Network Fault Research Articles

Stochastic analysis of delayed reporting of faults in a computer network using copula distribution

Stochastic analysis of delayed reporting of faults in a computer network using copula distribution

Improved Bayesian network-based for fault diagnosis of air conditioner system

To solve the problem of fault prediction and diagnosis of household air conditioning, an improved Bayesian network (BN) fault diagnosis model is proposed. Firstly, the orthogonal defect classification (ODC) is used to make statistics and analysis of air conditioning fault data, and the structure of BN fault diagnosis model is built based on the analysis results. Then, genetic algorithm (GA) is used to optimize the conditional probability of network nodes and determine the network parameters. Finally, the cooling and heating failure data of household air conditioning were taken as an example to diagnose. Compared with the traditional BN model, the accuracy of fault diagnosis increases from 81.13% to 92.83%, which verifies the effectiveness of the model.

Optimization of IoT-Fog Network Path and fault Tolerance in Fog Computing based Environment

Increasing use of smart devices and smart applications have attracted many Fog-based services like pervasive health monitoring, distributed computing, etc to improve the real-life experience of the end users. Here, various sensor-based devices gathers data and stores them in the cloud servers to provide real time information. In this context, Fog Computing provides the edge-based computation platform to the end-users and neighbouring devices to perform communication, sharing, etc. In this manuscript, we have proposed a proficient scheme that boosts the common performance by identifying the best cost path and reduces the packet transmission time by selecting the nearest neighbour amongst the fog node in the fog supporting scenario. The projected scheme also ensures live server fault by replicating server activities. The obtained results for the proposed scheme in the simulation setup of fog based environment represents the reduced network bandwidth 618020 Mbps with reduced cost $81900 USD along with the higher throughput up to 93% of the device in the environment.

Fault Diagnosis for Power Converters Based on Incremental Learning

In practical fault diagnosis, the monitoring fault data is accumulated incrementally, it is necessary to detect the newly added fault data. To this end, this paper proposed a broad residual network (BRES) fault diagnosis method with incremental learning capability. Firstly, the deep feature representation of the raw data is obtained by the residual network, and the obtained features and corresponding labels are then updated to the BLS. For the newly collected data, the incremental learning of new fault modes is achieved by automatic feature extraction of the ResNet and the node expansion of the BLS. The effectiveness of the proposed method is verified by motor-driven converters fault diagnosis. Experimental results indicate that the method can effectively update the diagnosis model to incrementally learn new fault categories and new fault modes.

Exploring High-Performance Architecture for Data Center Networks

As a critical infrastructure of cloud computing, data center networks (DCNs) directly determine the service performance of data centers, which provide computing services for various applications such as big data processing and artificial intelligence. However, current architectures of data center networks suffer from a long routing path and a low fault tolerance between source and destination servers, which is hard to satisfy the requirements of high-performance data center networks. Based on dual-port servers and Clos network structure, this paper proposed a novel architecture to construct high-performance data center networks. Logically, the proposed architecture is constructed by inserting a dual-port server into each pair of adjacent switches in the fabric of switches, where switches are connected in the form of a ring Clos structure. We describe the structural properties of in terms of network scale, bisection bandwidth, and network diameter. architecture inherits characteristics of its embedded Clos network, which can accommodate a large number of servers with a small average path length. The proposed architecture embraces a high fault tolerance, which adapts to the construction of various data center networks. For example, the average path length between servers is 3.44, and the standardized bisection bandwidth is 0.8 in (32, 5). The result of numerical experiments shows that enjoys a small average path length and a high network fault tolerance, which is essential in the construction of high-performance data center networks.

Phase-Shifted Full Bridge DC–DC Converter for Photovoltaic MVDC Power Collection Networks

The connection of photovoltaic sources to a medium voltage dc collection network requires a dc-dc converter having specific grid-connected converter capabilities. This article presents the application of a phase-shifted full bridge (PSFB) converter for medium voltage dc collection networks suited to photovoltaic power plants. The unidirectional structure of the converter is beneficial in terms of cost and simplicity of hardware implementation of the MV circuit components. The design of the PSFB converter is presented considering ratings of 250 kW power, 1.2 kV input, and 20 kV output. A converter model and a novel PSFB input voltage control regulating the dc-link voltage are developed and verified. A tuning method is given taking into account the effect of different transformer leakage inductance values. The behaviour of the PSFB under the PV power production profile and MV network faults is studied in simulation and verified against a reduced-scale prototype with ratings of 30 kW and 350 V / 600 V operating at 20 kHz. The experimental verification of the control is performed considering a real PV power profile. The experimental results under faults show the same response as in simulations. The PSFB fault response is observed to be superior compared to other dc–dc topologies with capacitive output filter only, making it suitable for grid-connected operation.

Determining Most Likely Links (MLL) for Network Fault Localization

We propose and evaluate a technique that learns the probability of a network transmission link experiencing a fault by using outlier flows (in the performance sense) as training data. This technique autonomously determines the most likely links causing performance degradation in a communications network; a critical feature of zero-touch network management. Our new Network Link Outlier Factor (NLOF) with most likely links (NLOF:MLL) is experimentally compared to the existing literature (including our original NLOF) using classification performance measures: recall, precision, F1-score, and time-to-detection. We utilize inferential statistics and a wide set of Mininet experiments to determine statistically significant performance differences. We find that our NLOF:MLL outperforms the existing literature wrt the important F1-score while exhibiting a competitive time-to-detection.

Drones applications for smart cities: Monitoring palm trees and street lights

Abstract This study explores drones’ applications and proposes a cost-effective drone monitoring system for both palm trees and street lighting networks. The planned drone technical system has two monitoring sections. First, a model is developed to examine the health of date palm trees, in which drone photos are used to determine whether palm trees are suffering from diseases such as black scorch and sudden decline syndrome. These images are transferred into a central computer to stimulate normalized difference vegetation index (NDVI) models using AgiSoft software. The simulated NDVI models indicated that there are no health issues with date palm trees, which has resulted in the positive feedback in terms of the economic growth. Second, drone technology is utilized to detect the technical faults in the lighting network to ensure proper maintenance and social security. Twelve images of street lights are captured to demonstrate the working condition and the operational status of the street lights. These images are processed in MATLAB software, and a stimulated image processing model is implemented to enhance the monitoring of the street lighting network. The simulation findings indicate that the light in one of the images is not functioning, and ArcGIS Pro is utilized to locate it.

Towards Fault Tolerance Management Systems in SDN

The issue of network operation, monitoring, and availability in traditional network environments has been one of the major challenges to addressing network administrators' struggles to deal with. The capacity for the network to comprehend the status and the performance of every node has been one of the priorities amongst others for network administrators to protect during troubleshooting in their network. However, the growing use of software-defined networks (SDN) technologies, as well as virtualization, pave the way to the solution of network operation, monitoring, and availability of hardware and services in a network environment. SDN has emerged with a novel paradigm of network abstractions that is dynamic, able to monitor network performance and fault management automatically, using its programmable capability. This paper presents a design of a fault tolerance management system for SDN controller framework for small to medium sized networks capable of detecting controller faults and nodes/links faultsin case entire network access is unavailable. The fault management system applies various approaches for fault detection and recovery to ensure the reliability and availability of the network resources.

Faulty feeder detection for single phase-to-ground faults in distribution networks based on patch-to-patch CNN and feeder-to-feeder LSTM

Faulty feeder detection has always been recognized as an essential issue in guaranteeing the stable and reliable operation of distribution networks. Existing methods fail to fully exploit the spatial correlation and temporal dependencies in the zero-sequence currents, which are exhibited as waveforms on the spatial domain and are displayed as time-series data on the time domain. In this paper, a novel detection method based on a hybrid model of convolutional neural network (CNN) and long short-term memory (LSTM) neural network is proposed, and the spatial–temporal information can be comprehensively explored. Deep spatial features are extracted by using CNN, and they are further processed by using LSTM network. Besides, to maintain the temporal dependencies of the extracted spatial features, the current waveforms are recognized on the patch scale by the proposed patch-to-patch CNN (PToP CNN). Moreover, a feeder-to-feeder LSTM (FToF LSTM) network is established to learn and compare spatial–temporal correlations between feeders. The joint PToP-CNN and FToF-LSTM can achieve collaborative superiority on mining the fault features in the zero-sequence currents. To verify the prospects in real installations, the hybrid model is implemented in an embedded device, called NVIDIA Jetson AGX Xavier, and the real-time detection demonstrates the efficiency of the proposed method.

Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems

We develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained using the Levenberg-Marquardt backpropagation (LMBP) method, which multi-stage BO optimizes for efficiency. During training, the feature vectors at the sending terminal of the dc link are selected based on the norm values of the observed waveforms at various frequency bands. The multilayer ANN is trained using a comprehensive set of offline data that takes the denoising scheme into account. This choice not only helps to reduce the computational load but also provides better accuracy. An overall percentage error of 0.5144% is observed for the proposed algorithm when tested against fault resistances ranging from 10 to 485 Ω. The simulation results show that the proposed method can accurately estimate the fault site to a precision of 485 Ω and is more robust.

An energy fault and consumption optimization strategy in wireless sensor networks with edge computing

With the operation of wireless sensor networks (WSNs), energy-constrained sensor nodes and inadequate energy constraint methods are becoming obsolete, as they reduce the efficiency of data transmission. The appearance of edge computing (EC) and causality graph provide a new opportunity for energy fault analysis and assessment in WSNs. As a result, by selecting a reliable data transmission path and averaging the energy consumption, we present an energy fault and consumption optimization (EFCO) algorithm for solving the energy hole and consumption balance (EHCB) problem in wireless sensor networks with edge computing (ECWSNs). Specifically, we first build a novel four-layer network architecture by using edge computing technology and causality graph theory. Then, the energy fault cost (EFC) in ECWSNs is formulated as an optimization problem that is constrained by the energy allocation of relay nodes. Furthermore, we propose a causal reasoning algorithm to deduce the single-value fault status probability of relay nodes. Finally, we utilize version 2 of a network simulator (NS-2) to evaluate the fault derivation and energy allocation efficiency of the EFCO algorithm in ECWSNs.

Intelligent fault diagnosis of gearbox based on differential continuous wavelet transform-parallel multi-block fusion residual network

Due to the difficulty of fault feature extraction and low accuracy of pattern recognition in fault diagnosis of gearboxes, a differential continuous wavelet transform-parallel multi-block fusion residual network fault diagnosis method is proposed. The signal is subjected to continuous wavelet transform after the first-order difference, which can effectively improve the resolution of the time–frequency feature images. The parallel fusion residual block (PFRB) is constructed, and the number of PFRBs can be selected adaptively based on the data features, thus enhancing the learning capability of the features. An attentional feature fusion layer is designed. This layer locates the fault features extracted by the previous layer through the attention mechanism. Through the feature fusion mechanism, the effective fault information is fused to achieve feature augmentation inside the network. The experimental results show that the proposed method has superior diagnostic performance compared with other methods in bearing and gearbox gear faults.

Exploring the Quality of Dynamic Open Government Data Using Statistical and Machine Learning Methods

Dynamic data (including environmental, traffic, and sensor data) were recently recognized as an important part of Open Government Data (OGD). Although these data are of vital importance in the development of data intelligence applications, such as business applications that exploit traffic data to predict traffic demand, they are prone to data quality errors produced by, e.g., failures of sensors and network faults. This paper explores the quality of Dynamic Open Government Data. To that end, a single case is studied using traffic data from the official Greek OGD portal. The portal uses an Application Programming Interface (API), which is essential for effective dynamic data dissemination. Our research approach includes assessing data quality using statistical and machine learning methods to detect missing values and anomalies. Traffic flow-speed correlation analysis, seasonal-trend decomposition, and unsupervised isolation Forest (iForest) are used to detect anomalies. iForest anomalies are classified as sensor faults and unusual traffic conditions. The iForest algorithm is also trained on additional features, and the model is explained using explainable artificial intelligence. There are 20.16% missing traffic observations, and 50% of the sensors have 15.5% to 33.43% missing values. The average percent of anomalies per sensor is 71.1%, with only a few sensors having less than 10% anomalies. Seasonal-trend decomposition detected 12.6% anomalies in the data of these sensors, and iForest 11.6%, with very few overlaps. To the authors' knowledge, this is the first time a study has explored the quality of dynamic OGD.

Practice on fifth-generation core (5GC) network fault self-recovery based on a Digital Twin

Background: The development of cloud-based, service-focused and intelligent networks has increased the demand for highly reliable, error-tolerant and computationally efficient means of reducing the costs associated with network operation, maintenance, testing and innovations. Methods: We present a fault self-recovery method for fifth-generation core (5GC) networks. Data models are built according to the data governance approach to include the equipment, links and services of the physical network in the digital twin. Visual topology technology is used to extract knowledge-as-a-service (KaaS) capabilities such as call quality tests, fault-propagation chain reasoning and disaster recovery analysis. Results: The proposed method realises 5GC closed-loop self-recovery through four processes: perception, analysis, decision-making and execution. In tests, it achieved 5GC network fault detection in 1 min, delimitation in 20 min, and recovery in 5 min. Conclusions: Through the network digital twin technology, based on the model and state data, the twinning capabilities such as simulation and event topology can be used to realize the network anomaly perception, fault rapid confinement and service survival decision, thus effectively improving the fault processing efficiency and reducing the fault impact.

Anomaly Detection and Early Warning Model for Latency in Private 5G Networks

Different from previous generations of communication technology, 5G has tailored several modes especially for industrial applications, such as Ultra-Reliable Low-Latency Communications (URLLC) and Massive Machine Type Communications (mMTC). The industrial private 5G networks require high performance of latency, bandwidth, and reliability, while the deployment environment is usually complicated, causing network problems difficult to identify. This poses a challenge to the operation and maintenance (O&M) of private 5G networks. It is needed to quickly diagnose or predict faults based on high-dimensional data of networks and services to reduce the impact of network faults on services. This paper proposes a ConvAE-Latency model for anomaly detection, which enhances the correlation between target indicators and hidden features by multi-target learning. Meanwhile, transfer learning is applied for anomaly prediction in the proposed LstmAE-TL model to solve the problem of unbalanced samples. Based on the China Telecom data platform, the proposed models are deployed and tested in an Automated Guided Vehicles (AGVs) application scenario. The results have been improved compared to existing research.

Evaluation of the impact of the electric network's quality on the appliance's signatures

The continuous increase in the demand for electrical energy has led to the design of highly complex electrical systems, which can even extend to entire countries. In this context, active residential customer participation in the smart grid can benefit from having control over a number of data points related to the behaviour of the grid and the devices connected to it. The load signatures are the basis for practical energy's consumption monitoring technologies, which involve identifying an electrical device and determining their operating status. Although several load identification techniques are under development in research laboratories, it is important to note that studies on the impact of power system quality on the signatures underlying these developments are not yet clear. Knowing that load profiles depend on environmental factors, user habits, and other non-deterministic factors, it is important to assess the impact that grid quality can have on load signatures in order to take it into account in the development of identification systems to be integrated into the smart grid. This research focuses on the two central components of these approaches: (1) Presenting an assessment of the different network faults that can impact the signatures of connected loads, (2) Analysing and quantifying the impact of each fault through load behavioural models and virtual simulation. The study considers the two types of loads generally encountered in homes (linear and non-linear). It then analyses the characteristic quantities such as waveforms, effective current and voltage values, active and reactive power (harmonics) and non-deforming power (fundamentals). The results of the simulations performed on Simulink/Simscape show that some network faults such as flicker have a significant and permanent impact on the signatures while others (Voltage Sag) have a temporary and sometimes insignificant effect.

Task Scheduling for Probabilistic In -Band Network Telemetry

In-band Network Telemetry (INT) is a novel framework for monitoring network health in real-time, and its recent variant, Probabilistic INT (PINT), reduces its bandwidth consumption with a probabilistic approach. However, as we show in this paper, a PINT task can be successfully accomplished only when it is allocated a sufficient number of packets, and if there are many tasks executed in parallel, packets become a scarce resource. Meanwhile, today’s production network generally executes multiple measurement tasks for tracing different network states simultaneously. Therefore, in such a context, scheduling parallel PINT tasks on one single INT flow that has a limited number of packets becomes a critical problem. In this paper, we address this problem for the first time. We propose an algorithm that efficiently schedules multiple parallel PINT tasks on a flow by allocating the flow’s packets to the tasks and showing that the allocation is optimal. We realize the algorithm with a packet processing pipeline and implement it on software and hardware-programmable switches. Comprehensive evaluation on a FatTree testbed shows that at a low scheduling overhead, our algorithm can conduct parallel PINT tasks to detect various network faults in a timely and accurate manner. Additionally, the algorithm accomplishes more PINT tasks with higher quality than the alternative solutions.

Research on Line Selection Technology for Two-point Same-phase Ground Faults in Medium-voltage Distribution Networks

At present, the problematic line selection method for single phase grounding faults of the small current grounding system has been mature, but line selection method for two-point same-phase ground faults is rarely studied. For the problem that the accuracy of line selection equipment is low for two-point same-phase ground faults, a fault model is established and the fault signatures are analyzed theoretically. As the faulty line zero-sequence current is affected by more factors, it is not possible to select the line with the common line selection technology for single-phase grounding faults. By further theoretical derivation, a new method for successive judgment of faulty lines is proposed, and the correctness of problematic characteristics and the feasibility of line selection technology are verified to many different cases by simulation using the ATP simulation experimental platform.

A Deep Learning Technique for Detecting High Impedance Faults in Medium Voltage Distribution Networks

Utility companies always struggle with the High Impedance Fault (HIF) in the electrical distribution systems. In this article, the current signal is seen in situations involving 10,400 different samples, with and without HIF, like linear, non-linear load, and capacitance switching. A better method that processes signals very fast and with low sample rates, requiring less memory and computational labor, is demonstrated by Mathematical Morphology (MM). For HIF identification, Deep Convolution Neural Networks (DCNNs) are being developed. This paper presents a novel method for signal processing with low sample rates, high signal processing speed, and low computational and memory requirements. The suggested six-layer DCNN is compared with other models, such as the four-layer and eight-layer DCNN models and the results are discussed.