Intelligent Network Applications Monitoring and Diagnosis Employing Software Sensing and Machine Learning Solutions

Abstract

The article presents a research in the field of complex sensing, detection, and recovery of communications networks applications and hardware, in case of failures, maloperations, or unauthorized intrusions. A case study, based on Davis AI engine operation versus human maintenance operation is performed on the efficiency of artificial intelligence agents in detecting faulty operation, in the context of growing complexity of communications networks, and the perspective of future development of internet of things, big data, smart cities, and connected vehicles. (*). In the second part of the article, a new solution is proposed for the detection of applications faults or unauthorized intrusions in traffic of communications networks. The first objective of the proposed method is to propose an approach for predicting time series. This approach is based on a multi-resolution decomposition of the signals employing the undecimate wavelet transform (UWT). The second approach for assessing traffic flow is based on the analysis of long-range dependence (LRD) (for this case, a long-term dependence). Estimating the degree of long-range dependence is performed by estimating the Hurst parameter of the analyzed time series. This is a relatively new statistical concept in communications traffic analysis and can be implemented using UWT. This property has important implications for network performance, design, and sizing. The presence of long-range dependency in network traffic is assumed to have a significant impact on network performance, and the occurrence of LRD can be the result of faults that occur during certain periods. The strategy chosen for this purpose is based on long-term dependence on traffic, and for the prediction of faults occurrence, a predictive control model (MPC) is proposed, combined with a neural network with radial function (RBF). It is demonstrated via simulations that, in the case of communications traffic, time location is the most important feature of the proposed algorithm.

Fault Diagnosis of Subway Mechanical Equipment Based on 5G Intelligent Sensor Network Signal Processing

“…The kernel method represented by the intelligent sensor network has brought the third revolution in the field of pattern analysis. This kind of method implicitly maps the original spatial data to the feature space through the kernel function [3][4][5], finds a linear relationship in the feature space, and realizes the efficient solution of nonlinear problems [6]. The failures of subway machinery often show nonlinear behavior [7], and the kernel method is especially suitable for the processing of subway machinery fault diagnosis and mode analysis problems [8].…”

Smart Preventive Maintenance of Hybrid Networks and IoT Systems Using Software Sensing and Future State Prediction

“…These agents harvest information both from hardware and communication channels loads, as well as from the applications' availability and response times. As a continuation of a previous research [52], the use of intelligent agents in early discovering and noticing deviations of normal operation and lowering of the level of service is associated in this work with the updating of a current state matrix and computing different state probabilities for a future state prediction matrix. The latter is aimed at providing the operator with alerts and suggestions for alleviating malfunctions' and maloperations' negative effects.…”

“…For the intelligent monitoring of the backbone data network, previous work results have been presented in [52]. The following intelligent agents have been in use for monitoring smart city services:…”

Using Brain-Computer Interface to Control a Virtual Drone Using Non-Invasive Motor Imagery and Machine Learning

“…The term σ represents a scaling factor, while τ is a translation factor. Common ψ (σ,τ) (•) wavelet basis functions are the Haar wavelet, Symlets wavelet, Daubechies wavelet and Mexican Hat wavelet [46].…”