战略互联网故障智能诊断策略研究
|
摘要
随着新一代战略互联网规模的不断扩大,网络应用不断增加,传统的网络故障诊断系统功能单一、操作复杂、效率低下,已不能满足军网管理的发展需要。如何有效地、安全地、易扩展地管理网络故障是目前迫切需要解决的问题,其中,故障检测、故障定位是故障管理中的关键环节。本文由网络故障的层次传播性出发,从信息的可用性角度,构建一个战略互联网故障诊断问题的合理解决方案。
本文首先针对战略互联网的管理由集中式向分布式的发展趋势,依据动态SNMP代理群的思想,讨论了动态群管理策略(包括组群策略和故障管理模式变更策略),建立了一个自适应分布式诊断模型,并提出了基于易损链路的稳态群首选举算法。在此基础上,本文提出分层分散故障诊断策略,对战略互联网四层结构(物理接入层,链路传送层,网络控制层和应用层)的不同故障特点和状态属性融入不同的检测策略,给出一个较为完整的解决方案。
本文主要研究工作和取得的成果如下:
(1) 基于仿生学的免疫原理,将肽链定义为网络中执行的事件检测序列,提出并实现了一种新型的物理层故障节点定位方法—基于生物免疫学的故障定位。该方法首先依据“阳性选择”原则进行事件库设计,对高频度行为模式优先分析和处理,提高了检测的速度和效率。其次,依据故障之间的事件检测序列关联关系,运用图论和邻接矩阵的方法求出根故障集,由故障相关性确定故障源,有效地起到故障过滤和定位的功能。经实验证明,本方法具有很强的实效性。
(2) 基于粗糙集的神经网络理论,提出链路传输层故障诊断的RSNN算法,实现不一致情况下的故障规则获取和学习样本的净化处理。该算法具有简化样本、适应性强、容错性高等特点,能有效处理链路传送层故障诊断中噪声和不相容的信息。由于诊断问题的实质是一种映射,该算法用一种前馈型网络来逼近这种映射关系,实现对故障的有效分类。实验表明,利用该方法实现的系统与同类的其他方法相比,大大提高了诊断准确率和诊断速度。
(3) 运用弱T范数簇模糊神经元,设计出一种基于粗糙模糊神经网络的网络控制层拥塞预测算法(RFNN)。RFNN不仅具有单调性和连续性,而且能满足网络拥塞的推理一致性要求。实验表明,利用RFNN的处理不确定性问题和自学习能力进行流量预测,与传统拥塞预测方法相比,具有较好的效果。
(4) 提出了基于SVM的网络应用层故障检测模型,并对模型各个组件的功能、机制和实现进行了深入探讨。对用于检测的网络数据特征,本文利用异构数据集上的
The new generation strategic internet is a new type military network, constituted by physical layer, link transport layer, network control layer and application layer. It can flexibly support multi-service, and has anti-destroy, re-combined properties. With the development of computer science and communication network, the scale of strategic internet is growing larger, together with the emergence of more network applications. Owing to simple function, complex operation and lower efficiency, the old network troubleshooting system already can't satisfy for the demands of carrier development. In order to perform high efficiency and reliability, it is very important for us to set up a perfect network troubleshooting system. With the development of the present distributed network troubleshooting management, a self-adapting distributed network management framework based on dynamic SNMP agent groups is presented in this paper. The explanation of how to achieve this model is discussed. Especially, dynamic groups' management policy in the model is discussed, including grouping policy and choice of management mode, and a stable group Ω leader election algorithm based on loss links is given. According to the feature of strategic internet architecture, this paper brings layering-decentralization intelligence into this field, which makes it possible for the failure automatic location and diagnosis.The main achievements of this paper are as follows:(1) According to the immunology principles of bionics, a new physical layer nodefault location method-Immunology based Fault Location Method is presented. Inthis paper event detection sequences are viewed as analogous to peptide. According to the principle of positive selection in Immunology, the system builds up its event database. The behavior model whose frequency is higher will be analyzed and processed first. It improves the speed and effectiveness of intrusion detection. Fault Location is based on the event detection sequences correlation, graph theory and adjacency matrix are two methods to get the root failure sets. With the relationship of failures, this paper gives a method to determine the source of failure in this paper, which will perform failure filtration and location function effectively. The experiment system implemented by this method shows a good diagnostic ability.(2) Puts forward RSNN algorithm, a designing fault diagnosis method for link transport layer, which tightly combines neural network and rough sets. We can get reduced
information table, which implies that the number of evaluation criteria is reduced with no information loss through rough set approach. And then, this reduced information is used to develop classification rules and train neural network to infer appropriate parameter. The rules developed by RS-Neural network analysis show the best prediction accuracy, if a case does match any of the rules. It's capable of overcoming several shortcomings in existing diagnosis systems, such as a dilemma between stability and redundancy. Since the essence of fault diagnosis is a kind of mapping, an artificial neural network model is adopted to deal with the mapping relation, categorizing the network faults. The experiment system implemented by this method shows a good diagnostic ability.(3) Consisting of weak T-norm cluster fuzzy neuron, a rough fuzzy neural network (RFNN) is constructed in this paper, which is applied to network control layercongestion inference. RFNN overcomes a few shortcoming of the conventional CRI, and it is much easier to satisfy consistency principle of fuzzy inference than CRI. Analyzed the properties of the new method, we discovered that it is continuous and monotonic. The reasoning results prove better performance obtained than other conventional congestion methods.(4) A framework of SVM based Network Fault Detection System of Application Layer is proposed. The function, mechanism and realization of the components of this framework are discussed in the paper. By means of distance metric of heterogeneous datasets, the feature data of network are preprocessed. Based on guaranteed estimators, we estimate the size of test set. Thus we not only avoid bad train result for lack of examples, but also reduce the training time and improve the efficiency of training. During the training, by means of fuzzy mathematics, considering the effect of different network data features to the classification, a weight method is brought forward. It improves the accuracy of network fault detection. The problem of low detection accuracy of some types of faults for the imbalance of training examples is researched. A method of increasing the proportion of the examples of these types is presented. It improves the detection accuracy of these types of faults.(5) A framework model proposed in this paper is a data-link redundant strategy based on reliability theory. The redundant running(RUS) could be combined with the normal maintenance, which greatly improves the performance of the network system. The static-checking and policy of authentication mechanism ensure the running network without any error. The redundant equipments are independent but are capable of communication with each other when they work their actions. The model is independent of
本文首先针对战略互联网的管理由集中式向分布式的发展趋势,依据动态SNMP代理群的思想,讨论了动态群管理策略(包括组群策略和故障管理模式变更策略),建立了一个自适应分布式诊断模型,并提出了基于易损链路的稳态群首选举算法。在此基础上,本文提出分层分散故障诊断策略,对战略互联网四层结构(物理接入层,链路传送层,网络控制层和应用层)的不同故障特点和状态属性融入不同的检测策略,给出一个较为完整的解决方案。
本文主要研究工作和取得的成果如下:
(1) 基于仿生学的免疫原理,将肽链定义为网络中执行的事件检测序列,提出并实现了一种新型的物理层故障节点定位方法—基于生物免疫学的故障定位。该方法首先依据“阳性选择”原则进行事件库设计,对高频度行为模式优先分析和处理,提高了检测的速度和效率。其次,依据故障之间的事件检测序列关联关系,运用图论和邻接矩阵的方法求出根故障集,由故障相关性确定故障源,有效地起到故障过滤和定位的功能。经实验证明,本方法具有很强的实效性。
(2) 基于粗糙集的神经网络理论,提出链路传输层故障诊断的RSNN算法,实现不一致情况下的故障规则获取和学习样本的净化处理。该算法具有简化样本、适应性强、容错性高等特点,能有效处理链路传送层故障诊断中噪声和不相容的信息。由于诊断问题的实质是一种映射,该算法用一种前馈型网络来逼近这种映射关系,实现对故障的有效分类。实验表明,利用该方法实现的系统与同类的其他方法相比,大大提高了诊断准确率和诊断速度。
(3) 运用弱T范数簇模糊神经元,设计出一种基于粗糙模糊神经网络的网络控制层拥塞预测算法(RFNN)。RFNN不仅具有单调性和连续性,而且能满足网络拥塞的推理一致性要求。实验表明,利用RFNN的处理不确定性问题和自学习能力进行流量预测,与传统拥塞预测方法相比,具有较好的效果。
(4) 提出了基于SVM的网络应用层故障检测模型,并对模型各个组件的功能、机制和实现进行了深入探讨。对用于检测的网络数据特征,本文利用异构数据集上的
The new generation strategic internet is a new type military network, constituted by physical layer, link transport layer, network control layer and application layer. It can flexibly support multi-service, and has anti-destroy, re-combined properties. With the development of computer science and communication network, the scale of strategic internet is growing larger, together with the emergence of more network applications. Owing to simple function, complex operation and lower efficiency, the old network troubleshooting system already can't satisfy for the demands of carrier development. In order to perform high efficiency and reliability, it is very important for us to set up a perfect network troubleshooting system. With the development of the present distributed network troubleshooting management, a self-adapting distributed network management framework based on dynamic SNMP agent groups is presented in this paper. The explanation of how to achieve this model is discussed. Especially, dynamic groups' management policy in the model is discussed, including grouping policy and choice of management mode, and a stable group Ω leader election algorithm based on loss links is given. According to the feature of strategic internet architecture, this paper brings layering-decentralization intelligence into this field, which makes it possible for the failure automatic location and diagnosis.The main achievements of this paper are as follows:(1) According to the immunology principles of bionics, a new physical layer nodefault location method-Immunology based Fault Location Method is presented. Inthis paper event detection sequences are viewed as analogous to peptide. According to the principle of positive selection in Immunology, the system builds up its event database. The behavior model whose frequency is higher will be analyzed and processed first. It improves the speed and effectiveness of intrusion detection. Fault Location is based on the event detection sequences correlation, graph theory and adjacency matrix are two methods to get the root failure sets. With the relationship of failures, this paper gives a method to determine the source of failure in this paper, which will perform failure filtration and location function effectively. The experiment system implemented by this method shows a good diagnostic ability.(2) Puts forward RSNN algorithm, a designing fault diagnosis method for link transport layer, which tightly combines neural network and rough sets. We can get reduced
information table, which implies that the number of evaluation criteria is reduced with no information loss through rough set approach. And then, this reduced information is used to develop classification rules and train neural network to infer appropriate parameter. The rules developed by RS-Neural network analysis show the best prediction accuracy, if a case does match any of the rules. It's capable of overcoming several shortcomings in existing diagnosis systems, such as a dilemma between stability and redundancy. Since the essence of fault diagnosis is a kind of mapping, an artificial neural network model is adopted to deal with the mapping relation, categorizing the network faults. The experiment system implemented by this method shows a good diagnostic ability.(3) Consisting of weak T-norm cluster fuzzy neuron, a rough fuzzy neural network (RFNN) is constructed in this paper, which is applied to network control layercongestion inference. RFNN overcomes a few shortcoming of the conventional CRI, and it is much easier to satisfy consistency principle of fuzzy inference than CRI. Analyzed the properties of the new method, we discovered that it is continuous and monotonic. The reasoning results prove better performance obtained than other conventional congestion methods.(4) A framework of SVM based Network Fault Detection System of Application Layer is proposed. The function, mechanism and realization of the components of this framework are discussed in the paper. By means of distance metric of heterogeneous datasets, the feature data of network are preprocessed. Based on guaranteed estimators, we estimate the size of test set. Thus we not only avoid bad train result for lack of examples, but also reduce the training time and improve the efficiency of training. During the training, by means of fuzzy mathematics, considering the effect of different network data features to the classification, a weight method is brought forward. It improves the accuracy of network fault detection. The problem of low detection accuracy of some types of faults for the imbalance of training examples is researched. A method of increasing the proportion of the examples of these types is presented. It improves the detection accuracy of these types of faults.(5) A framework model proposed in this paper is a data-link redundant strategy based on reliability theory. The redundant running(RUS) could be combined with the normal maintenance, which greatly improves the performance of the network system. The static-checking and policy of authentication mechanism ensure the running network without any error. The redundant equipments are independent but are capable of communication with each other when they work their actions. The model is independent of
引文
1 Zhu Y, Chen T and Liu S. Models and analysis of trade-offs in distributed network management approaches. Proceedings of the 7th IFIP/IEEE International Symposium on Integrated Network Management (IM 01), Seattle W A, 2001.391-395.
2 Goldszmidt G and Yemini Y. Delegated agents for network management. IEEE Trans. Commun., Mar. 1998, 36:66-70.
3 Puliafito A and Tomarchio O. Using mobile agents to implement flexible network management strategies. Computer Communications, April, 2000, 23 (8):708-719.
4 Harrington D and Presuhn R. Architecture for describing simple network management protocol (SNMP) management frameworks. RFC3411, Dec, 2002.
5 Aguilera M K, Delporte-Gallet C, Fauconnier H and Toueg S. Stable leader election. Proceedings of the 15th International Symposium on Distributed Algorithms (DISC 01), Berlin Heidelberg. 2001. 108-122.
6 Al-Shaer E. A dynamic group management framework for large-scale distributed event monitoring. Proceedings of the 7th IFIP/IEEE International Symposium on Integrated Network Management (IM 01), Seattle W A, 2001. 565-578.
7 Othmar kyas, Network Troubleshooting. New York: Agilent Technologies, 2001
8 Jacobson V, Nichols K, Poduri K. An Expedited Forwarding PHB. IETF Internet RFC 2598, 1999
9 R. Haas, P. Droz, and B. Stiller. Autonomic service deployment in networks. IBM Systems Journal, 2003, 42(1): 1258-1267
10 Hong J W K, Kong J Y. Web-based intranet services and network management. IEEE Communications Magazine, 1997, 35(10):100-110.
11 Kahani M. Decentralized approaches for network management. ACM Computer Communication Review, 1997, 27(3): 36-47.
12 Barillaud F. Network management using internet technologies. 5th IFIP/IEEE International Symposium on Integrated Network Management (IM'97). San Diego: IEEE Press, 1997: 61-70.
13 Brunner M, Stadler R. Service management in multiparty active networks. IEEE Communications Magazine, March 2000:144-151.
14 Han S J, Lee J H. A mobility management using dynamic updates of domain name in mobile computing environment. International Conference on Internet Computing. Las Vegas: CSREA Press, 2001: 444-450.
15 Wang P, Li X M, Zhao H. A scalable hierarchical architecture for distributed network management. International Conference on Computer Networks and Mobile Computing[C]. IEEE Computer Society Press, 2001:21-26.
16 李千目,张宏,刘凤玉.智能化的网络故障诊断研究.国防科技报告.2003.7.25,编号:NLG-2002-076
17 戚涌,李千目,刘凤玉.基于BP神经网络的网络智能诊断系统.微电子学与计算机.2004,21(10):10-13
18 李千目,戚涌,张宏,刘凤玉.基于神经网络的网络故障诊断.计算机工程.2003,29(21):6-7,11.
19 杨云,徐永红,李千目,刘凤玉.一种QoS路由多目标遗传算法.通信学报,2004年,25(1):43-51
20 杨云,徐永红,李千目,刘凤玉.一种基于TCP/IP的QoS路由多目标遗传算法.模式识别与人工智能.2004年,17(2):232-238
21 沈俊,顾冠群,罗军舟.网络管理的研究和发展.计算机研究与发展.2002(10):1153—1167
22 李千目,戚勇,张宏,刘凤玉.基于粗糙集神经网络的网络故障诊断新方法.计算机研究与发展.2004年,41(10):1696-1702
23 E. N. Skoundrianos, S. G. Tzafestas. Fault Diagnosis via Local Neural Networks. Mathematics and Computers in Simulation, 2002, 60(3-5): 169-180
24 Rolf Iserman. Process Fault Detection Based on Modeling and Estimation and Knowledge Processing-Tutorial Paper. Automatic,1999, 29(4):815-835
25 R. Tagliaferri, A. Eleuteri, M. Meneganti, F. Barone. Fuzzy Min-Max Neural Network: from Classification to Regression. Soft Computing, 2001, 32(5):69-76.
26 Jagannathan R, Neumann P, Javitz H, Valdes A, Garvey T. A Real-Time Fault Diagnosis Expert System(FDES). Final Technical Report, Computer Science Laboratory, SRI International, Menlo Park, Calif., Feb. 2002
27 R. Tagliaferri, A. Eleuteri, M. Meneganti, E Barone. Fuzzy Min-Max Neural Network: from Classification to Regression. Soft Computing, 2001, 32(5):69-76.
28 K. ichiro Minami, H. Nakajima, and T. Toyoshima, Real-time discrimination of ventricular tachyarrhythmia with fourier-transform neural network. IEEE Trans. Biomed. Eng., 1999, 46(2):485-496
29 刘凤玉,李千目,衷宜.基于贝叶似分类的分布式网络故障诊断模型.南京理工大学学报,2003,27(5):546-550
30 Zhang WX, Mi JS, et al. Knowledge reduction in inconsistent information systems. Chinese Journal of Computer. 2003, 26(1): 12-18
31 Veres A, Boda M. The chaotic nature of TCP congestion control. In: Proc INFOCOM2000, Tel Aviv, Israel, CA: IEEE Computer Society 2000
32 ChenDan, HeHua-Can, WangHui. A new t-norm and its application in fuzzy control. In: Proc WCICIA'2000, Hefei, China, 2000. 1284-1289
33 Yager R. OWA neurons: A new class of fuzzy neurons. In: Proc IEEE-FUZZ, 1992. 2316-2340
34 Glorennec Pierre-Yves. Neuro-fuzzy logic. In: ProcIEEE-FUZZ, 1996. 512-518
35 Witold Pedrycz. Fuzzy neural networks and neuro computations. Fuzzy Sets and Systems. 1992, 56(1):1-28
36 Witold Pedrycz. Logic-based neurons: Extensions, uncertainty representation and development of fuzzy controllers. Fuzzy Sets and Systems, 1994, 66(1): 251-266
37 Bailey S A, Chen Ye-Hwa. A two layerd network using the OR/AND neuron. In: Proc IEEE-FUZZ, 1998. 1566-1571
38 陈丹,何华灿,王晖.一种新的基于弱T范数簇的神经元模型.计算机学报.2001,24(10):1115-1120
39 Averkin A N. Decision making based on multivalued logic and fuzzy logic, architectures for semiotic modeling and situation analysis in large complex systems. In: Proc ISIC Workshop, Monterey, 1995. 871-875
40 He Hua-Can et al. Generalized logic in experience thinking. Science in China(E), 1996, 39(3): 225-234
41 Buckley J J, Siler W. A new t-norm. Fuzzy Sets and Systems, 1998, 16(1):283-290
42 Christoph L, Schuba, Ivan V, Krsul. Analysis of denial of service attack on TCP. Proceedings of the IEEE Computer Society Symposium on Research in Security and Privacy 2000
43 晏蒲柳,夏德麟,郭成城.计算机网络智能故障诊断知识库构造方法.模式识别与人工智能,2000.13(2)142—144
44 C-C Lo. S-H Chen. A scheduling based event correlation scheme for fault identification in communications network. Computer Communications. 1999. 22(5):432-438
45 R. D. Gardner. d. A. Harle. Pattern discovery and specification techniques for alarm correlation. Proceedings of Network Operations and Management Symposium 1998(NOM'98). New Orleans. Feb. 1998. Vol. 3:713-722
46 R. Sasisekaran. V. Seshadri. S. M. Weiss. Data mining and forecasting in large scale telecommunication network[J]. IEEE Expert. 1996(2):37-43
47 W. Klosgen. Efficient discovery of interesting statements in data based[J]. Journal of Intelligent Information Systems. 1995(4):53-69
48 Wang Xinmiao. Huang Tianxi. Yan. Puliu. Knowledge Discovery from communication network alarm databases[J]. Wuhan University Journal of Natural Sciences. 2000. 5(2). 194-198
49 Deri L, Ban B. Static vs Dynamic CMIP/SNMP Network Management Using CORBA. Proc IS & N'97, Como, Italy, May 1997:329-337
50 Feit S. SNMP: A Guide to Network Management. New York: McGraw-Hill, 1994
51 Z. Pawlak. Rough sets and their application. Microcomputer Application. 1994, 13(2):71-75.
52 S. S. Y. Lau. Image segmentation based on the indiscernibility relation. Rough sets, Fyzzy sets and Knowledge discovery. 1994, 22(7):395-404.
53 Z. M. Wojcik. Intelligent image filtering using rough sets. Rough sets, Fuzzy sets and Knowledge discovery. 1994, 16(5):337-386.
54 George Bolt. Investigating Fault Tolerance Artificial Neural Networks. Advanced Computer Architecture Group, Department of Computer Science, University of York, Heslington, York, Y01 5DD, U. K, March 1991
55 R. Rengaswamy, V. Venkatasubramanian. A fast training neural network architecture and it's updation for incipient fault detection and diagnosis, Computers and Chemical Engineering, 2000., 24(2), 431-437
56 David Wetherall, Ulana Legedza, John Guttag. ANTS: A toolkit for building and dynamically deploying network protocols. IEEE Networking, 1998, 12(3): 12-20
57 Dasgupta D. Immunity-based Intrusion Detection System: A General Framework. In 22nd National Information System Security Conference, 18～21 Oct. 1999, Arlington, VA, USA(Gaithersburg, MD, USA, 1999), NIST, pp. 147～60 vol. 1
58 Tolle J, Niggermann O. Supporting Intrusion Detection by Graph Clustering and Graph Drawing. Lecture Notes in Computer Science 1907(200). In Recent Advances In Intrusion Detection(RAID) Workshop, 2000
59 Mukkamala S, Janoski G, Sung A. Intrusion Detection Using Neural Networks And Support Vector Machines. In 2002 International Joint Conference on Neural Networks (IJCNN), 12～17 May 2002, Honolulu, HI, USA (Piscataway, NJ, USA, 2002), vol.2, IEEE, pp. 1702～1707.
60 D Randall Wilson, Tony R Martinez. Improved Heterogeneous Distance Functions. Journal of Artificial Intelligence Research, 1997, 6(1): 1～34
61 Srinivas Mukkamala, Andrew H. Sung. Identifying Significant Feature for Network Forensic Analysis Using Artificial Intelligent Techniques[J]. Internation Journal of Digital Evidence, Winter 2003, Volume 1, Issue4
62 K. R. Muller, S. Mika, G. Ratsch, K. Tsuda, and B. Scholkopf. An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks, 2001, 12(2): 181-201
63 Roy A Maxion, Frank E Feather. A case study of Ethernet anomalies in a distributed computing environment. IEEE Transactions on Reliability, 1999, 39 (4): 142-146
64 Polly Huang, Anja Feldmann. A nonintrusive, wavelet—based approach to detecting network performance problems. ACM SIGCOMM Internet measurement workshop 2001, San Francisco.
65 Paul Barford and David Plonka. Characteristics of network traffic flow anomalies. In Proceeding of the ACM SIGCOMM Internet Measurement Workshop, 2001
66 Rajesh Talpade. Traffic-based network monitoring framework for anomaly detection. Proceeding of the 4 IEEE symposium on computer and communication, July, 1999, Egypt.
67 Lawerence Ho and Symeon Papavassiliou. Network and service anomaly detection in multi-service transaction—based electronic commerce wide area networks. Proceeding of the 4 IEEE symposium on computer and communication, July, 1999, Egypt.
68 Vladimir N Vapnik.统计学习理论的本质[M].张学工译.北京:清华大学出版社,2000
69 D Randall Wilson, Tony R Martinez. Improved Heterogeneous Distance Functions. Journal of Artificial Intelligence Research, 1997, 6(1): 1-34
70 Srinivas Mukkamala, Andrew H. Sung. Identifying Significant Feature for Network Forensic Analysis Using Artificial Intelligent Techniques. Internation Journal of Digital Evidence, Winter 2003, Volume 1, Issue4
71 Asa Ben-Hur, David Horn, Hava T. Siegelmann. Support Vector Clustering. Journal of Machine Learning Research, 2001(2): 125-137
72 DARPA, MA (USA): Lincoln Laboratory, Massachusetts Institute of technology. http://www.11.mit.edu/IST/ideval/index.html
73 KDD Cup 1999 Data. Irvine, CA(USA), Information and Computer Science, University of California, Irivine http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
74 Othmar Kyas. Network Troubleshooting. Berlin: Agilrnt Technologies, 2002.
75 张军,李宏,李忠孝等.一种新的自组织时分多址甚高频数据链隐藏终端分析方法.电子学报.2001.29(12):258-263
76 葛彤,冯正平,朱继懋.分段重构控制策略.自动化学报.2000.26(6):431-436
77 钱方,贾焰,黄杰等.提高冗余服务性能的动态容错算法.软件学报.2001.12(6):541-546
78 Patterson, D. A., A. Brown, P. Broadwell, G. etc. Recovery-Oriented Computing (ROC): Motivation, Definition, Techniques, and Case Studies. UC Berkeley Computer Science Technical Report UCB//CSD-02-1175, March 15, 2002: 571-574.
79 Brown, A. and D. A. Patterson. Embracing Failure: A Case for Recovery-Oriented Computing (ROC). 2001 High Performance Transaction Processing Symposium, Asilomar, CA, October 2001: 854-859.
80 Oppenheimer, D., Archana Ganapathi, and David A. Patterson. Why do Internet services fail, and what can be done about it? 4th USENIX Symposium on Internet Technologies and Systems (USITS'03), March 2003:125-128.
81 K. Vaidyanathan and Kishor S. Trivedi, Workload-Based Estimation of Resource Exhaustion in Software Systems, Dept. of Electrical & Computer Engineering, Duke University, 1999:213-217.
82 R. Haas, P. Droz, and B. Stiller. Autonomic service deployment in networks. IBM Systems Journal, 2003, 42 (1): 82-87.
83 Castelli V., et al. Proactive Management of Software Aging. IBM JRD. 2001, 45(2): 311-332.
84 Garg S., Puliafito A., Trivedi K. S. Analysis of Software Rejuvenation using Markov Regenerative Stochastic Petri Net. In: Proc. of ISSRE 1995, Toulouse, France, 1995: 158-132.
85 Dohi T., Goseva-Popstojanova K., Trivedi K. S. Statistical Non-parametric Algorithms to Estimate the Optimal Software Rejuvenation Schedule. In: Proc. 2000 Pacific Rim International Symposium on Dependable Computing (PRDC 2000), Los Angeles, CA, 2000:582-588
86 Dohi T., K. Goseva-Popstojanova, K. S. Trivedi. Analysis of Software Cost Models with Rejuvenation. In: Proc. 5th IEEE International Symposium on High Assurance Systems Engineering (HASE 2000), Albuquerque, New Mexico, 2000:465-470
87 Pfening S., et al. Optimal Software Rejuvenation for Tolerating Soft Failures. Performance Evaluation. 1996(27/28): 491-506
88 Garg S., et al. Analysis of Preventive Maintenance in Transactions Based Software Systems. IEEE Trans. on Computers. 1998, 47(1): 96-107.
89 Garg S., et al. On the analysis of software rejuvenation policies. In: Proc. of the 12th Annual Conf. on Computer Assurance, 1997: 88-96.
90 Vaidyanathan K., et al. Analysis and implementation of software rejuvenation in cluster systems. In: Proceedings of the Joint International Conference on Measurement and Modeling of Computer System, ACM SIGMETRICS 2001/PERFORMANCE 2001, Cambridge, MA, 2001: 62-71.
91 S. Chen and K. Nahrstedt. On Finding Multi-Constrained Paths. International Conference on Communications (ICC'98),. IEEE, 1998:874-879
92 T. Korkmaz and M. Krunz. A Randomized Algorithm for Finding a Path Subject to Multiple QoS Constrains. Computer Networks. Amsterdam, Netherlands. 1999.
93 Shaikh, A., Rexford, J., Shin, K. G. Evaluating the impact of stale link state on
2 Goldszmidt G and Yemini Y. Delegated agents for network management. IEEE Trans. Commun., Mar. 1998, 36:66-70.
3 Puliafito A and Tomarchio O. Using mobile agents to implement flexible network management strategies. Computer Communications, April, 2000, 23 (8):708-719.
4 Harrington D and Presuhn R. Architecture for describing simple network management protocol (SNMP) management frameworks. RFC3411, Dec, 2002.
5 Aguilera M K, Delporte-Gallet C, Fauconnier H and Toueg S. Stable leader election. Proceedings of the 15th International Symposium on Distributed Algorithms (DISC 01), Berlin Heidelberg. 2001. 108-122.
6 Al-Shaer E. A dynamic group management framework for large-scale distributed event monitoring. Proceedings of the 7th IFIP/IEEE International Symposium on Integrated Network Management (IM 01), Seattle W A, 2001. 565-578.
7 Othmar kyas, Network Troubleshooting. New York: Agilent Technologies, 2001
8 Jacobson V, Nichols K, Poduri K. An Expedited Forwarding PHB. IETF Internet RFC 2598, 1999
9 R. Haas, P. Droz, and B. Stiller. Autonomic service deployment in networks. IBM Systems Journal, 2003, 42(1): 1258-1267
10 Hong J W K, Kong J Y. Web-based intranet services and network management. IEEE Communications Magazine, 1997, 35(10):100-110.
11 Kahani M. Decentralized approaches for network management. ACM Computer Communication Review, 1997, 27(3): 36-47.
12 Barillaud F. Network management using internet technologies. 5th IFIP/IEEE International Symposium on Integrated Network Management (IM'97). San Diego: IEEE Press, 1997: 61-70.
13 Brunner M, Stadler R. Service management in multiparty active networks. IEEE Communications Magazine, March 2000:144-151.
14 Han S J, Lee J H. A mobility management using dynamic updates of domain name in mobile computing environment. International Conference on Internet Computing. Las Vegas: CSREA Press, 2001: 444-450.
15 Wang P, Li X M, Zhao H. A scalable hierarchical architecture for distributed network management. International Conference on Computer Networks and Mobile Computing[C]. IEEE Computer Society Press, 2001:21-26.
16 李千目,张宏,刘凤玉.智能化的网络故障诊断研究.国防科技报告.2003.7.25,编号:NLG-2002-076
17 戚涌,李千目,刘凤玉.基于BP神经网络的网络智能诊断系统.微电子学与计算机.2004,21(10):10-13
18 李千目,戚涌,张宏,刘凤玉.基于神经网络的网络故障诊断.计算机工程.2003,29(21):6-7,11.
19 杨云,徐永红,李千目,刘凤玉.一种QoS路由多目标遗传算法.通信学报,2004年,25(1):43-51
20 杨云,徐永红,李千目,刘凤玉.一种基于TCP/IP的QoS路由多目标遗传算法.模式识别与人工智能.2004年,17(2):232-238
21 沈俊,顾冠群,罗军舟.网络管理的研究和发展.计算机研究与发展.2002(10):1153—1167
22 李千目,戚勇,张宏,刘凤玉.基于粗糙集神经网络的网络故障诊断新方法.计算机研究与发展.2004年,41(10):1696-1702
23 E. N. Skoundrianos, S. G. Tzafestas. Fault Diagnosis via Local Neural Networks. Mathematics and Computers in Simulation, 2002, 60(3-5): 169-180
24 Rolf Iserman. Process Fault Detection Based on Modeling and Estimation and Knowledge Processing-Tutorial Paper. Automatic,1999, 29(4):815-835
25 R. Tagliaferri, A. Eleuteri, M. Meneganti, F. Barone. Fuzzy Min-Max Neural Network: from Classification to Regression. Soft Computing, 2001, 32(5):69-76.
26 Jagannathan R, Neumann P, Javitz H, Valdes A, Garvey T. A Real-Time Fault Diagnosis Expert System(FDES). Final Technical Report, Computer Science Laboratory, SRI International, Menlo Park, Calif., Feb. 2002
27 R. Tagliaferri, A. Eleuteri, M. Meneganti, E Barone. Fuzzy Min-Max Neural Network: from Classification to Regression. Soft Computing, 2001, 32(5):69-76.
28 K. ichiro Minami, H. Nakajima, and T. Toyoshima, Real-time discrimination of ventricular tachyarrhythmia with fourier-transform neural network. IEEE Trans. Biomed. Eng., 1999, 46(2):485-496
29 刘凤玉,李千目,衷宜.基于贝叶似分类的分布式网络故障诊断模型.南京理工大学学报,2003,27(5):546-550
30 Zhang WX, Mi JS, et al. Knowledge reduction in inconsistent information systems. Chinese Journal of Computer. 2003, 26(1): 12-18
31 Veres A, Boda M. The chaotic nature of TCP congestion control. In: Proc INFOCOM2000, Tel Aviv, Israel, CA: IEEE Computer Society 2000
32 ChenDan, HeHua-Can, WangHui. A new t-norm and its application in fuzzy control. In: Proc WCICIA'2000, Hefei, China, 2000. 1284-1289
33 Yager R. OWA neurons: A new class of fuzzy neurons. In: Proc IEEE-FUZZ, 1992. 2316-2340
34 Glorennec Pierre-Yves. Neuro-fuzzy logic. In: ProcIEEE-FUZZ, 1996. 512-518
35 Witold Pedrycz. Fuzzy neural networks and neuro computations. Fuzzy Sets and Systems. 1992, 56(1):1-28
36 Witold Pedrycz. Logic-based neurons: Extensions, uncertainty representation and development of fuzzy controllers. Fuzzy Sets and Systems, 1994, 66(1): 251-266
37 Bailey S A, Chen Ye-Hwa. A two layerd network using the OR/AND neuron. In: Proc IEEE-FUZZ, 1998. 1566-1571
38 陈丹,何华灿,王晖.一种新的基于弱T范数簇的神经元模型.计算机学报.2001,24(10):1115-1120
39 Averkin A N. Decision making based on multivalued logic and fuzzy logic, architectures for semiotic modeling and situation analysis in large complex systems. In: Proc ISIC Workshop, Monterey, 1995. 871-875
40 He Hua-Can et al. Generalized logic in experience thinking. Science in China(E), 1996, 39(3): 225-234
41 Buckley J J, Siler W. A new t-norm. Fuzzy Sets and Systems, 1998, 16(1):283-290
42 Christoph L, Schuba, Ivan V, Krsul. Analysis of denial of service attack on TCP. Proceedings of the IEEE Computer Society Symposium on Research in Security and Privacy 2000
43 晏蒲柳,夏德麟,郭成城.计算机网络智能故障诊断知识库构造方法.模式识别与人工智能,2000.13(2)142—144
44 C-C Lo. S-H Chen. A scheduling based event correlation scheme for fault identification in communications network. Computer Communications. 1999. 22(5):432-438
45 R. D. Gardner. d. A. Harle. Pattern discovery and specification techniques for alarm correlation. Proceedings of Network Operations and Management Symposium 1998(NOM'98). New Orleans. Feb. 1998. Vol. 3:713-722
46 R. Sasisekaran. V. Seshadri. S. M. Weiss. Data mining and forecasting in large scale telecommunication network[J]. IEEE Expert. 1996(2):37-43
47 W. Klosgen. Efficient discovery of interesting statements in data based[J]. Journal of Intelligent Information Systems. 1995(4):53-69
48 Wang Xinmiao. Huang Tianxi. Yan. Puliu. Knowledge Discovery from communication network alarm databases[J]. Wuhan University Journal of Natural Sciences. 2000. 5(2). 194-198
49 Deri L, Ban B. Static vs Dynamic CMIP/SNMP Network Management Using CORBA. Proc IS & N'97, Como, Italy, May 1997:329-337
50 Feit S. SNMP: A Guide to Network Management. New York: McGraw-Hill, 1994
51 Z. Pawlak. Rough sets and their application. Microcomputer Application. 1994, 13(2):71-75.
52 S. S. Y. Lau. Image segmentation based on the indiscernibility relation. Rough sets, Fyzzy sets and Knowledge discovery. 1994, 22(7):395-404.
53 Z. M. Wojcik. Intelligent image filtering using rough sets. Rough sets, Fuzzy sets and Knowledge discovery. 1994, 16(5):337-386.
54 George Bolt. Investigating Fault Tolerance Artificial Neural Networks. Advanced Computer Architecture Group, Department of Computer Science, University of York, Heslington, York, Y01 5DD, U. K, March 1991
55 R. Rengaswamy, V. Venkatasubramanian. A fast training neural network architecture and it's updation for incipient fault detection and diagnosis, Computers and Chemical Engineering, 2000., 24(2), 431-437
56 David Wetherall, Ulana Legedza, John Guttag. ANTS: A toolkit for building and dynamically deploying network protocols. IEEE Networking, 1998, 12(3): 12-20
57 Dasgupta D. Immunity-based Intrusion Detection System: A General Framework. In 22nd National Information System Security Conference, 18～21 Oct. 1999, Arlington, VA, USA(Gaithersburg, MD, USA, 1999), NIST, pp. 147～60 vol. 1
58 Tolle J, Niggermann O. Supporting Intrusion Detection by Graph Clustering and Graph Drawing. Lecture Notes in Computer Science 1907(200). In Recent Advances In Intrusion Detection(RAID) Workshop, 2000
59 Mukkamala S, Janoski G, Sung A. Intrusion Detection Using Neural Networks And Support Vector Machines. In 2002 International Joint Conference on Neural Networks (IJCNN), 12～17 May 2002, Honolulu, HI, USA (Piscataway, NJ, USA, 2002), vol.2, IEEE, pp. 1702～1707.
60 D Randall Wilson, Tony R Martinez. Improved Heterogeneous Distance Functions. Journal of Artificial Intelligence Research, 1997, 6(1): 1～34
61 Srinivas Mukkamala, Andrew H. Sung. Identifying Significant Feature for Network Forensic Analysis Using Artificial Intelligent Techniques[J]. Internation Journal of Digital Evidence, Winter 2003, Volume 1, Issue4
62 K. R. Muller, S. Mika, G. Ratsch, K. Tsuda, and B. Scholkopf. An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks, 2001, 12(2): 181-201
63 Roy A Maxion, Frank E Feather. A case study of Ethernet anomalies in a distributed computing environment. IEEE Transactions on Reliability, 1999, 39 (4): 142-146
64 Polly Huang, Anja Feldmann. A nonintrusive, wavelet—based approach to detecting network performance problems. ACM SIGCOMM Internet measurement workshop 2001, San Francisco.
65 Paul Barford and David Plonka. Characteristics of network traffic flow anomalies. In Proceeding of the ACM SIGCOMM Internet Measurement Workshop, 2001
66 Rajesh Talpade. Traffic-based network monitoring framework for anomaly detection. Proceeding of the 4 IEEE symposium on computer and communication, July, 1999, Egypt.
67 Lawerence Ho and Symeon Papavassiliou. Network and service anomaly detection in multi-service transaction—based electronic commerce wide area networks. Proceeding of the 4 IEEE symposium on computer and communication, July, 1999, Egypt.
68 Vladimir N Vapnik.统计学习理论的本质[M].张学工译.北京:清华大学出版社,2000
69 D Randall Wilson, Tony R Martinez. Improved Heterogeneous Distance Functions. Journal of Artificial Intelligence Research, 1997, 6(1): 1-34
70 Srinivas Mukkamala, Andrew H. Sung. Identifying Significant Feature for Network Forensic Analysis Using Artificial Intelligent Techniques. Internation Journal of Digital Evidence, Winter 2003, Volume 1, Issue4
71 Asa Ben-Hur, David Horn, Hava T. Siegelmann. Support Vector Clustering. Journal of Machine Learning Research, 2001(2): 125-137
72 DARPA, MA (USA): Lincoln Laboratory, Massachusetts Institute of technology. http://www.11.mit.edu/IST/ideval/index.html
73 KDD Cup 1999 Data. Irvine, CA(USA), Information and Computer Science, University of California, Irivine http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
74 Othmar Kyas. Network Troubleshooting. Berlin: Agilrnt Technologies, 2002.
75 张军,李宏,李忠孝等.一种新的自组织时分多址甚高频数据链隐藏终端分析方法.电子学报.2001.29(12):258-263
76 葛彤,冯正平,朱继懋.分段重构控制策略.自动化学报.2000.26(6):431-436
77 钱方,贾焰,黄杰等.提高冗余服务性能的动态容错算法.软件学报.2001.12(6):541-546
78 Patterson, D. A., A. Brown, P. Broadwell, G. etc. Recovery-Oriented Computing (ROC): Motivation, Definition, Techniques, and Case Studies. UC Berkeley Computer Science Technical Report UCB//CSD-02-1175, March 15, 2002: 571-574.
79 Brown, A. and D. A. Patterson. Embracing Failure: A Case for Recovery-Oriented Computing (ROC). 2001 High Performance Transaction Processing Symposium, Asilomar, CA, October 2001: 854-859.
80 Oppenheimer, D., Archana Ganapathi, and David A. Patterson. Why do Internet services fail, and what can be done about it? 4th USENIX Symposium on Internet Technologies and Systems (USITS'03), March 2003:125-128.
81 K. Vaidyanathan and Kishor S. Trivedi, Workload-Based Estimation of Resource Exhaustion in Software Systems, Dept. of Electrical & Computer Engineering, Duke University, 1999:213-217.
82 R. Haas, P. Droz, and B. Stiller. Autonomic service deployment in networks. IBM Systems Journal, 2003, 42 (1): 82-87.
83 Castelli V., et al. Proactive Management of Software Aging. IBM JRD. 2001, 45(2): 311-332.
84 Garg S., Puliafito A., Trivedi K. S. Analysis of Software Rejuvenation using Markov Regenerative Stochastic Petri Net. In: Proc. of ISSRE 1995, Toulouse, France, 1995: 158-132.
85 Dohi T., Goseva-Popstojanova K., Trivedi K. S. Statistical Non-parametric Algorithms to Estimate the Optimal Software Rejuvenation Schedule. In: Proc. 2000 Pacific Rim International Symposium on Dependable Computing (PRDC 2000), Los Angeles, CA, 2000:582-588
86 Dohi T., K. Goseva-Popstojanova, K. S. Trivedi. Analysis of Software Cost Models with Rejuvenation. In: Proc. 5th IEEE International Symposium on High Assurance Systems Engineering (HASE 2000), Albuquerque, New Mexico, 2000:465-470
87 Pfening S., et al. Optimal Software Rejuvenation for Tolerating Soft Failures. Performance Evaluation. 1996(27/28): 491-506
88 Garg S., et al. Analysis of Preventive Maintenance in Transactions Based Software Systems. IEEE Trans. on Computers. 1998, 47(1): 96-107.
89 Garg S., et al. On the analysis of software rejuvenation policies. In: Proc. of the 12th Annual Conf. on Computer Assurance, 1997: 88-96.
90 Vaidyanathan K., et al. Analysis and implementation of software rejuvenation in cluster systems. In: Proceedings of the Joint International Conference on Measurement and Modeling of Computer System, ACM SIGMETRICS 2001/PERFORMANCE 2001, Cambridge, MA, 2001: 62-71.
91 S. Chen and K. Nahrstedt. On Finding Multi-Constrained Paths. International Conference on Communications (ICC'98),. IEEE, 1998:874-879
92 T. Korkmaz and M. Krunz. A Randomized Algorithm for Finding a Path Subject to Multiple QoS Constrains. Computer Networks. Amsterdam, Netherlands. 1999.
93 Shaikh, A., Rexford, J., Shin, K. G. Evaluating the impact of stale link state on