开（1995- ），男，陕西榆林人，西安理工大学硕士生，主要研究方向为云系统性能监控与故障诊断。" ]
  [ "朱磊（1983- ），男，陕西咸阳人，博士，西安理工大学讲师，主要研究方向为数据挖掘。" ]
  [ "冯锴（1997- ），男，内蒙古锡林浩特人，西安理工大学硕士生，主要研究方向为数据挖掘。" ]
  [ "黑新宏（1976- ），男，陕西延安人，博士，西安理工大学教授、博士生导师，主要研究方向为系统可靠性和安全性评估。" ]
- 基金信息：
  
  国家自然科学基金资助项目(61602375);国家自然科学基金资助项目(61773313)
- DOI：10.11959/j.issn.1000-436x.2021015
  中图分类号： TP311.1
- 网络出版日期：2021-01，
  
  纸质出版日期：2021-01-25
- 稿件说明：
移动端阅览
孟海宁, 童新宇, 石月开, 等. 基于ARIMA-RNN组合模型的云服务器老化预测方法[J]. 通信学报, 2021,42(1):163-171.

Haining MENG, Xinyu TONG, Yuekai SHI, et al. Cloud server aging prediction method based on hybrid model of auto-regressive integrated moving average and recurrent neural network[J]. Journal on communications, 2021, 42(1): 163-171.
孟海宁, 童新宇, 石月开, 等. 基于ARIMA-RNN组合模型的云服务器老化预测方法[J]. 通信学报, 2021,42(1):163-171. DOI： 10.11959/j.issn.1000-436x.2021015.

Haining MENG, Xinyu TONG, Yuekai SHI, et al. Cloud server aging prediction method based on hybrid model of auto-regressive integrated moving average and recurrent neural network[J]. Journal on communications, 2021, 42(1): 163-171. DOI： 10.11959/j.issn.1000-436x.2021015.

摘要

针对云服务器系统运行环境具有非线性、随机性和突发性的特点，提出了基于整合移动平均自回归和循环神经网络组合模型（ARIMA-RNN）的软件老化预测方法。首先，采用 ARIMA 模型对云服务器时间序列数据进行老化预测；然后，利用灰色关联度分析法计算时间序列数据的相关性，确定 RNN 模型的输入维度；最后，将ARIMA模型预测值和历史数据作为RNN模型的输入进行二次老化预测，从而克服了ARIMA模型对波动较大的时间序列数据预测精度较低的局限性。实验结果表明，ARIMA-RNN组合模型比ARIMA模型及RNN模型的预测精度高，且比RNN模型预测收敛速度快。

Abstract

In view of the nonlinear

stochastic and sudden characteristics of operating environment of cloud server system

a software aging prediction method based on hybrid auto-regressive integrated moving average and recurrent neural network model (ARIMA-RNN) was proposed.Firstly

the ARIMA model performs software aging prediction of time series data in cloud server.Then the grey relation analysis method was used to calculate the correlation of the time series data to determine the input dimension of RNN model.Finally

the predicted value of ARIMA model and historical data were used as the input of RNN model for secondary aging prediction

which overcomes the limitation that ARIMA model has low prediction accuracy for time series data with large fluctuation.The experimental results show that the proposed ARIMA-RNN model has higher prediction accuracy than ARIMA model and RNN model

and has faster prediction convergence speed than RNN model.

关键词

Keywords

references

GROTTKE M , MATIAS R , TRIVEDI K S . The fundamentals of software aging [C ] // 2008 IEEE International Conference on Software Reliability Engineering Workshops . Piscataway:IEEE , 2008 : 1 - 6 .

GROTTKE M , TRIVEDI K S . Fighting bugs:remove,retry,replicate,and rejuvenate [J ] . Computer , 2007 , 40 : 107 - 109 .

HUANG Y , KINTALA C , KOLETTIS N , et al . Software rejuvenation:analysis,module and applications [C ] // 1995 Twenty-Fifth International Symposium on Fault-Tolerant Computing . Piscataway:IEEE Press , 1995 : 381 - 390 .

OKAMURA H , LUO C , DOHI T . Estimating response time distribution of server application in software aging phenomenon [C ] // 2013 International Symposium On Software Reliability Engineering Workshops . Piscataway:IEEE Press , 2013 : 281 - 284 .

MATOS R , ARAUJO J , MACIEL P , et al . A hybrid method based on multiple thresholds and time series prediction.international transaction on systems science and applications [J ] . Software Rejuvenation in Eucalyptus Cloud Computing Infrastructure , 2012 , 8 : 1 - 16 .

ISLAM J , KEUNG J , LEE K , LIU A . Empirical prediction models for adaptive resource provisioning in the cloud [J ] . Future Generation Computer Systems , 2012 , 28 ( 1 ): 155 - 162 .

LANGNER F , ANDRZEJAK A . Detecting software aging in a cloud computing framework by comparing development versions [C ] // 2013 International Symposium on Integrated Network Management . Piscataway:IEEE Press , 2013 : 896 - 899 .

KOUSIOURIS G , CUCINOTTA T , VARVARIGOU T . The effects of scheduling,workload type and consolidation scenarios on virtual machine performance and their prediction through optimized artificial neural networks [J ] . Journal of Systems and Software , 2011 , 84 ( 8 ): 1270 - 1291 .

郑鹏飞 , 齐勇 , 陈鹏飞 . 软件老化的多元时间序列分析方法 [J ] . 计算机科学与探索 , 2012 ( 2 ): 33 - 41 .

ZHENG P F , QI Y , CHEN P F . Multivariate time series analysis of software aging [J ] . Journal of Frontiers of Computer Science ＆ Technology , 2012 ( 2 ): 33 - 41 .

林已杰 , 赖清 , 周敏 . 基于 BP 神经网络和马尔可夫模型的服务器软件老化预测方法 [J ] . 西南师范大学学报(自然科学版) , 2011 , 36 ( 4 ): 193 - 197 .

LIN Y J , LAI Q , ZHOU M . A study on software aging forecasting of web server in BP neural network methods ＆ Markov model methods [J ] . Journal of Southwest China Normal University(Natural Science Edition) , 2011 , 36 ( 4 ): 193 - 197 .

ABU A I A S , MAGHARI A Y A . Forecasting groundwater production and rain amounts using ARIMA-hybrid ARIMA:case study of deir El-Balah City in GAZA [C ] // 2018 International Conference on Promising Electronic Technologies . Piscataway:IEEE Press , 2018 : 135 - 140 .

YANG H , PAN Z , TAO Q . Online learning for vector autoregressive moving-average time series prediction [J ] . Neurocomputing , 2018 , 315 : 9 - 17 .

TRIANTAFYLLOPOULOS K , SHAKANDLI M , CAMPBELL M . Count time series prediction using particle filters [J ] . Quality and Reliability Engineering International , 2019 , 35 ( 4 ): 1445 - 1449 .

SAOUD L S , GHORBANI R . Metacognitive octonion-valued neural networks as they relate to time series analysis [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 32 ( 2 ): 539 - 548 .

ESKANDARPOUR R , KHODAEI A . Leveraging accuracy-uncertainty tradeoff in SVM to achieve highly accurate outage predictions [J ] . IEEE Transactions on Power Systems , 2017 , 33 ( 1 ): 1139 - 1141 .

LAMOURINE M . OpenStack [J ] . Login::the Magazine of USENIX ＆SAGE , 2014 , 39 : 17 - 20 .

ALBAROODI H , MANICKAM S , SINGH P . Critical review of OpenStack security:issues and weaknesses [J ] . Journal of Computer Science , 2014 , 10 ( 1 ): 1032 .

HORNIK K . Approximation capabilities of multilayer feedforward networks [J ] . Neural Networks , 1991 , 4 ( 2 ): 251 - 257 .

刘思峰 , 蔡华 , 杨英杰 , 等 . 灰色关联分析模型研究进展 [J ] . 系统工程理论与实践 , 2013 ( 8 ): 2041 - 2046 .

LIU S F , CAI H , YANG Y J , et al . Advance in grey incidence analysis modelling [J ] . Systems Engineering-Theory ＆ Practice , 2013 ( 8 ): 2041 - 2046 .

TORQUATO M , MACIEL P , ARAUJO J , et al . An approach to investigate aging symptoms and rejuvenation effectiveness on software systems [C ] // 2017 12th Iberian Conference on Information SystemsandTechnologies . Piscataway:IEEE Press , 2017 : 1 - 6 .

WIDIYANINGTYAS T , MULADI , QONITA A . Use of ARIMA method to predict the number of train passenger in Malang City [C ] // 2019 International Conference of Artificial Intelligence and Information Technology . Piscataway:IEEE Press , 2019 : 359 - 364

TOKGÖZ , ÜNAL G , . A RNN based time series approach for forecasting turkish electricity load [C ] // 2018 26th Signal Processing and Communications Applications Conference . Piscataway:IEEE Press , 2018 : 1 - 4 .

浏览量

506

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据