Network Failure Detection and Diagnosis by Analyzing Syslog and SNS Data: Applying Big Data Analysis to Network Operations

Abstract

We present two major information examination strategies for diagnosing the reasons for system disappointments and for identifying system disappointments early. Syslogs contain log information created by the framework. We dissected syslogs what's more, prevailing with regards to distinguishing the reason for a system disappointment via consequently learning more than 100 million logs without requiring any past learning of log information. Investigation of the information of an interpersonal interaction benefit (in particular, Twitter) empowered us to recognize conceivable system disappointments by extricating system disappointment related tweets, which represent under 1% of all tweets, continuously and with high exactness.

Decentralized dynamic power control in an islanded DC microgrid with hybrid energy storage system

“…The battery circuit is shown in Figure 3. If 𝑉 𝑜𝑐 represents open circuit voltage (V), 𝑉′ 𝑜𝑐 represents full charge open circuit voltage (V), T represents temperature of electrolyte in C, S represents the state of charge of battery and K is a constant in volts/C, then 𝑉 𝑜𝑐 is given by (7): The minimum capacitance CMIN required can be obtained by neglecting Req under constant discharge power:…”

“…The designed system is simulated in Simulink and the output waveforms are analyzed. The system proves to improve regulation of DC link voltage, reliable supply to the loads and will be an attractive alternative of power in future for small community, school, hospital, and other sectors [6], [7]. The proposed model of the microgrid consists of solar PV, hybrid energy storage system (consisting of battery and supercapacitor), constant and dynamic loads, as shown in Figure 1.…”

Modeling and analysis of brushless DC motor system based on intelligent controllers

“…The key issue with this engine is the high design and development, as well as the BLDC motor controller is much complicated compared with the traditional motor controller [5]. BLDCM include a better energy density compared with different type of motors (e.g., induction machines (IM)), this kind seems to have no loss and therefore no commutation inside rotor copper so it has been utilized extensively in manufacturing and are ideal for high-performance applications [6], [7]. Those other variables add to popularity of brushless DC motors in productivity-critical utilization and where there are spikes caused by switching are (undesired).…”

Hajj pilgrimage video analytics using CNN

“…Other approaches to crowd analysis have been resulted in several semi-automated solutions for density estimation and crowd counting [5]- [7]. Effective implementation of the semi-automated solutions, however, is limited by two significant limitations; (1) lack of capacity to accommodate hundreds or thousands of crowds, rather than a few tens of people [5]; and (2) dependence on temporal limitations in crowd videos that do not extend to still images which are more prevalent [8]. In addition to arbitrary camera position and crowd density, there are still problem of erroneous crowd counts from an arbitrary still image [7].…”

“…Among available dataset related to crowd images are the 50 static images obtained from Flickr from different crowd scenes [9]. Other commonly used UCSD dataset were made up of movies collected from one or more scenes [10], [5]. In this work, we obtained our dataset from the YouTube and the detailed dataset is discussed in methodology section.…”