Towards Cognitive Autonomous Networks: Network Management Automation for 5G and Beyond

Cover
List of Contributors
Foreword I
Foreword II
Preface
1 The Need for Cognitive Autonomy in Communication Networks
	1.1 Complexity in Communication Networks
	1.2 Cognition in Network Management Automation
	1.3 Taxonomy for Cognitive Autonomous Networks
	References
2 Evolution of Mobile Communication Networks
	2.1 Voice and Low‐Volume Data Communications
	2.2 Mobile Broadband Communications
	2.3 Network Evolution – Towards Cloud‐Native Networks
	2.4 Multi‐Service Mobile Communications
	2.5 Evolution of Transport Networks
	2.6 Management of Communication Networks
	2.7 Conclusion – Cognitive Autonomy in 5G and Beyond
	References
3 Self‐Organization in Pre‐5G Communication Networks
	3.1 Automating Network Operations
	3.2 Network Deployment and Self‐Configuration
	3.3 Self‐Optimization
	3.4 Self‐Healing
	3.5 Support Function for SON Operation
	3.6 5G SON Support and Trends in 3GPP
	3.7 Concluding Remarks
	References
4 Modelling Cognitive Decision Making
	4.1 Inspirations from Bio‐Inspired Autonomy
	4.2 Self‐Organization as Visible Cognitive Automation
	4.3 Human Cognition
	4.4 Modelling Cognition: A Perception‐Reasoning Pipeline
	4.5 Implications for Network Management Automation
	4.6 Conclusions
	References
5 Classic Artificial Intelligence: Tools for Autonomous Reasoning
	5.1 Classical AI: Expectations and Limitations
	5.2 Expert Systems
	5.3 Closed‐Loop Control Systems
	5.4 Case‐Based Reasoning
	5.5 Fuzzy Inference Systems
	5.6 Bayesian Networks
	5.7 Time Series Forecasting
	5.8 Conclusion
	References
6 Machine Learning: Tools for End‐to‐End Cognition
	6.1 Learning from Data
	6.2 Neural Networks
	6.3 A Dip into Deep Neural Networks
	6.4 Reinforcement Learning
	6.5 Conclusions
	References
7 Cognitive Autonomy for Network Configuration
	7.1 Context Awareness for Auto‐Configuration
	7.2 Multi‐Layer Co‐Channel PCI Auto‐Configuration
	7.3 Energy Saving Management in Multi‐Layer RANs
	7.4 Dynamic Baselines for Real‐Time Network Control
	7.5 Conclusions
	References
8 Cognitive Autonomy for Network‐Optimization
	8.1 Self‐Optimization in Communication Networks
	8.2 Q‐Learning Framework for Self‐Optimization
	8.3 QL for Mobility Robustness Optimization
	8.4 Fuzzy Q‐Learning for Tilt Optimization
	8.5 Interference‐Aware Flexible Resource Assignment in 5G
	8.6 Summary and Open Challenges
	References
9 Cognitive Autonomy for Network Self‐Healing
	9.1 Resilience and Self‐Healing
	9.2 Overview on Cognitive Self‐Healing
	9.3 Anomaly Detection in Radio Access Networks
	9.4 Diagnosis and Remediation in Radio Access Networks
	9.5 Knowledge Sharing in Cognitive Self‐Healing
	9.6 The Future of Self‐Healing in Cognitive Mobile Networks
	References
10 Cognitive Autonomy in Cross‐Domain Network Analytics
	10.1 System State Modelling for Cognitive Automation
	10.2 Real‐Time User‐Plane Analytics
	10.3 Real‐Time Customer Experience Management
	10.4 Mobile Backhaul Automation
	10.5 Summary
	References
11 System Aspects for Cognitive Autonomous Networks
	11.1 The SON Network Management Automation System
	11.2 NMA Systems as Multi‐Agent Systems
	11.3 Post‐Action Verification of Automation Functions Effects
	11.4 Optimistic Concurrency Control Using Verification
	11.5 A Framework for Cognitive Automation in Networks
	11.6 Synchronized Cooperative Learning in CANs
	11.7 Inter‐Function Coopetition – A Game Theoretic Opportunity
	11.8 Summary and Open Challenges
	References
12 Towards Actualizing Network Autonomy
	12.1 Cognitive Autonomous Networks – The Vision
	12.2 Modelling Networks: The System View
	12.3 The Development – Operations Interface in CANs
	12.4 CAN as Data Intensive Network Operations
	References
Index
End User License Agreement