scholarly journals A Framework for Detecting System Performance Anomalies Using Tracing Data Analysis

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1011
Author(s):  
Iman Kohyarnejadfard ◽  
Daniel Aloise ◽  
Michel R. Dagenais ◽  
Mahsa Shakeri
Keyword(s):  
Large Scale ◽  
Performance Metrics ◽  
Abnormal Behavior ◽  
Software Architectures ◽  
Computing Power ◽  
Software Bugs ◽  
Learning Module ◽  
System Calls ◽  
Hardware Failures ◽  
Software Execution

Advances in technology and computing power have led to the emergence of complex and large-scale software architectures in recent years. However, they are prone to performance anomalies due to various reasons, including software bugs, hardware failures, and resource contentions. Performance metrics represent the average load on the system and do not help discover the cause of the problem if abnormal behavior occurs during software execution. Consequently, system experts have to examine a massive amount of low-level tracing data to determine the cause of a performance issue. In this work, we propose an anomaly detection framework that reduces troubleshooting time, besides guiding developers to discover performance problems by highlighting anomalous parts in trace data. Our framework works by collecting streams of system calls during the execution of a process using the Linux Trace Toolkit Next Generation(LTTng), sending them to a machine learning module that reveals anomalous subsequences of system calls based on their execution times and frequency. Extensive experiments on real datasets from two different applications (e.g., MySQL and Chrome), for varying scenarios in terms of available labeled data, demonstrate the effectiveness of our approach to distinguish normal sequences from abnormal ones.

A Novel Static Path Planning Method for Mobile Anchor-Assisted Localization in Wireless Sensor Networks

2020 ◽  
Vol 10 ◽  
Author(s):  
Abdelhady M. Naguib ◽  
Shahzad Ali
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Path Planning ◽  
Sensor Node ◽  
Large Scale ◽  
Performance Metrics ◽  
Wireless Sensor ◽  
Anchor Node ◽  
Mobile Anchor ◽  
Planning Methods

Background: Many applications of Wireless Sensor Networks (WSNs) require awareness of sensor node’s location but not every sensor node can be equipped with a GPS receiver for localization, due to cost and energy constraints especially for large-scale networks. For localization, many algorithms have been proposed to enable a sensor node to be able to determine its location by utilizing a small number of special nodes called anchors that are equipped with GPS receivers. In recent years a promising method that significantly reduces the cost is to replace the set of statically deployed GPS anchors with one mobile anchor node equipped with a GPS unit that moves to cover the entire network. Objectives: This paper proposes a novel static path planning mechanism that enables a single anchor node to follow a predefined static path while periodically broadcasting its current location coordinates to the nearby sensors. This new path type is called SQUARE_SPIRAL and it is specifically designed to reduce the collinearity during localization. Results: Simulation results show that the performance of SQUARE_SPIRAL mechanism is better than other static path planning methods with respect to multiple performance metrics. Conclusion: This work includes an extensive comparative study of the existing static path planning methods then presents a comparison of the proposed mechanism with existing solutions by doing extensive simulations in NS-2.

scholarly journals Wireless Sensor Networks for Smart Cities: Network Design, Implementation and Performance Evaluation

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 218
Author(s):  
Ala’ Khalifeh ◽  
Khalid A. Darabkh ◽  
Ahmad M. Khasawneh ◽  
Issa Alqaisieh ◽  
Mohammad Salameh ◽  
...  
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Experimental Evaluation ◽  
Large Scale ◽  
Performance Metrics ◽  
Smart Cities ◽  
Field Tests ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Real Field

The advent of various wireless technologies has paved the way for the realization of new infrastructures and applications for smart cities. Wireless Sensor Networks (WSNs) are one of the most important among these technologies. WSNs are widely used in various applications in our daily lives. Due to their cost effectiveness and rapid deployment, WSNs can be used for securing smart cities by providing remote monitoring and sensing for many critical scenarios including hostile environments, battlefields, or areas subject to natural disasters such as earthquakes, volcano eruptions, and floods or to large-scale accidents such as nuclear plants explosions or chemical plumes. The purpose of this paper is to propose a new framework where WSNs are adopted for remote sensing and monitoring in smart city applications. We propose using Unmanned Aerial Vehicles to act as a data mule to offload the sensor nodes and transfer the monitoring data securely to the remote control center for further analysis and decision making. Furthermore, the paper provides insight about implementation challenges in the realization of the proposed framework. In addition, the paper provides an experimental evaluation of the proposed design in outdoor environments, in the presence of different types of obstacles, common to typical outdoor fields. The experimental evaluation revealed several inconsistencies between the performance metrics advertised in the hardware-specific data-sheets. In particular, we found mismatches between the advertised coverage distance and signal strength with our experimental measurements. Therefore, it is crucial that network designers and developers conduct field tests and device performance assessment before designing and implementing the WSN for application in a real field setting.

scholarly journals Design and Evaluation of Large-Scale IoT-Enabled Healthcare Architecture

2021 ◽  
Vol 11 (8) ◽  
pp. 3623
Author(s):  
Omar Said ◽  
Amr Tolba
Keyword(s):  
Packet Loss ◽  
Large Scale ◽  
Performance Metrics ◽  
Medical System ◽  
Healthcare Data ◽  
High Altitude Platforms ◽  
Wide Range ◽  
Simulation Results ◽  
Healthcare Architecture ◽  
The Internet Of Things

Employment of the Internet of Things (IoT) technology in the healthcare field can contribute to recruiting heterogeneous medical devices and creating smart cooperation between them. This cooperation leads to an increase in the efficiency of the entire medical system, thus accelerating the diagnosis and curing of patients, in general, and rescuing critical cases in particular. In this paper, a large-scale IoT-enabled healthcare architecture is proposed. To achieve a wide range of communication between healthcare devices, not only are Internet coverage tools utilized but also satellites and high-altitude platforms (HAPs). In addition, the clustering idea is applied in the proposed architecture to facilitate its management. Moreover, healthcare data are prioritized into several levels of importance. Finally, NS3 is used to measure the performance of the proposed IoT-enabled healthcare architecture. The performance metrics are delay, energy consumption, packet loss, coverage tool usage, throughput, percentage of served users, and percentage of each exchanged data type. The simulation results demonstrate that the proposed IoT-enabled healthcare architecture outperforms the traditional healthcare architecture.

scholarly journals Cloud-based intelligent self-diagnosis and department recommendation service using Chinese medical BERT

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Junshu Wang ◽  
Guoming Zhang ◽  
Wei Wang ◽  
Ka Zhang ◽  
Yehua Sheng
Keyword(s):  
Cloud Computing ◽  
Large Scale ◽  
Medical Service ◽  
Rapid Development ◽  
Medical Knowledge ◽  
Language Models ◽  
Computing Environment ◽  
Computing Power ◽  
Cloud Computing Environment ◽  
Proposed Model

AbstractWith the rapid development of hospital informatization and Internet medical service in recent years, most hospitals have launched online hospital appointment registration systems to remove patient queues and improve the efficiency of medical services. However, most of the patients lack professional medical knowledge and have no idea of how to choose department when registering. To instruct the patients to seek medical care and register effectively, we proposed CIDRS, an intelligent self-diagnosis and department recommendation framework based on Chinese medical Bidirectional Encoder Representations from Transformers (BERT) in the cloud computing environment. We also established a Chinese BERT model (CHMBERT) trained on a large-scale Chinese medical text corpus. This model was used to optimize self-diagnosis and department recommendation tasks. To solve the limited computing power of terminals, we deployed the proposed framework in a cloud computing environment based on container and micro-service technologies. Real-world medical datasets from hospitals were used in the experiments, and results showed that the proposed model was superior to the traditional deep learning models and other pre-trained language models in terms of performance.

scholarly journals Opportunistic Large Array Propagation Models: A Comprehensive Survey

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4206
Author(s):  
Farhan Nawaz ◽  
Hemant Kumar ◽  
Syed Ali Hassan ◽  
Haejoon Jung
Keyword(s):  
Energy Efficient ◽  
Large Scale ◽  
Performance Metrics ◽  
Experimental Studies ◽  
Cooperative Transmission ◽  
Analytical Models ◽  
Future Research ◽  
Large Array ◽  
Propagation Models ◽  
Comprehensive Survey

Enabled by the fifth-generation (5G) and beyond 5G communications, large-scale deployments of Internet-of-Things (IoT) networks are expected in various application fields to handle massive machine-type communication (mMTC) services. Device-to-device (D2D) communications can be an effective solution in massive IoT networks to overcome the inherent hardware limitations of small devices. In such D2D scenarios, given that a receiver can benefit from the signal-to-noise-ratio (SNR) advantage through diversity and array gains, cooperative transmission (CT) can be employed, so that multiple IoT nodes can create a virtual antenna array. In particular, Opportunistic Large Array (OLA), which is one type of CT technique, is known to provide fast, energy-efficient, and reliable broadcasting and unicasting without prior coordination, which can be exploited in future mMTC applications. However, OLA-based protocol design and operation are subject to network models to characterize the propagation behavior and evaluate the performance. Further, it has been shown through some experimental studies that the most widely-used model in prior studies on OLA is not accurate for networks with networks with low node density. Therefore, stochastic models using quasi-stationary Markov chain are introduced, which are more complex but more exact to estimate the key performance metrics of the OLA transmissions in practice. Considering the fact that such propagation models should be selected carefully depending on system parameters such as network topology and channel environments, we provide a comprehensive survey on the analytical models and framework of the OLA propagation in the literature, which is not available in the existing survey papers on OLA protocols. In addition, we introduce energy-efficient OLA techniques, which are of paramount importance in energy-limited IoT networks. Furthermore, we discuss future research directions to combine OLA with emerging technologies.

scholarly journals Earth System Model Evaluation Tool (ESMValTool) v2.0 – an extended set of large-scale diagnostics for quasi-operational and comprehensive evaluation of Earth system models in CMIP

2020 ◽  
Vol 13 (7) ◽  
pp. 3383-3438 ◽  
Author(s):  
Veronika Eyring ◽  
Lisa Bock ◽  
Axel Lauer ◽  
Mattia Righi ◽  
Manuel Schlund ◽  
...  
Keyword(s):  
Model Evaluation ◽  
Large Scale ◽  
Performance Metrics ◽  
Earth System Model ◽  
System Model ◽  
Earth System ◽  
Evaluation Tool ◽  
The Earth ◽  
And Performance ◽  
Earth System Models

Abstract. The Earth System Model Evaluation Tool (ESMValTool) is a community diagnostics and performance metrics tool designed to improve comprehensive and routine evaluation of Earth system models (ESMs) participating in the Coupled Model Intercomparison Project (CMIP). It has undergone rapid development since the first release in 2016 and is now a well-tested tool that provides end-to-end provenance tracking to ensure reproducibility. It consists of (1) an easy-to-install, well-documented Python package providing the core functionalities (ESMValCore) that performs common preprocessing operations and (2) a diagnostic part that includes tailored diagnostics and performance metrics for specific scientific applications. Here we describe large-scale diagnostics of the second major release of the tool that supports the evaluation of ESMs participating in CMIP Phase 6 (CMIP6). ESMValTool v2.0 includes a large collection of diagnostics and performance metrics for atmospheric, oceanic, and terrestrial variables for the mean state, trends, and variability. ESMValTool v2.0 also successfully reproduces figures from the evaluation and projections chapters of the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report (AR5) and incorporates updates from targeted analysis packages, such as the NCAR Climate Variability Diagnostics Package for the evaluation of modes of variability, the Thermodynamic Diagnostic Tool (TheDiaTo) to evaluate the energetics of the climate system, as well as parts of AutoAssess that contains a mix of top–down performance metrics. The tool has been fully integrated into the Earth System Grid Federation (ESGF) infrastructure at the Deutsches Klimarechenzentrum (DKRZ) to provide evaluation results from CMIP6 model simulations shortly after the output is published to the CMIP archive. A result browser has been implemented that enables advanced monitoring of the evaluation results by a broad user community at much faster timescales than what was possible in CMIP5.

scholarly journals Construction of a century solar chromosphere data set for solar activity related research

2017 ◽  
Vol 3 (2) ◽  
pp. 5-8
Author(s):  
Линь Ганхуа ◽  
Lin Ganghua ◽  
Ван Сяо-Фань ◽  
Wang Xiao Fan ◽  
Ян Сяо ◽  
...  
Keyword(s):  
Data Mining ◽  
Solar Activity ◽  
Space Weather ◽  
Large Scale ◽  
Abnormal Behavior ◽  
Solar Chromosphere ◽  
Solar Cycles ◽  
Data Set ◽  
Related Research ◽  
Data Mining Algorithms

This article introduces our ongoing project “Construction of a Century Solar Chromosphere Data Set for Solar Activity Related Research”. Solar activities are the major sources of space weather that affects human lives. Some of the serious space weather consequences, for instance, include interruption of space communication and navigation, compromising the safety of astronauts and satellites, and damaging power grids. Therefore, the solar activity research has both scientific and social impacts. The major database is built up from digitized and standardized film data obtained by several observatories around the world and covers a timespan more than 100 years. After careful calibration, we will develop feature extraction and data mining tools and provide them together with the comprehensive database for the astronomical community. Our final goal is to address several physical issues: filament behavior in solar cycles, abnormal behavior of solar cycle 24, large-scale solar eruptions, and sympathetic remote brightenings. Significant progresses are expected in data mining algorithms and software development, which will benefit the scientific analysis and eventually advance our understanding of solar cycles.

scholarly journals Does Tail Label Help for Large-Scale Multi-Label Learning

2018 ◽  
Author(s):  
Tong Wei ◽  
Yu-Feng Li
Keyword(s):  
Large Scale ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Predictive Performance ◽  
Low Complexity ◽  
Tail Distribution ◽  
Prediction Time ◽  
Unseen Data ◽  
Model Size ◽  
Fast Prediction

Large-scale multi-label learning annotates relevant labels for unseen data from a huge number of candidate labels. It is well known that in large-scale multi-label learning, labels exhibit a long tail distribution in which a significant fraction of labels are tail labels. Nonetheless, how tail labels make impact on the performance metrics in large-scale multi-label learning was not explicitly quantified. In this paper, we disclose that whatever labels are randomly missing or misclassified, tail labels impact much less than common labels in terms of commonly used performance metrics (Top-$k$ precision and nDCG@$k$). With the observation above, we develop a low-complexity large-scale multi-label learning algorithm with the goal of facilitating fast prediction and compact models by trimming tail labels adaptively. Experiments clearly verify that both the prediction time and the model size are significantly reduced without sacrificing much predictive performance for state-of-the-art approaches.

scholarly journals A Nonlinear Model For The Optimal Capacity Placement In Self-Healing ATM Networks Based On Link Restoration Strategy

2021 ◽  
Author(s):  
ABM B. Alam
Keyword(s):  
Communication Systems ◽  
Large Scale ◽  
Performance Metrics ◽  
Asynchronous Transfer Mode ◽  
Critical Issue ◽  
Self Healing ◽  
Network Failure ◽  
Optimal Capacity ◽  
Telecommunications Network ◽  
Important Challenge

Network Survivability is a critical issue in telecommunications network due to increasing dependence of the society on communication systems. Fast restoration from a network failure is an important challenge that deserves attention. This thesis addresses an optimal link capacity design problem for survivable asynchronous transfer mode (ATM) network based on the link restoration strategy. Given a projected traffic demands and the network topology, capacity and flow assignment are jointly optimized to yield the optimal capacity placement. The problem is formulated as large-scale nonlinear programming and is solved using a specific type of Lagrange method (so called Separable Augmented Lagrangian Algorithm or SALA for short). Several networks with diverse topological characteristics are used in the experiments to validate our proposed novel model, using capacity installation cost, routing cost, total network cost, used capacity and required CPU time, as performance metrics. Link restoration strategy is compared against global reconfiguration strategy using these performance metrics.

Sign in / Sign up

Export Citation Format

Share Document