Neural network based approach for time to crash prediction to cope with software aging

Neural network based approach for time to crash prediction to cope with software aging

下载PDF

导出

摘要 Recent studies have shown that software is one of the main reasons for computer systems unavailability. A growing ac- cumulation of software errors with time causes a phenomenon called software aging. This phenomenon can result in system per- formance degradation and eventually system hang/crash. To cope with software aging, software rejuvenation has been proposed. Software rejuvenation is a proactive technique which leads to re- moving the accumulated software errors by stopping the system, cleaning up its internal state, and resuming its normal operation. One of the main challenges of software rejuvenation is accurately predicting the time to crash due to aging factors such as me- mory leaks. In this paper, different machine learning techniques are compared to accurately predict the software time to crash un- der different aging scenarios. Finally, by comparing the accuracy of different techniques, it can be concluded that the multilayer per- ceptron neural network has the highest prediction accuracy among all techniques studied. Recent studies have shown that software is one of the main reasons for computer systems unavailability. A growing ac- cumulation of software errors with time causes a phenomenon called software aging. This phenomenon can result in system per- formance degradation and eventually system hang/crash. To cope with software aging, software rejuvenation has been proposed. Software rejuvenation is a proactive technique which leads to re- moving the accumulated software errors by stopping the system, cleaning up its internal state, and resuming its normal operation. One of the main challenges of software rejuvenation is accurately predicting the time to crash due to aging factors such as me- mory leaks. In this paper, different machine learning techniques are compared to accurately predict the software time to crash un- der different aging scenarios. Finally, by comparing the accuracy of different techniques, it can be concluded that the multilayer per- ceptron neural network has the highest prediction accuracy among all techniques studied.

作者 Moona Yakhchi Javier Alonso Mahdi Fazeli Amir Akhavan Bitaraf Ahmad Patooghy

机构地区 School of Computer Science Institute of Advanced Studies on Cybersecurity Department of Computer Engineering

出处《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2015年第2期407-414,共8页 系统工程与电子技术（英文版）

关键词 software reliability software rejuvenation machine learning software reliability,software rejuvenation,machine learning

分类号 TP311.53 [自动化与计算机技术—计算机软件与理论] TP183 [自动化与计算机技术—控制理论与控制工程]

引文网络
相关文献

参考文献24

1I. Koren, C. M. Krishna. Fault tolerant systems. Amsterdam: Elsevier, 2007.
2Y. Huang, C. Kintala, N. D. Funton. Software rejuvenation: analysis, module and applications. Proc. of the 25th IEEE hl- ternational Symposium on Fault Tolerant Camputing, 1995: 381 - 390.
3J. A. Lopez, R. Matias, E. Vicente, et al. A comparative ex- perimental study of software rejuvenation overhead. Journal of Petfolvnance Evaluation, 2013, 70(3): 231 -250.
4S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, et al. Improve- ments to the SMO algorithm for SVM regression. IEEE Trans. on Neural Networks, 2(100, 11(5): 1188- 1193.
5K. Vaidyanathan, K. S. Trivedi. A comprehensive model for software rejuvenation. IEEE Trans. on Dependable and Secure Computing, 2005, 2(2): 124- 137.
6J. A. Lopez, L. Silva, A. Andrzejak, et al. High-available grid services through the use of virtualized clustering. Proc. of the 8th IEEE/ACM htelvational Conference on Grid Computing, 2007: 34-41.
7J. A. Lopez, J. Torres, R. Gavalda. Predicting web server crashes: a case study in comparing prediction algorithms. Proc. of the 34th hlternational Conference on Distributed Computing Systems, 2009: 264- 269.
8J. A. Lopez, L. Belanche, D. R. Avresky. Predicting software anomalies using machine learning techniques. Proc. of the lOth IEEE International Symposium on Network Computing and Applications, 2011 : 163 - 170.
9R. Matos, J. Araujo, P. Maciel, et al. Software rejuvenation in eucalyptus cloud computing infrastructure: a hybrid method based on multiple thresholds and time series prediction. Inter- national Transactions on Systems Science and Applications, 2012(8): 1- 16.
10J. A. Lopez, A. Bovenzi, J. Li, et al. Software rejuvenation - Do IT & Telco industries use Proc. of the 23rd IEEE hlternational Symposium on Sftware Reliabili Engineering Workshops, 2012:229 - 304.

1David J Handelsman.An old emperor finds new clothing： rejuvenation in our time[J].Asian Journal of Andrology,2011,13(1):125-129. 被引量：3
2徐远通,王其如.ON THE CONJECTURE OF M.K.GRAMMATIKOPOULOS et al.[J].Chinese Science Bulletin,1992,37(10):877-877. 被引量：1
3何声武,汪嘉冈.STOPPED PROCESSES OF TEMPORALLY HOMOGENEOUS MARKOV JUMP PROCESSES[J].Chinese Science Bulletin,1992,37(8):623-626.
4WANG Zongjun(College of Business and Management Huazhong University of Science and Technology)Wuhan 430074, China.Study　on　Fuzzy　Comprehensive　Evaluation　of　Simulation　Schemes　of　Socio－economic　Systems[J].Systems Science and Systems Engineering,1996,6(2):155-161. 被引量：2
5Han Shan-Ling Zhu Ping Lin Zhong-Qin Shi Yu-Liang.Frontal Crash Analysis of a Fully Detailed Car Model Based on Finite Element Method[J].上海交通大学学报,2004,38(z2):136-141.
6孙红岩.Neural network fault diagnosis method optimization with rough set and genetic algorithms[J].Journal of Chongqing University,2006,5(2):94-97.
7王友年,马腾才.Electronic Stopping Power of Intermediate-velocity Heavy Ions in Solids[J].Chinese Science Bulletin,1993,38(12):993-997.
8李耀勇,郑南宁.Improved dynamical model for neural network and the stabilization of associative memory[J].Progress in Natural Science:Materials International,1998,8(5):99-107.
9ZHU Tao,\ WANG Zheng\|ou Institute of Systems Engineering, Tianjin University, Tianjin 300072, China.A Simple Hybrid Recursive Learning Algorithm with High Generalization Performance for Radial Basis Function Neural Network[J].Systems Science and Systems Engineering,2000,10(1):16-27. 被引量：12
10Li Renhou & Gao Feng (Institute of Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China).Complex Function Approximation Based on Multi-ANN Approach[J].Journal of Systems Engineering and Electronics,1995,6(2):22-31.

Journal of Systems Engineering and Electronics

2015年第2期

浏览历史

内容加载中请稍等...

Neural network based approach for time to crash prediction to cope with software aging

参考文献24

相关作者

相关机构

相关主题

浏览历史