L. Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In IM'93 [19], pp. 671--681.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of the underlying system and, for small systems, may provide a powerful tool for eliminating the least likely hypotheses. The downsides of rule based systems include the inability to learn from experience, inability to deal with unseen problems, and difficulty in updating the system knowledge [31]. Rule based systems are difficult to maintain because the rules frequently contain hard coded network configuration information. Although approaches have been proposed to automatically derive correlation rules based on the statistical analysis of alarm databases [29] it is still necessary to ....

....model based approaches have the potential to solve novel problems and their knowledge may be organized in an expandable, upgradeable and modular fashion. However, the models may be difficult to obtain and keep up to date, and their manipulation is computationally complex. Case based systems [31] make their decisions based on experience and past situations. They try to acquire relevant knowledge of past cases and previously used solutions to propose solutions for new problems. If a direct match for an open problem is found in the database, the solution from the matching case is returned. ....

L. Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In IM'93 [19], pp. 671--681.

.... and system bottleneck prediction Support for uncertainty and lost events 13 6 Related work In the past various event correlation techniques were proposed including rule based systems [18, 26] model based reasoning systems [13, 21] model traversing techniques [14, 15] case based systems [17], fault propagation models [9, 16] and the code book approach [27] Rule based systems are composed of rules (productions) of the form conclusion if condition. The condition part is a logical combination of propositions about the current set of received alarms and the system state [18, 26] the ....

....during correlation. Yemanja allows the time window to be specified separately for every event layer, which is based on the latency of the monitoring tool active in the particular layer. Testing and database lookup is easily incorporated into Yemanja s correlation scenarios. Case based systems [17] try to use experience gathered through past problem solving to find a solution for the new problem. The solution for the new problem is adapted form the solution of the closest matching problem solved in 14 the past. Case based systems are able to learn correlation patterns and are resilient to ....

L. Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In H. G. Hegering and Y. Yemini, editors, Integrated Network Management III, pages 671--681, San Francisco, CA, Apr. 1993. North-Holland.

.... faults three faults four faults Figure 9: Fault localization time with Algorithm 7 Related work In the past, various event correlation techniques were proposed including rule based systems [22, 34] model based reasoning systems [15, 24] model traversing techniques [16] case based systems [21], fault propagation models [12, 18] and the codebook approach [35] Most of the above approaches utilize deterministic reasoning. This paper focuses on non deterministic event correlation which is unavoidable in fault diagnosis related to quality of service degradation particularly in upper ....

L. Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In Hegering and Yemini [14], pp. 671--681.

.... literature are (1) incomplete knowledge about the existence of causal relationships between network events [13] 2) possibility of incomplete symptom observations or spurious symptoms [9, 25] 3) system adaptability to configuration changes [1] 4) ability to learn event correlation patterns [14], and (5) temporal event correlation [15] Most of these techniques rely on the assumption that the existence of multiple simultaneous faults is negligible. Relationships between network objects are often represented using a dependency graph [8, 12, 13] Dependency graph is a directed acyclic ....

L. Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In IFIP/IEEE Intg'ed Network Management III, pp. 671--681, San Francisco, CA, 1993. North-Holland.

....yielding high accuracy even for approximate probability input data. IX. RELATED WORK In the past, various event correlation techniques were proposed including rule based systems [22] 23] model based reasoning systems [24] 25] model traversing techniques [26] case based systems [27], fault propagation models [6] 7] and 0 7803 7476 2 02 17.00 (c) 2002 IEEE. 0.55 0.6 0.65 0.7 0.75 0.8 0.85 0.9 0.95 1 rate Network size exact three confidence levels two confidence levels one confidence level Fig. 10. Detection rate of Algorithm 1 with exact and approximate ....

L. Lewis, "A case-based reasoning approach to the resolution of faults in communications networks," In Hegering and Yemini [33], pp. 671--681.

.... frequent episode from large alarm database, which was applied to the TASA system [4] Weiss and Hirsh [9] studied how to predict the rare event from alarm database by genetic algorithms and presented the timeweaver algorithm, which was applied to the ANSWER system [10] Although many methods [1,2,9,20,21,22,23] have been proposed to analyze the alarm correlation, few methods took account of the effects of noise data contained in alarm database. In order to discover alarm correlation rules from alarm database containing noise data, we define two parameters Win freq and Win add as the measures of ....

L. Lewis, A Case-Based Reasoning Approach to resolution of faults in communication networks, In Integrated Network Management, III, 671-682, Elsevier Science Publisher B.V., Amsterdam., 1993.

.... approach to problem solving and learning that has received considerable attention over the last few years Kolodner (1993) Aamodt Plaza (1994) Applications of CBR include many domains, for example, meteorology, medicine, and telecommunications, Jones Roydhouse (1995) Schuster et al. 1997) Lewis (1993). CBR relies on the assumption that reminding and adaptation play a crucial role in human expert problem solving. Reminding means that facing a new problem situation domain experts very often get, or try to get, reminded of similar situations that have been solved in the past. Whenever such prior ....

Lewis, L., 1993, "A Case-based Reasoning Approach to the Resolution of Faults in Communications Networks", IFIP Trans. C-Comms Systems, Vol.12, pp. 671-682.

....object management , common database etc. 4] ffl Management Applications These are developed by multiple vendors and can work on the above platforms to realize the management solutions (e.g. troubleticketing, inventory etc) mostly based on object oriented software technology [5] [6]. 2.2 Integrated Management Application Framework While this management model adequately describes the Instrumentation aspect of a network management framework, it is necessary to use richer modeling techniques to tackle the complexity of distributed heterogeneous management applications. The ....

L. Lewis. "A Case-based Reasoning Approach to the Resolution of Faults in Communication Networks". In "Proc. 3rd International Symposium on Integrated Network Management(ISINM `93), April 1993.

....done to apply the approach and section 5 gives an overview of the prototype developed so far. Finally, section 6 summarizes the paper and gives an outlook to further work. 2 Existing Approaches 2. 1 Overview of Existing Approaches to Event Correlation One group of approaches developed so far ( Lew93] KYY 95] HKH 96] starts with a set of cases (codes, episodes) containing symptom cause pairs and does some reasoning on them. When receiving events such a case based event correlator regards them as a set of symptoms. It searches through its case database for cases with similar ....

L. Lewis. A case--based reasoning approach to the resolution of faults in communication networks. In Hegering and Yemini [HY93], pages 671--682.

....here as reliable. To find out which agents are reliable or not, one must diagnose the Intelligent Agents Network. Many different diagnosis models exist, for instance: model based diagnosis [11] alarm correlation [5, 17] probabilistic methods [12] expert systems and case based reasoning [6, 10, 18] and the System Level Diagnosis (SLD) model. Due to the specific characteristics of the Intelligent Agent system case, the SLD was chosen to update continuously the knowledge of the reliability degree of the Intelligent Agent system. The contents of this article are the following. The choice of ....

L. Lewis. A case-based reasoning approach to the resolution of faults in communication networks. In Proceedings of the IFIP TC6/WG6.6 Third International Sysposium on Integrated Network Management, pages 671--682. Elsevier Science Publishers, 1993.

....its robustness [Lewis and Dreo, 1993] since the system may lack the alternatives in many common situations in an integrated network management environment. In areas which are quickly modified, as is the case of telecommunications networks, rule based systems tend to become quickly obsolete [Lewis, 1993]. 2.2.2 Fuzzy Logic Due to the complexity of the managed networks, it is not always possible to build precise models of these networks, in which all the situations in which the occurrence of a given set of alarms indicates a fault on a given equipment are made evident. The knowledge of the cause ....

....with the remainder of Pacific Bell s network management system and the construction of the infrastructure for the expert system lasted three years. Additional developments still had to be made to enable the system to carry out event correlation and fault diagnosis. 44 2.4. 13 CRITTER CRITTER [Lewis, 1993] is a trouble ticket system which utilizes case based reasoning (CBR, cf. item 2.2.8) for the diagnosis of network faults. Here, each closed trouble ticket constitutes one case. One trouble ticket database is a case library. The CBR component of the CRITTER system provides mechanisms to retrieve a ....

Lundy Lewis. A case-based reasoning approach to the resolution of faults in communications networks. In IFIP International Symposium on Integrated Network Management, III (ISINM'93) [1993], pages 671--682.

.... Examples from the first group are Tivoli EnterpriseConsole (Prolog) and Micromuse NetCool (SQL) The latter group includes HP Event Correlation Services (Correlation Circuits) NerveCenter (Behaviour Models) and Smarts InCharge (MODEL) The second group of approaches developed so far including [Lew93] KYY 95] HKH 96] WTJ 97] starts with a set of cases (codes, episodes) and does some reasoning on it. These cases define a mapping of sets of input events to their probable cause. The outcome of these approaches obviously heavily depends on the quality of the case database as ....

L. Lewis. A case--based reasoning approach to the resolution of faults in communication networks. In Hegering and Yemini [HY93], pages 671--682.

....recovery actions (corrective action planning) are taken to restore the system to an acceptable state. This process is referred to as policy driven fault management. Much of the work in this area is currently in its preliminary stages. While some successes have been realized so far in this work [2, 5, 6, 7, 9], much remains to be done: ffl Most of the work used network management services to provide information about the status of network devices (i.e. nodes, routers, etc) by occasionally polling these devices to see if they are still alive. This is usually done by using SNMP or CMIP [11] agents. To ....

L. Lewis. A Case-Based Reasoning Approach to the Resolution of Faults in Communications Networks. Integrated Network Management III, Elsevier Science Publishers B.V. (North-Holland: 1993.

....ones. Once solved, the cases are learned by being added to the case repository. The prototype system for network traffic management described in (Goyal 1991) is one example of how a case based reasoner can recognize, treat, and monitor traffic routing problems. Another example is presented in (Lewis 1993), where the diagnosis functionality is built on top of a trouble ticket system. The critical factors in CBR, however, are the similarity metrics based on which the retrieval of cases similar to the current one is possible, and the adaptation methods that ensure the transformation of the current ....

Lewis, L. (1993) A case-based reasoning approach to the resolution of faults in communication networks. In Integrated Network Management, III, 671-682. Elsevier Science Publishers B.V., Amsterdam.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC