Performance Degradation Model of Application Server System Based on Time Series Analysis

徐文彬 1; 2; 齐勇 1; 侯迪 1; 刘亮 3

您当前的位置：

首页 >

文章列表页 >

Performance Degradation Model of Application Server System Based on Time Series Analysis

更新时间：2025-12-08

- Performance Degradation Model of Application Server System Based on Time Series Analysis
- Vol. 41, Issue 4, Pages: 426-429(2007)
- 作者机构：
  
  1. 西安交通大学电子与信息工程学院,西安,710049
  2. 常熟理工学院计算机系, 215500, 常熟
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP31
- Online First：10 April 2007，
  
  Published：2007
- 稿件说明：
移动端阅览
徐文彬 1, 2, 齐勇 1, et al. Performance Degradation Model of Application Server System Based on Time Series Analysis[J]. 2007, 41(4): 426-429.
DOI：

徐文彬 1, 2, 齐勇 1, et al. Performance Degradation Model of Application Server System Based on Time Series Analysis[J]. 2007, 41(4): 426-429. DOI：

摘要

针对JUFrame应用服务器老化情况

设计了多种类型的客户请求程序和服务器端程序

记录了各种参数共计5类36个.对影响应用服务器中间件性能的主要指标“内存利用率”

采用时间序列分析方法建模

经采样数据的统计分析得出了自相关函数明显拖尾、偏自相关函数明显截尾的结果.模型的仿真结果表明

预测值与原始数据拟合良好

且可作为系统再生的依据

它适用于预测实际的运行系统.与其他软件老化预测方法比较

所提模型更切合系统的实际运行状况

有利于提高系统的可用率.

Abstract

Many kinds of client request applications and server programs are designed for the aging of JUFrame application sever

in which 36 parameters in 5 groups are recorded. The key index “memory usage” that affects the performance of middleware of application server is modeled based on time series analysis. The results that the auto correlation function(ACF)is clearly tail-dragged and the partial auto correlation function is clearly tail-truncated can be drawn via detailed statistical analysis of sampled data. The result of model simulation shows that the predicted value fits the original data well and can be regarded as the basis of system rejuvenation

and is applicable for predicting runtime systems. Compared to other software aging prediction methods

the proposed method is more suitable for the practical case of systems

and the availability of the system is improved.

关键词

Keywords

references

Huang Y, Kintala C, Kolettis N, et al. Software rejuvenation: analysis, module and applications [C]∥Proceedings of 25th IEEE International Symposium on Fault Tolerant Computing. Los Alamitos, USA: IEEE Computer Society, 1995:381-390.

Avritzer A, Weyuker E J. Monitoring smoothly degrading systems for increased dependability [J]. Empirical Software Engineering, 1997, 2(1):59-77.

Garg S, van Moorsel A, Vaidyanathan K, et al. A methodology for detection and estimation of software aging [C]∥Proceedings 9th International Symposium on Software Reliability Engineering. Los Alamitos, USA: IEEE Computer Society, 1998:283-292.

Vaidyanathan K, Trivedi K S. A measurement-based model for estimation of resource exhaustion in operational software systems [C]∥Proceedings 10th International Symposium on Software Reliability Engineering. Los Alamitos, USA: IEEE Computer Society, 1999:84-93.

Li Lei, Vaidyanathan K, Trivedi K S. An approach for estimation of software aging in a Web server [C]∥Proceedings of 2002 International Symposium on Empirical Software Engineering. Los Alamitos, USA: IEEE Computer Society, 2002:91-100.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Software Rejuvenation Model Based on Reconfiguration and Periodical Rejuvenation

A Relational Analysis Approach of Time Series with Uncertain Information

Chaotic Characteristics of Partial Discharges Time Series in Oil-Paper Insulation with Applications to Pattern Recognition

A Software Aging Detection Method Based on Bayesian Framework Using Least Squares Support Vector Machine

Fault Diagnosis of Rolling Bearings Using Recurrence Plot Coding Technique and Residual Network

Related Author

陈滢 2

侯迪 1

齐勇 1

杜小智 1

朱荣昌 1

孙卫 2

高亮 1

Related Institution

Engineering Institute, Air Force Engineering University

School of Electrical Engineering, Xi'an Jiaotong University

School of Mathematics and Statistics, Hainan Normal University

(State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure, East China Jiaotong University,,)

⁰