Faults In Wireless Networks Research Articles

Cellular Network Fault Diagnosis Method Based on a Graph Convolutional Neural Network.

The efficient and accurate diagnosis of faults in cellular networks is crucial for ensuring smooth and uninterrupted communication services. In this paper, we propose an improved 4G/5G network fault diagnosis with a few effective labeled samples. Our solution is a heterogeneous wireless network fault diagnosis algorithm based on Graph Convolutional Neural Network (GCN). First, the common failure types of 4G/5G networks are analyzed, and then the graph structure is constructed with the data in the network parameter, given data sets as nodes and similarities as edges. GCN is used to extract features from the graph data, complete the classification task for nodes, and finally predict the fault types of cells. A large number of experiments are carried out based on the real data set, which is achieved by driving tests. The results show that, compared with a variety of traditional algorithms, the proposed method can effectively improve the performance of network fault diagnosis with a small number of labeled samples.

Hybrid tree model for root cause analysis of wireless network fault localization

Localizing the root cause of network faults is crucial to network operation and maintenance. Operational expenses will be saved if the root cause can be identified accurately. However, due to the complicated wireless environments and network architectures, accurate root cause localization of network falut meets the difficulties including missing data, hybrid fault behaviors, and short of well-labeled data. In this study, global and local features are constructed to make new feature representation for data sample, which can highlight the temporal characteristics and contextual information of the root cause analysis data. A hybrid tree model (HTM) ensembled by CatBoost, XGBoost and LightGBM is proposed to interpret the hybrid fault behaviors from several perspectives and discriminate different root causes. Based on the combination of global and local features, a semi-supervised training strategy is utilized to train the HTM for dealing with short of well-labeled data. The experiments are conducted on the real-world dataset from ICASSP 2022 AIOps Challenge, and the results show that the global and local feature based HTM achieves the best model performance comparing with other models. Meanwhile, our solution achieves third place in the competition leaderboard which shows the model effectiveness.

Simulation of Fault Detection in the Wireless Networked Control System

Wireless network control system is characterized by high uncertain delay time, thus the state of the system can not be fully observed. The fault characteristic is interfered by time delay so to be unstable, leading inaccurate fault detection. Traditional fault detection method of wireless network control system is usually based on the characteristics of the stability of the network status data. If the network has time delay fluctuations, it is unable to obtain accurate fault detection results. This paper presents a stochastic delay fault detection method. It builds a state space model of the system, analyzes the delay vector between the sensor end of the system and the controller end, depending on the delay residual signal of the system and the corresponding evaluation function to obtain the system failure detection result. The final simulation result shows that this method has high accuracy in the detection of Stability and randomness of the wireless network fault detection. Thus it is an effective wireless network control system fault detection method.

A topology control algorithm based on D-region fault tolerance

In a wireless network, node failure due to either natural disasters or human intervention can cause network partitioning and other communication problems. For this reason, a wireless network should be fault tolerant. At present, most researchers use k-connectivity to measure fault tolerance, which requires the network to be connected after the failure of any up to k-1 nodes. However, wireless network node failures are usually spatially related, and particularly in military applications, nodes from the same limited area can fail together. As a metric of fault-tolerance, k-connectivity fails to capture the spatial relativity of faults and hardly satisfies the fault tolerance requirements of a wireless network design. In this paper, a new metric of fault-tolerance, termed D-region fault tolerance, is introduced to measure wireless network fault tolerance. A D-region fault tolerant network means that even after all the nodes have failed in a circular region with diameter D, it still remains connected. Based on D-region fault tolerance, we propose two fault-tolerant topology control algorithms—the global region fault tolerance algorithm (GRFT) and the localized region fault tolerance algorithm (LRFT). It is theoretically proven that both algorithms are able to generate a network with D-region fault tolerance. Simulation results indicate that with the same fault tolerance capabilities, networks based on both GRFT and LRFT algorithms have a lower transmission radius and lower logical degree.

Design and implementation of an embedded intrusion detection system for wireless applications

The exponential growth in wireless network faults, vulnerabilities and attacks makes the wireless local area network (WLAN) security management a challenging research area. In this study, a new embedded wireless intrusion detection system (WIDS) is designed and implemented in order to protect a multi-services wireless network. The proposed WIDS must be in small size in order to be integrated in different wireless devices, low cost in order to be placed in many places and has good performance to cover the data rate of the WLAN. All these attributes are achieved by network processor, and Ubicom network processor is used to implement the proposed WIDS. Different implementations of the proposed intrusion detection system are suggested and various searching algorithms are tested on an experimental platform. Finally, the WIDS approach is validated by experimenting with ten different types of attacks. The experimental results obtained from this work indicate that the proposed WIDS can worked efficiently at IEEE 802.11b WLAN network which provides different services to its clients with data rate ranges between 1.08 and 9.24 Mbps, and memory capacity of 250 rules.

A Hybrid Data Mining based Intrusion Detection System for Wireless Local Area Networks

The exponential growth in wireless network faults, vulnerabilities, and attacks make the WLAN security management a challenging research area (29). Data mining applied to intrusion detection is an active area of research. The main reason for using data mining techniques for intrusion detection systems is due to the enormous volume of existing and newly appearing network data that require processing. Data mining follows anomaly based intrusion detection. The drawback of the anomaly based intrusion detection in a wireless network is the high rate of false positive. This can be solved by a designing a hybrid intrusion detection system by connecting a misuse detection module to the anomaly detection module. In this paper, we propose to develop a hybrid intrusion detection system for wireless local area networks, based on Fuzzy logic. In this Hybrid Intrusion Detection system, anomaly detection is performed using the Bayesian network technique and misuse detection is performed using the Support Vector Machine (SVM) technique. The overall decision of system is performed by the fuzzy logic. For anomaly detection using Bayesian network, each node has a monitoring agent and a classifier within it for its detection and a mobile agent for information collection. The anomaly is measured based on the naive Bayesian technique. For misuse detection using SVM, all the data that lie within the hyper plane are considered to be normal whereas the data that lie outside the hyper plane are considered to be intrusive. The outputs of both anomaly detection and misuse detection modules are applied by the fuzzy decision rules to perform the final decision making. Hybrid detection system improves the detection performance by combining the advantages of the misuse and anomaly detection (33).

Event Correlation in Integrated Management: Lessons Learned and Outlook

When event correlation was first used in integrated management, in the early 1980s, several techniques devised by the artificial intelligence and database communities were applied to network element management for analyzing alarms sent by expensive, self-monitoring telephone switches. Today, it is used for detecting faults in wireless networks, for monitoring the performance of commodity, often non-self-aware devices in enterprise networks, for detecting intrusions in firewalls, for ascribing breaches in service level agreements to specific problems in the underlying IT infrastructure, etc. In other words, the problem to be solved has changed completely. Can today's event correlators still meet customers' expectations? If not, how should they evolve to meet them? In this paper, we try to capture the main lessons learned by the integrated management community in event correlation in the past 25 years, and to identify important challenges that we are faced with. By doing this, we hope to streamline and encourage research in this field, which needs better models, algorithms and systems to deal with ever more complex and integrated networks, systems and services.