"This dissertation proposes a new methodology for modeling and predicting network traffic. It features an adaptive architecture based on artificial neural networks and is especially suited for large-scale, global, network-centric systems. Accurate characterization and prediction of network traffic is essential for network resource sizing and real-time network traffic management. As networks continue to increase in size and complexity, the task has become increasingly difficult and current methodology is not sufficiently adaptable or scaleable. Current methods model network traffic with express mathematical equations which are not easily maintained or adjusted. The accuracy of these models is based on detailed characterization of the traffic stream which is measured at points along the network where the data is often subject to constant variation and rapid evolution. The main contribution of this dissertation is development of a methodology that allows utilization of artificial neural networks with increased capability for adaptation and scalability. Application on an operating global, broadband network, the Connexion by Boeing® network, was evaluated to establish feasibility. A simulation model was constructed and testing was conducted with operational scenarios to demonstrate applicability on the case study network and to evaluate improvements in accuracy over existing methods"--Abstract, leaf iii.
First published in 1998, this volume enters the debate on human behaviour in the form of neural networks in a spatial context. As most transportation research techniques had been developed in the 1960s and 1970s, these authors sought to bring that research into the modern era. Featuring 17 articles from 37 contributors, it begins with an overview and proceeds to examine aspects of travel behaviour, traffic flow and traffic management.
This book shares new methodologies, technologies, and practices for resolving issues associated with leveraging AI-centric modeling, data analytics, machine learning-aided models, Internet of Things-driven applications, and cybersecurity techniques in the era of Industrial Revolution 4.0. AI-Centric Modeling and Analytics: Concepts, Technologies, and Applications focuses on how to implement solutions using models and techniques to gain insights, predict outcomes, and make informed decisions. This book presents advanced AI-centric modeling and analysis techniques that facilitate data analytics and learning in various applications. It offers fundamental concepts of advanced techniques, technologies, and tools along with the concept of real-time analysis systems. It also includes AI-centric approaches for the overall innovation, development, and implementation of business development and management systems along with a discussion of AI-centric robotic process automation systems that are useful in many government and private industries. This reference book targets a mixed audience of engineers and business analysts, researchers, professionals, and students from various fields.
This book mainly discusses the most important issues in artificial intelligence-aided future networks, such as applying different ML approaches to investigate solutions to intelligently monitor, control and optimize networking. The authors focus on four scenarios of successfully applying machine learning in network space. It also discusses the main challenge of network traffic intelligent awareness and introduces several machine learning-based traffic awareness algorithms, such as traffic classification, anomaly traffic identification and traffic prediction. The authors introduce some ML approaches like reinforcement learning to deal with network control problem in this book. Traditional works on the control plane largely rely on a manual process in configuring forwarding, which cannot be employed for today's network conditions. To address this issue, several artificial intelligence approaches for self-learning control strategies are introduced. In addition, resource management problems are ubiquitous in the networking field, such as job scheduling, bitrate adaptation in video streaming and virtual machine placement in cloud computing. Compared with the traditional with-box approach, the authors present some ML methods to solve the complexity network resource allocation problems. Finally, semantic comprehension function is introduced to the network to understand the high-level business intent in this book. With Software-Defined Networking (SDN), Network Function Virtualization (NFV), 5th Generation Wireless Systems (5G) development, the global network is undergoing profound restructuring and transformation. However, with the improvement of the flexibility and scalability of the networks, as well as the ever-increasing complexity of networks, makes effective monitoring, overall control, and optimization of the network extremely difficult. Recently, adding intelligence to the control plane through AI&ML become a trend and a direction of network development This book's expected audience includes professors, researchers, scientists, practitioners, engineers, industry managers, and government research workers, who work in the fields of intelligent network. Advanced-level students studying computer science and electrical engineering will also find this book useful as a secondary textbook.
This must-read text/reference introduces the fundamental concepts of convolutional neural networks (ConvNets), offering practical guidance on using libraries to implement ConvNets in applications of traffic sign detection and classification. The work presents techniques for optimizing the computational efficiency of ConvNets, as well as visualization techniques to better understand the underlying processes. The proposed models are also thoroughly evaluated from different perspectives, using exploratory and quantitative analysis. Topics and features: explains the fundamental concepts behind training linear classifiers and feature learning; discusses the wide range of loss functions for training binary and multi-class classifiers; illustrates how to derive ConvNets from fully connected neural networks, and reviews different techniques for evaluating neural networks; presents a practical library for implementing ConvNets, explaining how to use a Python interface for the library to create and assess neural networks; describes two real-world examples of the detection and classification of traffic signs using deep learning methods; examines a range of varied techniques for visualizing neural networks, using a Python interface; provides self-study exercises at the end of each chapter, in addition to a helpful glossary, with relevant Python scripts supplied at an associated website. This self-contained guide will benefit those who seek to both understand the theory behind deep learning, and to gain hands-on experience in implementing ConvNets in practice. As no prior background knowledge in the field is required to follow the material, the book is ideal for all students of computer vision and machine learning, and will also be of great interest to practitioners working on autonomous cars and advanced driver assistance systems.
This book offers a rigorous analysis of the achievements in the field of traffic control in large networks, oriented on two main aspects: the self-similarity in traffic behaviour and the scale-free characteristic of a complex network. Additionally, the authors propose a new insight in understanding the inner nature of things, and the cause-and-effect based on the identification of relationships and behaviours within a model, which is based on the study of the influence of the topological characteristics of a network upon the traffic behaviour. The effects of this influence are then discussed in order to find new solutions for traffic monitoring and diagnosis and also for traffic anomalies prediction. Although these concepts are illustrated using highly accurate, highly aggregated packet traces collected on backbone Internet links, the results of the analysis can be applied for any complex network whose traffic processes exhibit asymptotic self-similarity, perceived as an adaptability of traffic in networks. However, the problem with self-similar models is that they are computationally complex. Their fitting procedure is very time-consuming, while their parameters cannot be estimated based on the on-line measurements. In this aim, the main objective of this book is to discuss the problem of traffic prediction in the presence of self-similarity and particularly to offer a possibility to forecast future traffic variations and to predict network performance as precisely as possible, based on the measured traffic history.
The research community has considered in the past the application of Machine Learning (ML) techniques to control and operate networks. A notable example is the Knowledge Plane proposed by D.Clark et al. However, such techniques have not been extensively prototyped or deployed in the field yet. In this thesis, we explore the reasons for the lack of adoption and posit that the rise of two recent paradigms: Software-Defined Networking (SDN) and Network Analytics (NA), will facilitate the adoption of ML techniques in the context of network operation and control. We describe a new paradigm that accommodates and exploits SDN, NA and ML, and provide use-cases that illustrate its applicability and benefits. We also present some relevant use-cases, in which ML tools can be useful. We refer to this new paradigm as Knowledge-Defined Networking (KDN). In this context, ML can be used as a network modeling technique to build models that estimate the network performance. Network modeling is a central technique to many networking functions, for instance in the field of optimization. One of the objective of this thesis is to provide an answer to the following question: Can neural networks accurately model the performance of a computer network as a function of the input traffic?. In this thesis, we focus mainly on modeling the average delay, but also on estimating the jitter and the packets lost. For this, we assume the network as a black-box that has as input a traffic matrix and as output the desired performance matrix. Then we train different regressors, including deep neural networks, and evaluate its accuracy under different fundamental network characteristics: topology, size, traffic intensity and routing. Moreover, we also study the impact of having multiple traffic flows between each pair of nodes. We also explore the use of ML techniques in other network related fields. One relevant application is traffic forecasting. Accurate forecasting enables scaling up or down the resources to efficiently accommodate the load of traffic. Such models are typically based on traditional time series ARMA or ARIMA models. We propose a new methodology that results from the combination of an ARIMA model with an ANN. The Neural Network greatly improves the ARIMA estimation by modeling complex and nonlinear dependencies, particularly for outliers. In order to train the Neural Network and to improve the outliers estimation, we use external information: weather, events, holidays, etc. The main hypothesis is that network traffic depends on the behavior of the end-users, which in turn depend on external factors. We evaluate the accuracy of our methodology using real-world data from an egress Internet link of a campus network. The analysis shows that the model works remarkably well, outperforming standard ARIMA models. Another relevant application is in the Network Function Virtualization (NFV). The NFV paradigm makes networks more flexible by using Virtual Network Functions (VNF) instead of dedicated hardware. The main advantage is the flexibility offered by these virtual elements. However, the use of virtual nodes increases the difficulty of modeling such networks. This problem may be addressed by the use of ML techniques, to model or to control such networks. As a first step, we focus on the modeling of the performance of single VNFs as a function of the input traffic. In this thesis, we demonstrate that the CPU consumption of a VNF can be estimated only as a function of the input traffic characteristics.
Artificial neural networks (ANNs) present many benefits in analyzing complex data in a proficient manner. As an effective and efficient problem-solving method, ANNs are incredibly useful in many different fields. From education to medicine and banking to engineering, artificial neural networks are a growing phenomenon as more realize the plethora of uses and benefits they provide. Due to their complexity, it is vital for researchers to understand ANN capabilities in various fields. The Research Anthology on Artificial Neural Network Applications covers critical topics related to artificial neural networks and their multitude of applications in a number of diverse areas including medicine, finance, operations research, business, social media, security, and more. Covering everything from the applications and uses of artificial neural networks to deep learning and non-linear problems, this book is ideal for computer scientists, IT specialists, data scientists, technologists, business owners, engineers, government agencies, researchers, academicians, and students, as well as anyone who is interested in learning more about how artificial neural networks can be used across a wide range of fields.
The book is a collection of high-quality peer-reviewed research papers presented at International Conference on Frontiers of Intelligent Computing: Theory and applications (FICTA 2016) held at School of Computer Engineering, KIIT University, Bhubaneswar, India during 16 – 17 September 2016. The book presents theories, methodologies, new ideas, experiences and applications in all areas of intelligent computing and its applications to various engineering disciplines like computer science, electronics, electrical and mechanical engineering.
