基于时间序列预测的自适应失效检测模型
|
摘要
随着全球范围内分布式系统发展进程的加快及其构造的日趋复杂,越来越多的失效现象层出不穷,严重威胁着系统的高可用性。失效检测作为保障分布式系统高可用性的核心技术之一,已成为研究热点方向。目前,失效检测已被广泛应用于通信协议、Web服务器、集群管理和失效恢复等方面。同时,失效检测在无线网络、云计算平台、大数据等领域也得到了重要应用。
通过研究现有自适应失效检测算法及其实现过程可以发现,失效检测的本质是研究非线性时间序列的预测问题。而最小二乘支持向量回归算法是非线性时间序列预测领域的有效方法之一,在小样本空间和预测精度等方面有一定优势。传统失效检测算法基于概率统计模型计算下一心跳的到达时间,受限于某种概率分布且需要较大数据量,存在一定局限性。而采用最小二乘支持向量回归算法进行失效检测预测恰能弥补其不足。在实际应用中常面临小样本空间,为此本文提出FD-LSSVR模型并进行了讨论。针对现有自适应失效检测算法需考虑离群值这一问题,模型引入聚类分析法综合考虑心跳延迟和权值两个指标来过滤对预测结果影响较大的离群值,其中权值的分配满足幂律分布。
实验结果表明,本文提出的自适应失效检测模型FD-LSSVR不仅满足◇P检测级别,而且在检测时间和准确度方面均有较好表现,可用以缓解子网络延迟对失效检测的影响。另外,FD-LSSVR算法可根据实际情况,通过调整参数α值的大小来满足多种不同应用的需求,具有一定的灵活性。
With the acceleration of the developmental process of the worldwide distributed systems and its more complex structure than before, more and more failure phenomena happen that seriously threats the high availability of systems. As one of the core technology of protecting the high availability of distributed systems, failure detection has gradually become a hot research direction. Recently failure detection has been widely used in communication protocols, Web server, cluster management and failure recovery etc. At the same time, failure detection has also been an important application in the fields of wireless network, cloud computing platform, and big data etc.
Throughout the existing adaptive failure detection algorithm and in-depth research of the process of failure detection, we can understand that the nature of failure detection belongs to nonlinear time series prediction problem. The least squares support vector algorithm is one of the effective methods of nonlinear time series prediction, which has certain advantages in small sample space and forecast accuracy. The traditional adaptive failure detection algorithm is generally based on probability statistical model which is limited to some probability distribution and requires a large amount of data to calculate the arrival time of next heartbeat message, for what there are some limitations. While the use of least squares support vector regression algorithm for failure detection forecast just to make up for its shortcomings. Practical applications are often faced by small sample space, so this paper proposed and discussed FD-LSSVR (Failure Detection-Least Squares Sport Vector Regression) model, which also introduces clustering analysis method that considering the two indicators of heartbeat delays and weights to remove outliers that have a greater impact on predicted results for that the existing adaptive failure detection algorithms need to consider outliers. The weights assigned to meet the power-law distribution.
The experimental results show that the model not only satisfies the OP detection level, but also performs great at both detection time and accuracy, for what it can be used to alleviate the sub-network delay for failure detection. In addition, according to actual situation, FD-LSSVR can meet the needs of a variety of different applications by adjusting the size of the parameter a values, with a certain degree of flexibility.
通过研究现有自适应失效检测算法及其实现过程可以发现,失效检测的本质是研究非线性时间序列的预测问题。而最小二乘支持向量回归算法是非线性时间序列预测领域的有效方法之一,在小样本空间和预测精度等方面有一定优势。传统失效检测算法基于概率统计模型计算下一心跳的到达时间,受限于某种概率分布且需要较大数据量,存在一定局限性。而采用最小二乘支持向量回归算法进行失效检测预测恰能弥补其不足。在实际应用中常面临小样本空间,为此本文提出FD-LSSVR模型并进行了讨论。针对现有自适应失效检测算法需考虑离群值这一问题,模型引入聚类分析法综合考虑心跳延迟和权值两个指标来过滤对预测结果影响较大的离群值,其中权值的分配满足幂律分布。
实验结果表明,本文提出的自适应失效检测模型FD-LSSVR不仅满足◇P检测级别,而且在检测时间和准确度方面均有较好表现,可用以缓解子网络延迟对失效检测的影响。另外,FD-LSSVR算法可根据实际情况,通过调整参数α值的大小来满足多种不同应用的需求,具有一定的灵活性。
With the acceleration of the developmental process of the worldwide distributed systems and its more complex structure than before, more and more failure phenomena happen that seriously threats the high availability of systems. As one of the core technology of protecting the high availability of distributed systems, failure detection has gradually become a hot research direction. Recently failure detection has been widely used in communication protocols, Web server, cluster management and failure recovery etc. At the same time, failure detection has also been an important application in the fields of wireless network, cloud computing platform, and big data etc.
Throughout the existing adaptive failure detection algorithm and in-depth research of the process of failure detection, we can understand that the nature of failure detection belongs to nonlinear time series prediction problem. The least squares support vector algorithm is one of the effective methods of nonlinear time series prediction, which has certain advantages in small sample space and forecast accuracy. The traditional adaptive failure detection algorithm is generally based on probability statistical model which is limited to some probability distribution and requires a large amount of data to calculate the arrival time of next heartbeat message, for what there are some limitations. While the use of least squares support vector regression algorithm for failure detection forecast just to make up for its shortcomings. Practical applications are often faced by small sample space, so this paper proposed and discussed FD-LSSVR (Failure Detection-Least Squares Sport Vector Regression) model, which also introduces clustering analysis method that considering the two indicators of heartbeat delays and weights to remove outliers that have a greater impact on predicted results for that the existing adaptive failure detection algorithms need to consider outliers. The weights assigned to meet the power-law distribution.
The experimental results show that the model not only satisfies the OP detection level, but also performs great at both detection time and accuracy, for what it can be used to alleviate the sub-network delay for failure detection. In addition, according to actual situation, FD-LSSVR can meet the needs of a variety of different applications by adjusting the size of the parameter a values, with a certain degree of flexibility.
引文
[1]王强,周恩强,陈海涛等.一种基于环拓扑面向容灾的失效检测算法[J].计算机工程与科学,2010,32(7)：30-34
[2]Bhagwan R, Savage S, Voelker G M. Replication Strategies for Highly Available Peer-to-peer Storage Systems[C]. Proceedings of Fu-DiCo:Future directions in Distributed Computing.2002.
[3]Manivannan D, Singhal M. A Low-Overhead Recovery Technique Using Quasi Synchronous Check pointing[C]. Proceedings IEEE Int. Conf. Distributed Compute. Syst. Los Alamitos, CA, USA,1996:100-107.
[4]Avritzer A, Bondi A, Grottke M, et al. Performance Assurance via Software Rejuvenation: Monitoring, Statistics and Algorithms[C]. Proceedings of the 2006 International Conference on Dependable Systems and Networks (DSN). Philadelphia, Los Alamitos, CA, USA,2006:435-444.
[5]Carretero J, Vera X, Chaparro P,et al.Microarchitectural Online Testing for Failure Detection in Memory Order Buffers[J].IEEE Transactions on Computers,2010, 59(5):623-637
[6]Lindhorst T, Lukas G, Nett E, et al. Data-Mining-Based Link Failure Detection for Wireless Mesh Networks[C]. Proceedings of 29th IEEE Symposium on Reliable Distributed Systems. New Delhi, Punjab India,2010:353-357.
[7]Greve F, Sens P, Arantes L, et al. A Failure Detector for Wireless Networks with Unknown Membership[C]. Proceedings of the 17th International Conference on Parallel Processing. Bordeaux, France,2011, Ⅱ:27-38.
[8]Tsai W, Shao Q, Sun X, et al. Real-Time Service-oriented Cloud Computing[C]. Proceedings of the 6th World Congress on Services. Miami, Florida, USA,2010:473-478.
[9]侯金轩,林荣恒,邹华等.一种基于Volterra级数的云平台自适应失效检测机制[J].电信科学,2011,27(10)：51-56.
[10]杜海宁.基于云计算的图书馆海量数据存储研究[J].图书与情报,2010,3：99-101.
[11]Huang T, Qi F, Gao F.Failure Detection and Localization in OTN Based on Optical Power Analysis[C].2010 Second International Conference on Communication Software and Networks, Dalian,China,2010.46-51
[12]Contreras-Medina L M, Romero-Troncoso R J, Rangel-Magdaleno J J, et al. FPGA-Based Multiple-Channel Vibration Analyzer for Industrial Applications in Induction Motor Failure Detection[J].IEEE Transactions on Instrumentation and Measurement, 2010,59(1):63-72
[13]向小东.基于神经网络与混沌理论的非线性时间序列预测研究[D].[博士学位论文].成都：西南交通大学,2002.
[14]Du S, Wu T. Support Vector Machine for Regression[J]. Journal of System Simulation, 2003,15(11):1580-1585.
[15]Vapnik V N, Golowich S E, Smola A. Support Vector Method for Function Approximation, Regression Estimation, and Signal Processing [C]. Advances in neural information processing systems 9:proceedings of the 1996 conference /edited by Michael C. Mozer, Michael I. Jordan and Thomas Petsche.1996:281-287.
[16]Drucker h, Wu D H, Vapnik V N. Support vector machines for spam categorization [J]. Journal of IEEE Transactions on Neural Networks,1999,10(5):1048-1054.
[17]Platt J C. Fast training of support vector machines using sequential minimal optimization [M]. Advances in Kernel Methods-Support Vector Learning. Cambridge, Massachusetts: The MIT Press,1999:185-208.
[18]Suykens J A K, Vandewalle J. Least Squares Support Vector Machine Classifiers[J]. Journal of Neural Processing Letters 9,1999:293-300.
[19]Suykens J A K, Lukas L, Wandewalle J. Sparse approximation using least squares support vector machines[C]. Proceeding of the IEEE International Symposium on Circuits and Systems(ISCAS 2000),2000:757-760.
[20]刘定平,肖蔚然.应用最小二乘支持向量机和混合遗传算法的制粉系统优化控制[J].动力工程,2007,27(5)：728-731.
[21]冯学军.最小二乘支持向量机的研究与应用[J].安庆师范学院学报(自然科学版),2009,15(1)：112-114.
[22]吴洲,潘丰,田鹏.基于PSO和LSSVM的生化过程建模研究[J].自动化与仪表,2009,2：5-8.
[23]戴宏亮.基于智能遗传算法与复合最小二乘支持向量机的长江水质预测与评价[J].计算机应用研究,2009,26(1)：79-81.
[24]Jain A K, Murty M N, Flynn P J. Data clustering:A Review[J]. Journal of ACM Computing Surveys,1999,31(3):264-323.
[25]Everitt B S, Landau S, Leese M. Cluster Analysis (4th edition)[M]. London:Arnold Press, 2001.
[26]殷瑞飞.数据挖掘中的聚类方法及其应用.[博士学位论文]厦门：厦门大学,2008.
[27]李桃迎.交通领域中的聚类分析方法研究.[博士学位论文].大连：大连海事大学,2010.
[28]Hansen P, Jaumard B. Cluster analysis and mathematical programming [J]. Math Program, 1997,79:191-215..
[29]He Q. A review of clustering algorithms as applied to ir, UIUCLIS-1999/6+IRG. Univ. Illinois at Urban-Champaign,1999.
[30]Berkhin P. Survey of clustering data mining [EB].[2001-4-15] http://www.accrue.com/products/rp_cluster_review.pdf.
[31]Murtagh F. A survey of recent advances in hierarchical clustering algorithms [J]. Computer Journal,1983,26(4):354-359.
[32]Baraldi A, Blonda P. A survey of fuzzy clustering algorithms for pattern recognition-Part I and II[C]. IEEE transactions on Systems Man and Cybernetics Part B-Cybernetics,1999, 29(6):778-801.
[33]章成志,王惠临.多语言文本聚类研究综述[J].现代图书情报技术,2009,179(6)：31-36.
[34]张建华,江贺,张宪超.蚁群聚类算法综述[J].计算机工程与应用,2006,16：171-174.
[35]李峻金,向阳,芦英明等.粒子群聚类算法综述[J].计算机应用研究,2009,26(12)：4423-4427.
[36]侯垚森.基于消息延迟预测的自适应失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2010.
[37]Baldoni R, Helary J M, Raynal M. From Crash Fault-Tolerance to Arbitrary-Fault Tolerance:Towards a Modular Approach[C]. In:IEEE International Conference on Dependable Systems and Network. New Jersey:IEEE,2000:273-282.
[38]董辉,雷大军.分布式系统中失效检测器研究.计算机系统应用[J].2009,18(5)：38-41.
[39]Chandra TD, Toueg S. Unreliable failure detectors for reliable distributed systems[J]. Journal of ACM (JACM).1996,43(2):225-267.
[40]Chen W, Toueg S, Aguilera M K. On the Quality of Service of Failure Detectors [J]. IEEE Transactions on Computers,2002,51(1):13-32.
[41]李庆华,罗犀劲.基于检查点进程迁移机制的改进[J].计算机仿真,2003,20(5)：50-52.
[42]Bertier M, Marin O, Sens P. Implementation and Performance Evaluation of an Adaptable Failure Detector[C]. Proceedings of the 2002 International Conference on Dependable Systems and Networks (DSN'02). Washington, D.C., USA,2002:354-363.
[43]Hayashibara N, Cherif A, Katayama T. Failure detectors for large-scale distributed systems [C]. Proceedings of the 21st IEEE Symp. on Reliable Distributed Systems (SRDS 2002). Washington,2002.404-409.
[44]陈文远.累加型失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2012.
[45]刘丽娟.支持向量机超参数调节方法的研究及其在人脸识别中的应用[D].[硕士学位论文].重庆：重庆大学,2010.
[46]Vapnik V. The Nature of Statistical Learning Theory [M]. NY:Springer Verlag,1995.
[47]许允之,方磊,谭风雷等.基于最小二乘支持向量机的故障电机诊断方法[J].实验技术与管理,2012,29：35-37.
[48]张晓伟,谢强,陈伟.基于划分和孤立点检测的审计证据获取研究[J].计算机应用研究,2009,7：2495-2498.
[49]Li T, Chen Y. An improved k-means algorithm for clustering using entropy weighting measures[C]. Proceeding of the 7th World Congress on Intelligent Control and Automation (WCICA2008),2008,149-153.
[50]Jing L, Michael K N, Huang J Z. An Entropy Weighting k-Means Algorithm for Subspace Clustering of High-Dimensional Sparse Data[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2007,19(8):1026-1041.
[51]张伟莉,倪志伟,赖建章.一种新的基于网格的聚类算法[J].计算机应用研究,2008,25(2)：1337-1339.
[52]张世武,吴月华,杨杰等.基于信息寻觅智能体的网络用户浏览模式研究[J].计算机研究与发展,2004,41(11)：1966-1973.
[53]Defago X, Urba P, Hayashibara N, et al. Definition and Specification of Accrual Failure Detectors[C]. Proceedings of the 2005 International Conference on Dependable Systems and Networks (DSN'05). Yokohama, Japan,2005:206-215.
[54]Hayashibara N, Defago X, Yared R, et al. The φ Accrual Failure Detector[C]. Proceedings of the 23rd IEEE International Symposium on Reliable Distributed Systems.2004:66-78.
[55]公彦杰.基于LS SVM建立发酵过程动态模型的研究及软件实现[D].[硕士学位论文].北京：北京工业大学,2011.
[56]杨仕飞.基于灰色预测的失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2011.
[2]Bhagwan R, Savage S, Voelker G M. Replication Strategies for Highly Available Peer-to-peer Storage Systems[C]. Proceedings of Fu-DiCo:Future directions in Distributed Computing.2002.
[3]Manivannan D, Singhal M. A Low-Overhead Recovery Technique Using Quasi Synchronous Check pointing[C]. Proceedings IEEE Int. Conf. Distributed Compute. Syst. Los Alamitos, CA, USA,1996:100-107.
[4]Avritzer A, Bondi A, Grottke M, et al. Performance Assurance via Software Rejuvenation: Monitoring, Statistics and Algorithms[C]. Proceedings of the 2006 International Conference on Dependable Systems and Networks (DSN). Philadelphia, Los Alamitos, CA, USA,2006:435-444.
[5]Carretero J, Vera X, Chaparro P,et al.Microarchitectural Online Testing for Failure Detection in Memory Order Buffers[J].IEEE Transactions on Computers,2010, 59(5):623-637
[6]Lindhorst T, Lukas G, Nett E, et al. Data-Mining-Based Link Failure Detection for Wireless Mesh Networks[C]. Proceedings of 29th IEEE Symposium on Reliable Distributed Systems. New Delhi, Punjab India,2010:353-357.
[7]Greve F, Sens P, Arantes L, et al. A Failure Detector for Wireless Networks with Unknown Membership[C]. Proceedings of the 17th International Conference on Parallel Processing. Bordeaux, France,2011, Ⅱ:27-38.
[8]Tsai W, Shao Q, Sun X, et al. Real-Time Service-oriented Cloud Computing[C]. Proceedings of the 6th World Congress on Services. Miami, Florida, USA,2010:473-478.
[9]侯金轩,林荣恒,邹华等.一种基于Volterra级数的云平台自适应失效检测机制[J].电信科学,2011,27(10)：51-56.
[10]杜海宁.基于云计算的图书馆海量数据存储研究[J].图书与情报,2010,3：99-101.
[11]Huang T, Qi F, Gao F.Failure Detection and Localization in OTN Based on Optical Power Analysis[C].2010 Second International Conference on Communication Software and Networks, Dalian,China,2010.46-51
[12]Contreras-Medina L M, Romero-Troncoso R J, Rangel-Magdaleno J J, et al. FPGA-Based Multiple-Channel Vibration Analyzer for Industrial Applications in Induction Motor Failure Detection[J].IEEE Transactions on Instrumentation and Measurement, 2010,59(1):63-72
[13]向小东.基于神经网络与混沌理论的非线性时间序列预测研究[D].[博士学位论文].成都：西南交通大学,2002.
[14]Du S, Wu T. Support Vector Machine for Regression[J]. Journal of System Simulation, 2003,15(11):1580-1585.
[15]Vapnik V N, Golowich S E, Smola A. Support Vector Method for Function Approximation, Regression Estimation, and Signal Processing [C]. Advances in neural information processing systems 9:proceedings of the 1996 conference /edited by Michael C. Mozer, Michael I. Jordan and Thomas Petsche.1996:281-287.
[16]Drucker h, Wu D H, Vapnik V N. Support vector machines for spam categorization [J]. Journal of IEEE Transactions on Neural Networks,1999,10(5):1048-1054.
[17]Platt J C. Fast training of support vector machines using sequential minimal optimization [M]. Advances in Kernel Methods-Support Vector Learning. Cambridge, Massachusetts: The MIT Press,1999:185-208.
[18]Suykens J A K, Vandewalle J. Least Squares Support Vector Machine Classifiers[J]. Journal of Neural Processing Letters 9,1999:293-300.
[19]Suykens J A K, Lukas L, Wandewalle J. Sparse approximation using least squares support vector machines[C]. Proceeding of the IEEE International Symposium on Circuits and Systems(ISCAS 2000),2000:757-760.
[20]刘定平,肖蔚然.应用最小二乘支持向量机和混合遗传算法的制粉系统优化控制[J].动力工程,2007,27(5)：728-731.
[21]冯学军.最小二乘支持向量机的研究与应用[J].安庆师范学院学报(自然科学版),2009,15(1)：112-114.
[22]吴洲,潘丰,田鹏.基于PSO和LSSVM的生化过程建模研究[J].自动化与仪表,2009,2：5-8.
[23]戴宏亮.基于智能遗传算法与复合最小二乘支持向量机的长江水质预测与评价[J].计算机应用研究,2009,26(1)：79-81.
[24]Jain A K, Murty M N, Flynn P J. Data clustering:A Review[J]. Journal of ACM Computing Surveys,1999,31(3):264-323.
[25]Everitt B S, Landau S, Leese M. Cluster Analysis (4th edition)[M]. London:Arnold Press, 2001.
[26]殷瑞飞.数据挖掘中的聚类方法及其应用.[博士学位论文]厦门：厦门大学,2008.
[27]李桃迎.交通领域中的聚类分析方法研究.[博士学位论文].大连：大连海事大学,2010.
[28]Hansen P, Jaumard B. Cluster analysis and mathematical programming [J]. Math Program, 1997,79:191-215..
[29]He Q. A review of clustering algorithms as applied to ir, UIUCLIS-1999/6+IRG. Univ. Illinois at Urban-Champaign,1999.
[30]Berkhin P. Survey of clustering data mining [EB].[2001-4-15] http://www.accrue.com/products/rp_cluster_review.pdf.
[31]Murtagh F. A survey of recent advances in hierarchical clustering algorithms [J]. Computer Journal,1983,26(4):354-359.
[32]Baraldi A, Blonda P. A survey of fuzzy clustering algorithms for pattern recognition-Part I and II[C]. IEEE transactions on Systems Man and Cybernetics Part B-Cybernetics,1999, 29(6):778-801.
[33]章成志,王惠临.多语言文本聚类研究综述[J].现代图书情报技术,2009,179(6)：31-36.
[34]张建华,江贺,张宪超.蚁群聚类算法综述[J].计算机工程与应用,2006,16：171-174.
[35]李峻金,向阳,芦英明等.粒子群聚类算法综述[J].计算机应用研究,2009,26(12)：4423-4427.
[36]侯垚森.基于消息延迟预测的自适应失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2010.
[37]Baldoni R, Helary J M, Raynal M. From Crash Fault-Tolerance to Arbitrary-Fault Tolerance:Towards a Modular Approach[C]. In:IEEE International Conference on Dependable Systems and Network. New Jersey:IEEE,2000:273-282.
[38]董辉,雷大军.分布式系统中失效检测器研究.计算机系统应用[J].2009,18(5)：38-41.
[39]Chandra TD, Toueg S. Unreliable failure detectors for reliable distributed systems[J]. Journal of ACM (JACM).1996,43(2):225-267.
[40]Chen W, Toueg S, Aguilera M K. On the Quality of Service of Failure Detectors [J]. IEEE Transactions on Computers,2002,51(1):13-32.
[41]李庆华,罗犀劲.基于检查点进程迁移机制的改进[J].计算机仿真,2003,20(5)：50-52.
[42]Bertier M, Marin O, Sens P. Implementation and Performance Evaluation of an Adaptable Failure Detector[C]. Proceedings of the 2002 International Conference on Dependable Systems and Networks (DSN'02). Washington, D.C., USA,2002:354-363.
[43]Hayashibara N, Cherif A, Katayama T. Failure detectors for large-scale distributed systems [C]. Proceedings of the 21st IEEE Symp. on Reliable Distributed Systems (SRDS 2002). Washington,2002.404-409.
[44]陈文远.累加型失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2012.
[45]刘丽娟.支持向量机超参数调节方法的研究及其在人脸识别中的应用[D].[硕士学位论文].重庆：重庆大学,2010.
[46]Vapnik V. The Nature of Statistical Learning Theory [M]. NY:Springer Verlag,1995.
[47]许允之,方磊,谭风雷等.基于最小二乘支持向量机的故障电机诊断方法[J].实验技术与管理,2012,29：35-37.
[48]张晓伟,谢强,陈伟.基于划分和孤立点检测的审计证据获取研究[J].计算机应用研究,2009,7：2495-2498.
[49]Li T, Chen Y. An improved k-means algorithm for clustering using entropy weighting measures[C]. Proceeding of the 7th World Congress on Intelligent Control and Automation (WCICA2008),2008,149-153.
[50]Jing L, Michael K N, Huang J Z. An Entropy Weighting k-Means Algorithm for Subspace Clustering of High-Dimensional Sparse Data[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2007,19(8):1026-1041.
[51]张伟莉,倪志伟,赖建章.一种新的基于网格的聚类算法[J].计算机应用研究,2008,25(2)：1337-1339.
[52]张世武,吴月华,杨杰等.基于信息寻觅智能体的网络用户浏览模式研究[J].计算机研究与发展,2004,41(11)：1966-1973.
[53]Defago X, Urba P, Hayashibara N, et al. Definition and Specification of Accrual Failure Detectors[C]. Proceedings of the 2005 International Conference on Dependable Systems and Networks (DSN'05). Yokohama, Japan,2005:206-215.
[54]Hayashibara N, Defago X, Yared R, et al. The φ Accrual Failure Detector[C]. Proceedings of the 23rd IEEE International Symposium on Reliable Distributed Systems.2004:66-78.
[55]公彦杰.基于LS SVM建立发酵过程动态模型的研究及软件实现[D].[硕士学位论文].北京：北京工业大学,2011.
[56]杨仕飞.基于灰色预测的失效检测模型研究[D].[硕士学位论文].郑州：郑州大学,2011.