Screen LibraryDeveloping networks using artificial intelligence /
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 lea...
Saved in:
| Main Authors: | |
|---|---|
| Group Author: | ; |
| Published: |
Springer,
|
| Publisher Address: | Cham : |
| Publication Dates: | [2019] |
| Literature type: | Book |
| Language: | English |
| Series: |
Wireless networks,
|
| Subjects: | |
| Summary: |
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. |
| Carrier Form: | xi, 248 pages : illustrations ; 25 cm. |
| Bibliography: | Includes bibliographical references. |
| ISBN: |
9783030150273 3030150275 9783030150297 3030150291 9783030150303 3030150305 |
| Index Number: | Q335 |
| CLC: | TP18 |
| Call Number: | TP18/Y25 |
| Contents: |
Intro; Preface; Acknowledgments; Contents; 1 Introduction; 1.1 Background; 1.2 Overview of SDN and Machine Learning; 1.2.1 Software Defined Networking (SDN); 1.2.2 Machine Learning; 1.2.2.1 Supervised Learning; 1.2.2.2 Unsupervised Learning; 1.2.2.3 Reinforcement Learning; 1.3 Related Research and Development; 1.3.1 3GPP SA2; 1.3.2 ETSI ISG ENI; 1.3.3 ITU-T FG-ML5G; 1.4 Organizations of This Book; 1.5 Summary; 2 Intelligence-Driven Networking Architecture; 2.1 Network AI: An Intelligent Network Architecture for Self-Learning Control Strategies in Software Defined Networks 2.1.1 Network Architecture2.1.1.1 Forwarding Plane; 2.1.1.2 Control Plane; 2.1.1.3 AI Plane; 2.1.2 Network Control Loop; 2.1.2.1 Action Issue; 2.1.2.2 Network State Upload; 2.1.2.3 Policy Generation; 2.1.3 Use Case; 2.1.4 Challenges and Discussions; 2.1.4.1 Communication Overhead; 2.1.4.2 Training Cost; 2.1.4.3 Testbeds; 2.2 Summary; References; 3 Intelligent Network Awareness; 3.1 Intrusion Detection System Based on Multi-Level Semi-Supervised Machine Learning; 3.1.1 Proposed Scheme (MSML); 3.1.1.1 Pure Cluster Extraction (PCE); 3.1.1.2 Pattern Discovery (PD) 3.1.1.3 Fine-Grained Classification (FC)3.1.1.4 Model Updating; 3.1.1.5 The Hyper-Parameters; 3.1.2 Evaluation; 3.1.2.1 Dataset; 3.1.2.2 Data Pre-process; 3.1.2.3 Evaluation Criteria; 3.1.2.4 Baseline Model; 3.1.2.5 MSML; 3.2 Intrusion Detection Based on Hybrid Multi-Level Data Mining; 3.2.1 The Framework of HMLD; 3.2.2 HMLD with KDDCUP99; 3.2.2.1 KDDCUP99 Dataset; 3.2.2.2 MH-DE Module; 3.2.2.3 MH-ML Module; 3.2.2.4 MEM Module; 3.2.3 Experimental Results and Discussions; 3.2.3.1 Evaluation Criteria; 3.2.3.2 Experiments and Analysis 3.3 Abnormal Network Traffic Detection Based on Big Data Analysis3.3.1 System Model; 3.3.1.1 Normal Traffic Selection Model; 3.3.1.2 Abnormal Traffic Selection Model; 3.3.1.3 Abnormal Traffic Selection Model; 3.3.2 Simulation Results and Discussions; 3.3.2.1 Data Set; 3.3.2.2 Simulation Results; 3.3.2.3 Discussing Result of No. 8 and No. 11; 3.3.2.4 Discussing Result of No. 5 and No. 7; 3.3.2.5 Discussing Result of No. 3 and No. 4; 3.4 Summary; References; 4 Intelligent Network Control; 4.1 Multi-Controller Optimization in SDN; 4.1.1 System Model; 4.1.1.1 Network Model 4.1.1.2 Communication Model4.1.1.3 Computation Model; 4.1.1.4 Problem Formulation; 4.1.2 Methodology; 4.1.2.1 PSO Aided Near-Optimal Multi-Controller Placement; 4.1.2.2 Resource Management Relying on Deep Q-Learning; 4.1.3 Simulation Results; 4.2 QoS-Enabled Load Scheduling Based on ReinforcementLearning; 4.2.1 System Description; 4.2.1.1 Energy Internet; 4.2.1.2 Software-Defined Energy Internet; 4.2.1.3 Controller Mind framework; 4.2.1.4 Re-Queuing Module; 4.2.1.5 Info-Table Module; 4.2.1.6 Learning Module; 4.2.2 System Model; 4.2.2.1 Re-Queuing Model; 4.2.2.2 Workload Model |