FAULT DIAGNOSIS FOR LOCAL AREA NETWORK ENVIRONMENTS

2015 SAI Intelligent Systems Conference (IntelliSys), 2015

The dynamic and distributed nature of telecommunication networks makes complex the design of model-based approaches for network fault diagnosis. Most model-based approaches assume the prior existence of the model which is reduced to a static image of the network. Such models become rapidly obsolete when the network changes. We propose in this paper a 3-layered self-reconfigurable generic model of fault diagnosis in telecommunication networks. The Layer 1 of the model is an undirected graph which models the network topology. Network behavior, also called fault propagation, is modeled in Layer 2 using a set of directed acyclic graphs interconnected via the Layer 1. We handle uncertainties of fault propagation by quantifying strengths of dependencies between Layer 2 nodes with conditional probability distributions estimated from network generated data. Layer 3 is the junction tree representation of the loopy obtained Layer 2 Bayesian networks. The junction tree is the diagnosis computational layer since exact inference algorithms fail on loopy bayesian networks. This generic model embeds intelligent self-reconfiguration capabilities in order to track some changes in network topology and network behavior. These self-reconfiguration capabilities are highlighted through some example scenarios that we describe. We apply this 3-layered generic model to carry out active self-diagnosis of the GPON-FTTH access network. We present and analyze some experimental diagnosis results carried out by running a Python implementation of the generic model.

SRI International, 1996

Traditionally, network management activities, such as fault management, have been performed with direct human involvement. However, these activities are becoming more demanding and data intensive, due to the heterogeneous nature and increasing size of networks today. ...

IEEE Internet Computing, 1998

s the Internet becomes a critical component of our society, a key challenge is to maintain network availability and reliability. The increasing number of networks is making downtime more costly. Network management tools and techniques must therefore become better at detecting and identifying network faults. Fault management is no easy task, however. Fundamental changes to the network occur much more frequently as demand grows and components and applications are developed in an open environment. Although mixing and matching hardware and software from different vendors supports customization and use of the latest technologies, it also increases the risk of faults and other problems. 1 Current fault management implementations generally rely on the expertise of a human network manager, which is translated to a set of rules and then to threshold levels on the measurement variables being collected. As networks become more complex and changes occur more frequently, the human network manager will find it hard to maintain a sufficient level of expertise on a particular network's behavior. Fault management research has covered approaches such as expert systems, finite state machines, advanced database techniques, and probabilistic methods. Aurel Lazar and colleagues give a good review of communication network fault detection and identification. 2 The drawback to all these approaches is that they require a specification of the faults to be detected, and it is not feasible to specify all possible faults. Also, changes in network configuration, applications, and traffic can alter the type and nature of possible faults, which makes modeling them impractical in many cases.

2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2010

To reduce the loads imposed on network administrators, we have proposed AIR-NMS, which is a network management support system (NMS) based on Active Information Resource (AIR). In AIR-NMS, various information resources (e.g., state information of a network, practical knowledge of network management) are combined with software agents which have the knowledge and functions for supporting the utilization of the resources, and thus individual resources are given activities as AIRs. Through the organization and cooperation of AIRs, AIR-NMS provides the administrators with practical measures against a wide range of network faults. To make AIR-NMS fit for practical use, this paper proposes a method for achieving the effective installation and utilization of the network management knowledge needed in AIR-NMS.

2002

Future military communication networks will have a mixture of backbone terrestrial, satellite and wireless terrestrial networks. The speeds of these networks vary and they are very heterogeneous. As networks become faster, it is not enough to do reactive fault management. Our approach combines proactive and reactive fault management . Proactive fault management is implemented by dynamic and adaptive routing. Reactive fault management is implemented by a combination of a neural network and an expert system. The system has been developed for the X.25 protocol. Several fault scenarios were modeled and included in the study: reduced switch capacity, increased packet generation rate of a certain application, disabled switch in the X.25 cloud, disabled links. We also modeled o c currence of alarms including severity of the problem, location of the event and a threshold. To detect and identify faults we use both numerical data associated with the performance objects attributes in the MIB as well as SNMP traps alarms. Simulation experiments have been performed i n o r der to understand the convergence of the algorithms, the training of the neural networks involved and the G2 NeurOn-Line software environment and MIB design.

Journal of Network and Systems Management

Carrying out self-diagnosis of telecommunication networks requires an understanding of the phenomenon of fault propagation on these networks. This understanding makes it possible to acquire relevant knowledge in order to automatically solve the problem of reverse fault propagation. Two main types of methods can be used to understand fault propagation in order to guess or approximate as much as possible the root causes of observed alarms. Expert systems formulate laws or rules that best describe the phenomenon. Artificial intelligence methods consider that a phenomenon is understood if it can be reproduced by modeling. We propose in this paper, a generic probabilistic modeling method which facilitates fault propagation modeling on large-scale telecommunication networks. A Bayesian network (BN) model of fault propagation on GPON-FTTH (Gigabit-capable Passive Optical Network-Fiber To The Home) access network is designed according to the generic model. GPON-FTTH network skills are used to build structure and approximatively determine parameters of the BN model so-called expert BN model of the GPON-FTTH network. This BN model is confronted with reality by carrying out self-diagnosis of real malfunctions encountered on a commercial GPON-FTTH network. Obtained self-diagnosis results are very satisfying and we show how and why these results of the probabilistic model are more consistent with 1 the behaviour of the GPON-FTTH network, and more reasonable on a representative sample of diagnosis cases, than a rule-based expert system. With the main goal to improve diagnostic performances of the BN model, we study and apply EM (Expectation Maximization) algorithm in order to automatically fine-tune parameters of the BN model from real data generated by a commercial GPON-FTTH network. We show that the new BN model with optimized parameters reasonably improves self-diagnosis previously carried out by the expert Bayesian network model of the GPON-FTTH access network.

2008

As the complexity of networked systems increases, we need mechanisms to automatically detect failures in the network and diagnose the cause of such failures. To realize true self-healing networks, we also need mechanisms to fix these failures and ensure service availability by providing alternatives when a failure is detected. In this paper, we address the detection and diagnosis of network failures. We introduce DYSWIS ("Do you see what I see") which observes the system from multiple points in the network. Our system consists of detection nodes and diagnosis nodes. Detection nodes detect failures by passive traffic monitoring and active probing. Diagnosis nodes determine the cause of failures using historical information about similar failures and by performing active tests. They are based on a rule engine and represent network dependency relationship encoded as rules. We present our prototype system which considers network components present in a VoIP network and show the feasibility of our solution.

IEEE Transactions on Automation Science and Engineering, 2015

Fault diagnosis is a critical task for operators in the context of e-TOM (enhanced Telecom Operations Map) assurance process. Its purpose is to reduce network maintenance costs and to improve availability, reliability and performance of network services. Although necessary, this operation is complex and requires significant involvement of human expertise. The study of the fundamental properties of fault diagnosis shows that the diagnosis process complexity needs to be addressed using more intelligent and efficient approaches. In this paper, we present a hybrid approach that combines Bayesian networks and case-based reasoning in order to overcome the usual limits of fault diagnosis techniques and to reduce human intervention in this process. The proposed mechanism allows the identification of the root cause with a finer precision and a higher reliability. At the same time, it helps to reduce computation time while taking into account the network dynamicity. Furthermore, a study case is presented to show the feasibility and performance of the proposed approach based on a real-world use case: a virtual private network topology. Note to Practitioners-This paper was motivated by the problem of self-diagnosis in communication networks. The root cause identification process used currently consists of testing all of the network metrics without any prior knowledge of the dependency model. This process ignores the causal relationships which may exist between the network components. This paper suggests an approach based on prior modeling dependencies between metrics that compose a network (i.e., packet loss or jitter). The dependency model is achieved through a graph theory technique known as "Bayesian Network." Upon the detection of a failure, the approach considers only the most relevant metrics for the detected fault. The diagnosis consists of inferring the root cause using an algorithm based on the combination of Bayesian networks and case-based reasoning techniques. For the evaluation, observations collected from concrete network monitoring were used. This evaluation shows the efficiency of the proposed approach in terms of automation, speed, accuracy and reliability.

8th IFIP/IEEE International …, 1997

In this paper, we describe an application scenario where distributed artificial intelligence is needed for performance monitoring and fault diagnosis in a telecommunications network. We then describe the prototype agent-based system that we have developed for this task. Based on this application scenario, we highlight the key issues that have affected the design of our system, in terms of the communication language used between agents, and the strategies that agents use to coordinate their actions.