基于微重启和部分客观马尔可夫决策模型的智能水下机器人软件自修复方法

doi:10.11772/j.issn.1001-9081.2015.08.2375

计算机应用 ›› 2015, Vol. 35 ›› Issue (8): 2375-2379.DOI: 10.11772/j.issn.1001-9081.2015.08.2375

基于微重启和部分客观马尔可夫决策模型的智能水下机器人软件自修复方法

张汝波^1,2, 孟雷¹, 史长亭¹

1. 哈尔滨工程大学计算机科学与技术学院, 哈尔滨 150001;
2. 大连民族大学机电工程学院, 辽宁大连 116600

收稿日期:2015-03-25 修回日期:2015-06-03 出版日期:2015-08-10 发布日期:2015-08-14
通讯作者: 史长亭(1980-),男,山东茌平人,讲师,博士,主要研究方向:软件可靠性、智能控制,shichangting@hrbeu.edu.cn
作者简介:张汝波(1963-),男,吉林吉林人,教授,博士生导师,博士,主要研究方向:人工智能、机器学习、计算智能、模式识别; 孟雷(1987-),男,安徽宿州人,硕士研究生,主要研究方向:软件可靠性、机器学习。
基金资助:
装备预研基金项目(9140C270101130C27099)。

Self-repair method for autonomous underwater vehicle software based on micro-reboot and partially observable Markov decision process model

ZHANG Rubo^1,2, MENG Lei¹, SHI Changting¹

1. College of Computer Science and Technology, Harbin Engineering University, Harbin Heilongjiang 150001, China;
2. College of Mechanical and Electronic Engineering, Dalian Nationalities University, Dalian Liaoning 116600, China

Received:2015-03-25 Revised:2015-06-03 Online:2015-08-10 Published:2015-08-14

摘要/Abstract

摘要：

针对智能水下机器人(AUV)软件故障修复过程中存在的修复代价过高和系统环境只有部分可观察的问题,提出了一种基于微重启技术和部分客观马尔可夫决策(POMDP)模型的AUV软件故障修复方法。该方法结合AUV软件系统分层结构特点,构建了基于微重启的三层重启结构,便于细粒度的自修复微重启策略的实施;并依据部分可观马尔可夫决策过程理论,给出AUV软件自修复POMDP模型,同时采用基于点的值迭代(PBVI)算法求解生成修复策略,以最小化累积修复代价为目标,使系统在部分可观环境下能够以较低的修复代价执行修复动作。仿真实验结果表明,基于微重启技术和POMDP模型的AUV软件故障修复方法能够解决由软件老化及系统调用引起的AUV软件故障,同与两层微重启策略和三层微重启固定策略相比,该方法在累积故障修复时间和运行稳定性上明显更优。

关键词: 智能水下机器人, 微重启, 自修复, 部分客观马尔可夫决策, 基于点的值迭代算法

Abstract:

Aiming at the disadvantages of high fixing cost and partial observability of system environment in the process of repairing Autonomous Underwater Vehicle (AUV) software faults, a method was proposed based on micro-reboot mechanism and Partially Observable Markov Decision Process (POMDP) model for failure repair of AUV. To facilitate the implementation of the fine-grained self-repair micro-reboot strategy, a hierarchical structure was built based on micro-reboot combined with the characteristics of AUV software. Meanwhile, a self-repair model was put forward according to the theory of POMDP. With the goal of minimizing the fixing cost, the repair strategy was solved by Point Based Value Iteration (PBVI) algorithm to allow the repair action to execute in the partially observable environment at a lower cost.The simulation results show that the proposed repairing method can solve the AUV software failures caused by the software-aging and system calls. Compared with two-tier micro-repair strategy and three-tier micro-repair fixing strategy, this method is obviously superior to the contrast method in cumulative fault repair time and operational stability.

Key words: Autonomous Underwater Vehicle (AUV), micro-reboot, self-repair, Partially Observable Markov Decision Process (POMDP), Point Based Value Iteration (PBVI) algorithm

中图分类号:

TP311.52

张汝波, 孟雷, 史长亭. 基于微重启和部分客观马尔可夫决策模型的智能水下机器人软件自修复方法[J]. 计算机应用, 2015, 35(8): 2375-2379.

ZHANG Rubo, MENG Lei, SHI Changting. Self-repair method for autonomous underwater vehicle software based on micro-reboot and partially observable Markov decision process model[J]. Journal of Computer Applications, 2015, 35(8): 2375-2379.

参考文献

[1] XU Y, PANG Y, GAN Y, et al. AUV state of the art and prospect [J].Transactions on Intelligent Systems, 2006,1(1):11-14. (徐玉如,庞永杰,甘永,等.智能水下机器人技术展望[J].智能系统学报,2006,1(1):11-14.)
[2] ALDURGAM M M, DUFFUAA S O. Optimal joint maintenance and operation policies to maximise overall systems effectiveness [J]. International Journal of Production Research, 2013,51(5): 1319-1330.
[3] PSAIER H, SKOPIK F, SCHALL D, et al. Behavior monitoring in self-healing service-oriented systems [C]//Computer Software and Applications Conference (COMPSAC). Piscataway: IEEE, 2010;357-366.
[4] ANGELOPOULOS K, SOUZA V E S, PIMENTEL J. Requirements and architectural approaches to adaptive software systems: a comparative study [C]//SEAMS '13: Proceedings of the 8th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. Piscataway: IEEE, 2013: 23-32.
[5] WANG Y. System fault quick recovery design based on VxWorks [J]. Application of Electronic Technique, 2008, 34(6): 32-34. (王洋.基于VxWorks的系统故障快速恢复设计[J]. 电子技术应用, 2008,34(6):32-34.)
[6] HU Y, NAN Q, GAO A. Design and implementation of the check pointing and task recovery mechanism based on VxWorks [J]. Journal of Air Force Engineering University: Natural Science Edition, 2013,14(5):48-52. (胡延苏,南秦博,高昂. VxWorks中任务恢复机制的设计与实现[J]. 空军工程大学学报:自然科学版,2013,14(5):48-52.)
[7] YU K. Dynamic loading mechanism of spaceborne computer technology research based on Reliability[D]. Changsha: National University of Defense Technology,2009: 1-54. (于康.基于动态加载机制的星载计算机可靠性增强技术研究[D].长沙:国防科学技术大学,2009:1-54.)
[8] SUN K,MU D,ZHANG H. Design and implementation of high available fault-tolerant system based on VxWorks [J].Computer Technology and Development, 2012, 22(4): 123-125. (孙锴,慕德俊,张慧翔.基于VxWorks的高可用容错系统的设计与实现[J].计算机技术与发展,2012,22(4):123-125.)
[9] CANDEA G, CUTLER J, FOX A. Improving availability with recursive microreboots: a soft-state system case study [J]. Performance Evaluation Journal, 2004, 56(1/2/3): 213-248.
[10] LE M, TAMIR Y. Applying microreboot to system software [C]//Proceedings of the 2012 IEEE International Conference on Software Security and Reliability. Piscataway: IEEE, 2012: 1-20.
[11] XU Z, ZHAO F, BHAGALIA R, et al. Generic rebooting scheme and model-based probabilistic pruning algorithm for tree-like structure tracking [C]//Proceedings of the 2012 9th IEEE International Symposium on Biomedical Imaging. Piscataway: IEEE, 2012: 796-799.
[12] ALONSO J, MATIAS R, VICENTE E,et al. A comparative evaluation of software rejuvenation strategies [C]//Proceedings of the 2011 Third International Workshop on Software Aging and Rejuvenation. Piscataway: IEEE, 2011:26-31.
[13] WANG Z, GUO C, LIU F, et al. Research on the application of artificial neural network in the fine-grained software rejuvenation of computing system [J]. Chinese Journal of Computers,2008,31(7):1268-1274. (王湛,郭成昊,刘凤玉,等.神经网络在计算系统软件抗衰重启技术中的应用研究[J].计算机学报,2008,31(8):1268-1274.)
[14] YOU J. Research on fine grained software rejuvenation policy and related technology [D]. Nanjing: Nanjing University of Science and Technology, 2006: 1-88. (游静.细粒度软件抗衰策略及相关技术研究[D].南京:南京理工大学,2006:1-88.)
[15] SHI C, ZHANG R, ZHAO J. Software self-recovery method of AUV based on micro-reboot [C]//Proceedings of the 2011 9th World Congress on Intelligent Control and Automation. Piscataway: IEEE, 2011: 91-96.

基于微重启和部分客观马尔可夫决策模型的智能水下机器人软件自修复方法

Self-repair method for autonomous underwater vehicle software based on micro-reboot and partially observable Markov decision process model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics