Autonomous Fault Management Research Articles

Rogowski coil-based autonomous fault management strategy using Karen Bell Transformation for earthed active distribution networks

This paper introduces fault type identification, fault section selection, and fault phase selectivity using a Karen Bell Transformation matrix in earthed distribution grids coupled with Doubly Fed Induction Generator (DFIG). Rogowski Coil’s (RC) model is estimated using a system identification toolbox to obtain the precise terminal voltage. This model is calculated and verified using experimental results for the RC’s primary input current and output voltage. Then, the estimated voltage relies on the current signals in the measuring point. The transient slope of the ground and aerial modes voltages is extracted during the fault to classify the fault type, discriminate the fault section and identify the faulted phase in every cycle. Further, earth faults are detected using ground and phase faults using aerial modes. The relative polarity of the front slopes at the terminals of each section created by the fault voltage is extracted to perform faulty section discrimination. The value of aerial modes is used to identify the defective phase selectivity. The overall protection selectivity function’s integration procedure with modified autonomous control is proposed for earthed distribution systems. The Transient Selectivity Function (TSF) was presented in unearthed and compensated grids in the literature. After estimating the RC voltage output at each agent, the discrete Fourier transform (DFT) phasor extraction is done. Different standard fault cases and system conditions are investigated to evaluate the proposed scheme’s behavior. Simulation results are designed using the ATP-EMTP program. The simulation results obtained validate the effectiveness of the scheme proposed in this work.

An Open Approach to Autonomous Ran Fault Management

In this article, we propose a multi-stage AI-based framework called “open Fault Management” or “openFM,” for end-to-end autonomous fault management of the open radio access network (open RAN) that is also applicable to 5G and beyond 5G next-generation networks. Open RAN is the subsequent stage of evolution for the next-generation RAN. A unified vendor-independent fault management system architecture that can be seamlessly integrated with open RAN and other parallel evolving networks is outlined in this article. An optimized combination of classical machine learning and artificial neural network (ANN)-based deep learning is implemented and analyzed in different stages of the autonomous fault management process, and their accuracy and various other metrics of performance are presented. We are able to achieve a classification accuracy of 98 percent for the prediction of false alarms and 96 percent for the prediction of alarm-specific suggestive actions. The Random-Forest-based classifier outperforms five other classifiers by being consistently accurate with a precision rate of more than 97 percent and a recall score of more than 99 percent, also with a shorter training time.

Two-Phase Defect Detection Using Clustering and Classification Methods

Autonomous fault management of network and distributed systems is a challenging research problem and attracts many research activities. Solving this problem heavily depends on expertise knowledge and supporting tools for monitoring and detecting defects automatically. Recent research activities have focused on machine learning techniques that scrutinize system output data for mining abnormal events and detecting defects. This paper proposes a two-phase defect detection for network and distributed systems using log messages clustering and classification. The approach takes advantage of K-means clustering method to obtain abnormal messages and random forest method to detect the relationship of the abnormal messages and the existing defects. Several experiments have evaluated the performance of this approach using the log message data of Hadoop Distributed File System (HDFS) and the bug report data of Bug Tracking System (BTS). Evaluation results have disclosed some remarks with lessons learned.

Modified autonomous fault management strategy for enhancing distribution network reliability

Modified autonomous fault management strategy for enhancing distribution network reliability

A semantic data lake framework for autonomous fault management in SDN environments

AbstractFault Management is a vital issue for any network operator since the beginning of the telecommunications era. As networks have become more and more complex, their management systems are crucial for any operator company. In this ecosystem, the Software‐Defined Networking (SDN) approach has appeared as a possible solution for different networking issues. The flexibility provided by SDN to the network management enables a great dynamism in the configuration of network devices. However, this feature introduces the cost of a potential increase in failures because every modification introduced on the control plane is a new possibility for failures to appear and cause a decrement of the quality for offered services. Because of the growing pace of the networks, the classical approach is not feasible to cope that dynamism. Increasing the number of human operators in charge of the fault management process would increase the operation cost dramatically. Thus, this paper presents an approach to apply machine learning over a big data framework for an autonomous fault management process in SDN networks. In this paper, we present a Semantic Data Lake framework for a self‐diagnosis service, which is deployed on top of an SDN management platform. Moreover, we have developed a prototype of the proposed service with different diagnosis models for SDN networks. Models and algorithms have been evaluated showing good results.

Transient selectivity for enhancing autonomous fault management in unearthed distribution networks with DFIG-based distributed generations

This paper proposes a method for identifying the faulty section in unearthed distribution networks connected with Doubly-Fed Induction Generator (DFIG)-based distributed generation. The proposed method depends on a dedicated transient-based selectivity function that is incorporated in an autonomous fault management procedure. Faulty section discrimination is performed by extracting the relative polarities of the front slopes at the terminals of each section generated by the fault current. The integration procedure of the protection selectivity function with the autonomous control is designed for the unearthed MV networks. Both earth and phase faults are considered in order to realize a broad, versatile and practical classification for such networks. Simulation cases are prepared using the ATP-EMTP package for testing purposes. The results corroborate the efficacy of the proposed method for classifying the faulty segment in distribution networks even for high impedance arcing faults as well as with considerable amounts of distributed wind turbines.

Design and Evaluation of Techniques for Resilience and Survivability of the Routing Node

This paper presents the final results achieved within the EFIPSANS project on the topic of resilience and survivability in autonomic networks. In particular, the outcome of the investigation of the following issues is presented: adaptive level of recovery, unified architecture for autonomic routing resilience, synergies between autonomic fault-management and resilience in self-managing networks, as well as network resilience through autonomic reroute mechanism enhanced with multi-path node-to-node cooperation. The described ideas are supported by exhaustive descriptions and analyses featuring extensive validation results aimed to prove the applicability of the proposed concepts.

A cognitive model‐based approach for autonomic fault management in OpenFlow networks

SUMMARYAutonomic network management is an approach to the management of complex networks and services that incorporates the detection, diagnosis and reconfiguration, as well as optimization, of their performance. A control loop is fundamental as it facilitates the capture of the current state of the networks and the reconfiguration of network elements without human intervention. For new networking architectures such as software‐defined networking and OpenFlow networks, in which the control plane is moved onto a centralized controller, an efficient control loop and decision making are more crucial. In this paper, we propose a cognitive control loop based on a cognitive model for efficient problem resolving and accurate decision making. In contrast to existing control loops, the proposed control loop provides reactive, deliberative and reflective loops for managing systems based on analysis of current status. In order to validate the proposed control loop, we applied it to fault management in OpenFlow networks and found that the protection mechanism provides fast recovery from single failures in OpenFlow networks, but it cannot cover multiple‐failure cases. We therefore also propose a fast flow setup (FFS) algorithm for our control loop to manage multiple‐failure scenarios. The proposed control loop adaptively uses protection and FFS based on analysis of failure situations. We evaluate the proposed control loop and the FFS algorithm by conducting failure recovery experiments and comparing its recovery time to those of existing methods. Copyright © 2013 John Wiley & Sons, Ltd.

RAFD: Resource-aware fault diagnosis system for home environment with smart devices

With recent advancement in technologies used at home, smart home environment allows various resources such as device, network, or content to be connected to one another. Their configurations are changed by dynamic bindings at any time. In this smart home environment, a minor problem in a resource can trigger serious failures in home network services by causing multiple faults to the related resources simultaneously. To solve this problem, it is essential to analyze the dependency between resources and also to diagnose home network faults autonomously. This paper proposes the effective fault diagnosis system based on resource relation map which is dynamically constructed by information convergence model of heterogeneous home resources. The proposed system provides the tracing method for finding the root cause of a fault using the resource relation map. The resource relation map represents the snapshot of home situations at the given time. The proposed fault diagnosis method allows building cost effective remote maintenance system with high availability and manageability by tracing the fault cause along the dependency between resources using graph-style resource relation map as if humans trace the cause of problem. In addition, it can contribute to realize an autonomic fault management system for smart home. In this paper, the prototype of the proposed system is implemented and evaluated for performance in accuracy and latency of fault diagnosis in a real environment. The experimental results show that the proposed system, especially with the suggested back tracing diagnosis system, yields remarkable performance for home network fault diagnosis.

Resource-aware smart home management system by constructing resource relation graph

With the advent of smart home devices including Smart TV or smart appliances, home becomes smarter. Smart home is a complex environment where heterogeneous smart devices and appliances are connected to each other to provide various smart services. As the home environments become smarter and more complex, the need for an effective managing mechanism with minimum user's intervention is growing. However, just only putting together all the individual information of each resource is not enough, since it is very hard to catch out overall home situation without the relation information between the managed resources. In this paper, we propose a resource-aware management system with hierarchical smart home resource model, using the home context information which defines the information convergence model of heterogeneous home resources and builds a home knowledge by constructing a resource relation graph. The proposed system can accelerate deployment of advanced future smart home service features such as context-aware dynamic service composition, autonomous fault management systems. In addition, it allows cost effective remote maintenance system with highly convenient manageability. We implemented the prototype system of our proposed architecture and evaluated the performance on the query response time of home resources and relations in a real environment. Results showed that it has acceptable performance for navigating or control of home information and excellent improvements in terms of relation based search. We anticipate that the proposed system will bring the huge benefits not only to the consumers, home network service providers but also to the home network maintenance companies in terms of ease of management, and diagnostic effectiveness.

Towards autonomic management for Cloud services based upon volunteered resources

SUMMARYMany research institutions and Universities own computational capacity that is not effectively utilized, thereby providing an opportunity for such institutions to use such capacity to offer Cloud services (to both internal and external users). However, the unreliability and unpredictability of these resources mean that their use in the context of a Service Level Agreement (SLA) is high risk, leading to a reduction in reputation as well as economic penalties in case of SLA violation. We propose a methodology that addresses the issues of unreliability and unpredictability such that Cloud software services could be hosted upon volunteered resources. To enable the harnessing of these resources we rely on autonomic fault management techniques that allow such systems to independently adapt the resources they use based upon their perception of individual resource reliability. Using our approach we were able to scale out the backend infrastructure of the Cloud service elastically (min 30thinspaces per worker), opportunistically and autonomically. We address two key questions in this article: can a campus volunteer infrastructure be used in Cloud provisioning? What measures are necessary in order to ensure reliability at the resource level? Copyright © 2011 John Wiley & Sons, Ltd.

Design and implementation of an adaptive middleware based on the universal middleware bridge for heterogeneous home networks

As home networks become more complex and dynamic, it is crucial to support seamless interoperability through automatic reconfiguration and robustness through the efficient handling of faults. This paper presents an adaptive middleware that provides an adaptive autonomic configuration for the heterogeneous home networks and an autonomous fault management that includes fault diagnosis and recovery from unexpected faults such as device plug-outs, network link failures, service failures, and other such incidents. The proposed adaptive middleware is based on the universal middleware bridge (UMB) to guarantee interoperability and robustness in the middleware layer appropriate to heterogeneous home networks.

An error messages clustering-based fault management framework for adaptive home network middleware

This paper proposes an autonomous fault management framework consists of efficient fault detection, analysis and fault recovery based on clustering error messages. Most home network middlewares provide simple rule-based fault processing mechanisms optimized only to handle error messages individually. The proposed architecture focuses on detecting and analyzing error messages generated by identical faults as collectively as possible. For this, three relation graphs are used to decide the fault range and to find error messages. Message filters are also used to omit analyzing the previously found faults. Predefined fault recovery rules are used to handling the analyzed results and reconfigure home networks automatically. The proposed framework is implemented on an adaptive home network middleware based on the Universal Middleware Bridge (UMB) that provides adaptive autonomic configuration for the heterogeneous home networks.

UniFAFF: a unified framework for implementing autonomic fault management and failure detection for self‐managing networks

AbstractToday's network management, as known within the Fault, Configuration, Accounting, Performance, Security (FCAPS) management framework, is moving towards the definition and implementation of ‘self‐managing’ network functions, with the aim of eliminating or drastically reducing human intervention in some of the complex aspects or daunting tasks of network management. The fault management plane of the FCAPS framework deals with the following functions: fault detection, fault diagnosis, localization or isolation, and fault removal. Task automation is at the very heart of self‐managing (autonomic) nodes and networks, meaning that all functions and processes related to fault management must be automated as much as possible within the functionalities of self‐managing (autonomic) nodes and networks, in order for us to talk about autonomic fault management. At this point in time there are projects calling for implementing new network architectures that are flexible to support on‐demand functional composition for context‐ or situation‐aware networking. A number of such projects have started, under the umbrella of the so‐called clean‐slate network designs. Therefore, this calls for open frameworks for implementing self‐managing (autonomic) functions across each of the traditional FCAPS management planes. This paper presents a unified framework for implementing autonomic fault management and failure detection for self‐managing networks, a framework we are calling UniFAFF. Copyright © 2008 John Wiley & Sons, Ltd.

The Experience With the EURECA On-Board Autonomous Fault Management Functions

EURECA, the EUropean REtrievable CArrier was launched in July 1992 and retrieved in June 1993. It is the largest ESA spacecraft ever launched, and the first one designed to be launched and retrieved by the NASA Space Shuttle. The experience gained during the first EURECA mission in dealing with the various failures that occurred is described. Emphasis is given to the actual performance of the autonomous fault management functions, their success or failure in carrying out their task, their impact on mission operations and ground control. Suggestions for potential improvement in the concept of on-board failure handling are given.