Towards Wireless Heterogeneity in 6G Networks

Cover
Half Title
Title Page
Copyright Page
Contents
Contributors
Chapter 1: 6G: Opportunities and challenges
	1.1 INTRODUCTION
		1.1.1 Wireless communications
		1.1.2 Types of wireless communication systems
		1.1.3 Generations of wireless communication
	1.2 5G TECHNOLOGIES
		1.2.1 Application areas of 5G
		1.2.2 Performance of 5G
			1.2.2.1 Speed
			1.2.2.2 Latency
			1.2.2.3 Error rate
	1.3 6G TECHNOLOGIES
		1.3.1 Vision and application areas of 6G technologies
			1.3.1.1 Immersive cloud XR: A broad virtual space
			1.3.1.2 Holographic communications: Extremely immersive experience
			1.3.1.3 Sensory interconnection: Fusion of all senses
			1.3.1.4 Intelligent interaction: Interactions of feelings and thoughts
		1.3.2 6G applications
	1.4 MOVING TOWARDS INDUSTRY 5.0
	1.5 CHALLENGES AND FUTURE RESEARCH DIRECTIONS
	1.6 CONCLUSION
	References
Chapter 2: Disruptive technology directions for 6G
	2.1 INTRODUCTION
	2.2 6G\'s SUPPORT FOR EMERGING APPLICATION
		2.2.1 Virtual reality
		2.2.2 Autonomous vehicles
		2.2.3 Smart cities
	2.3 CHALLENGES FOR SUPPORTING NEW APPLICATIONS
	2.4 TECHNOLOGICAL DIRECTIONS FOR 6G
		2.4.1 Artificial intelligence
		2.4.2 Blockchain technology
		2.4.3 Quantum communications
		2.4.4 Unmanned aerial vehicles
		2.4.5 3D networking
		2.4.6 THz communications
		2.4.7 Big data analytics
		2.4.8 Holographic beamforming
	2.5 THE ONGOING 6G PROJECTS
		2.5.1 Hexa-x
		2.5.2 RISE 6G
		2.5.3 New 6G
		2.5.4 Next G alliance
	References
Chapter 3: Ultra-dense deployments in next-generation networks and metaverse
	3.1 INTRODUCTION
	3.2 ULTRA-DENSE DEPLOYMENTS IN 6G
	3.3 KEY CHARACTERISTICS OF NETWORK DENSIFICATION
		3.3.1 BS densification\'s key network properties
			3.3.1.1 Significant impact of antenna height
			3.3.1.2 Multi-layer network architecture
			3.3.1.3 Dynamics of Interference
			3.3.1.4 Wireless and wired fronthaul coexistence
		3.3.2 Significant network properties from ED densification
			3.3.2.1 Intermittent transmission of devices
			3.3.2.2 Coexistence of various sorts of traffic
			3.3.2.3 Environment with a spatial correlation between EDs
	3.4 FACING THE DENSIFICATION OF NETWORKS
		3.4.1 Facing BS densification
		3.4.2 Facing ED densification
			3.4.2.1 Issues with pilot contamination and user activity monitoring
			3.4.2.2 Fronthaul capacity dependent on available BS association
	3.5 POSSIBILITIES PRESENTED BY NETWORK DENSIFICATION
		3.5.1 Making BSs functional for different services
			3.5.1.1 BSs with computing abilities
			3.5.1.2 BSs with cache functionality
			3.5.1.3 Aerial device-oriented BSs
		3.5.2 Utilizing geographical correlation between communication lines to assign pilots
		3.5.3 Developing an intellectual buffer method to reduce the fronthaul limit
	3.6 METAVERSE
		3.6.1 Emergence of the metaverse
			3.6.1.1 Contributions and related works
		3.6.2 Architecture and tools of the metaverse
			3.6.2.1 Definition and architecture
			3.6.2.2 Tools, platforms, and frameworks
		3.6.3 Communication and ultra-dense networking
			3.6.3.1 Rate-reliability-latency 3D multimedia networks
			3.6.3.2 Human-in-the-loop communication
			3.6.3.3 Real-time physical-virtual synchronization
		3.6.4 Computation
			3.6.4.1 The paradigm of cloud-edge end computing
			3.6.4.2 Effective cloud-edge end rendering for AR and VR
		3.6.5 Directions for future research in the metaverse
	3.7 CONCLUSIONS
		3.7.1 Ultra-densification of networks
		3.7.2 Metaverse
	References
Chapter 4: Cognitive radios
	4.1 COGNITIVE RADIOS
	4.2 COGNITIVE RADIOS AND SPECTRUM SENSING
	4.3 THE COGNITIVE CYCLE
		4.3.1 Underlay
		4.3.2 Overlay
		4.3.3 Interweave
	4.4 TEMPERATURE INTERFERENCE IN CR
	4.5 DYNAMIC ALLOCATION
	4.6 REASONING
	4.7 ADAPTATION
	4.8 SPECTRUM SENSING IN COGNITIVE RADIOS
	4.9 COGNITIVE RADIOS AND SPECTRUM DATABASE
	4.10 COGNITIVE RADIO AND 6G NETWORK
	4.11 CONCLUSION
	References
Chapter 5: A novel energy-efficient optimization technique for intelligent transportation systems
	5.1 INTRODUCTION
		5.1.1 History
		5.1.2 Performance of wireless networks by using IRS
		5.1.3 Role of IRS in healthcare
	5.2 ENERGY EFFICIENCY OPTIMIZATION WITH IRS
		5.2.1 Conventional methods to optimize the EE
		5.2.2 Optimization techniques
		5.2.3 Relaxation and projection
		5.2.4 Majorization-minimization (MM)
		5.2.5 DL/ML-based techniques for IRS-aided networks
	5.3 SYSTEM MODEL AND PROBLEM DESIGN
		5.3.1 Channel estimation
		5.3.2 Design and analysis of EE
		5.3.3 IRS phase optimization by using clustering
		5.3.4 Passive beamforming for the end user based on location
	5.4 NUMERICAL RESULTS
	5.5 IMPLEMENTATION OF IRS: CHALLENGES AND RESEARCH DIRECTIONS
	5.6 CURRENT CHALLENGES AND RESEARCH DIRECTIONS
	5.7 CONCLUSION
	References
Chapter 6: AI applications at the scheduling and resource allocation schemes in web medium
	6.1 INTRODUCTION
		6.1.1 The first level: Basic
		6.1.2 Second: Managed
		6.1.3 Predictive at the third level
		6.1.4 The fourth level: Flexible
		6.1.5 Fifth level: Autonomic
	6.2 RELATED WORK
	6.3 OBJECTIVES OF THE STUDY AND STRATEGIES
		6.3.1 Algorithm for load balancing methods using priority ordering
		6.3.2 Coverage-based cell selection algorithm
		6.3.3 Cell degree-based resource allocation (CBRA)
		6.3.4 Distributed routing and scheduling techniques
	6.4 THE PROPOSED MODELS IN RESOURCE ALLOCATION
		6.4.1 Load balancing as a resolution for fog computing
			6.4.1.1 Reducing energy consumption and violation of SLA
			6.4.1.2 Delay-aware scheduling and load balancing: The solution in a four-tier architecture
			6.4.1.3 Task allocation and secure deduplication: Assistance from fog computing
			6.4.1.4 Data migration over cloud or fog based on applications
			6.4.1.5 Fog environment issues of load balancing and delay-aware scheduling
	6.5 PROPOSED MODEL IN SCHEDULING
	6.6 CONCLUSION
	References
Chapter 7: 6G vision on edge artificial intelligence
	7.1 INTRODUCTION
		7.1.1 Emerging technologies in 6G wireless network
			7.1.1.1 Optical-free technology
			7.1.1.2 Quantum technology
			7.1.1.3 Native network slicing
			7.1.1.4 Integrated access backhaul networks
			7.1.1.5 Holographic beam forming
	7.2 EFFECTIVE TRAINING MODELS
		7.2.1 Edge AI learning models
			7.2.1.1 Federated learning
			7.2.1.2 Decentralized learning
			7.2.1.3 Split learning
			7.2.1.4 Distributed reinforcement learning
			7.2.1.5 Trustworthy learning
		7.2.2 Wireless technique edge training
			7.2.2.1 Over-the-air computation
			7.2.2.2 Massive MIMO
			7.2.2.3 Reconfigurable intelligence surface
	7.3 EFFECTIVE EDGE INFERENCE
		7.3.1 Horizontal edge inference
			7.3.1.1 ED distributed inference
			7.3.1.2 ES cooperative inference
		7.3.2 Vertical edge inference
			7.3.2.1 ED-ES co-inference
			7.3.2.2 Low latency and ultra-reliable communication
			7.3.2.3 Task-oriented communication
	7.4 ARCHITECTURE FOR EDGE AI IN 6G WIRELESS NETWORK
		7.4.1 Centralized architecture
		7.4.2 Decentralized architecture
		7.4.3 Hybrid architecture
		7.4.4 Self-learning architecture
		7.4.5 End-to-end architecture
		7.4.6 Data governance
			7.4.6.1 Independent data plane
			7.4.6.2 Multiplayer and multi-domain roles
			7.4.6.3 Management and orchestration of edge AI
	7.5 EDGE AI APPLICATION TOWARDS 6G
		7.5.1 Characteristics of metaverse
			7.5.1.1 Immersive
			7.5.1.2 Multi-technology
			7.5.1.3 Interoperability
			7.5.1.4 Sociability
			7.5.1.5 Longevity
		7.5.2 Edge AI-based metaverse architecture
			7.5.2.1 Edge cloud metaverse (ECM) architecture
			7.5.2.2 Mobile ECM architecture
			7.5.2.3 Decentralized metaverse architecture
	7.6 CHALLENGES AND APPLICATIONS OF EDGE AI IN 6G
		7.6.1 Challenges of edge AI
			7.6.1.1 Adversarial learning and adaptation
			7.6.1.2 Interpretable AI
			7.6.1.3 Quality of experience
			7.6.1.4 Interactive AI
			7.6.1.5 Detecting and predicting human intention
			7.6.1.6 Intelligent human-to-machine communications
		7.6.2 Some more futuristic applications of edge AI in 6G
			7.6.2.1 Industrial Internet of Things (IIoT)
			7.6.2.2 Healthcare
			7.6.2.3 Autonomous driving vehicles
			7.6.2.4 Security and privacy
			7.6.2.5 Education
	7.7 CONCLUSION
	References
Chapter 8: Artificial intelligence-based energy efficiency models in green communications towards 6G
	8.1 INTRODUCTION
	8.2 REVIEW ANALYSIS ISSUES TOWARDS GREEN 6G
		8.2.1 Existing polls
		8.2.2 6G research concerns towards 6G
	8.3 PARADIGMS OVERVIEW OF 6G AND ARTIFICIAL INTELLIGENCE METHODS FOR EFFECTIVE ENERGY COMMUNICATIONS
		8.3.1 Several 6G paradigms
			8.3.1.1 Terahertz communications
			8.3.1.2 Space-air-ground integrated networks
			8.3.1.3 Energy harvesting
			8.3.1.4 AI-based communications
		8.3.2 Classical AI algorithms
			8.3.2.1 Heuristic algorithms
				8.3.2.1.1 Optimization of particle swarms
				8.3.2.1.2 Optimization of ant colonies
				8.3.2.1.3 Genetic algorithm
			8.3.2.2 Traditional machine learning
				8.3.2.2.1 Regression analysis
				8.3.2.2.2 Support vector machine
				8.3.2.2.3 Clustering with K-means
		8.3.3 Deep learning
			8.3.3.1 Development of deep learning models
			8.3.3.2 Deep reinforcement learning
		8.3.4 New training strategies
			8.3.4.1 Learning transfer
			8.3.4.2 Collaborative learning
				8.3.4.2.1 Summary
	8.4 OPEN RESEARCH PROBLEMS
		8.4.1 Green BS management for 6 GNet
		8.4.2 Low-energy space-air-ground integrated networks
		8.4.3 AI-based energy-efficient transmissions
		8.4.4 Artificial intelligence-enhanced energy harvesting and sharing
		8.4.5 AI-enabled network security
		8.4.6 Design of a lightweight AI model and hardware
	8.5 SOLUTION FOR RESEARCH PROBLEMS
	8.6 CONCLUSION
	References
Chapter 9: Centralized traffic engineering
	9.1 INTRODUCTION
	9.2 TRAFFIC ENGINEERING IN A SOFTWARE-DEFINED NETWORKING
		9.2.1 Flow setup in SDN
		9.2.2 SDN and network function virtualization (NFV)
	9.3 COMPUTING PARADIGMS
		9.3.1 Cloud computing
		9.3.2 Fog computing
		9.3.3 Mist computing
	9.4 INTELLIGENT TRANSPORTATION IN SMART CITIES
		9.4.1 SD-IoV platform utilizing cloud and fog computing
		9.4.2 SD-IoV platform utilizing mist, cloud, and fog computing
		9.4.3 Topology based slicing in SD-IoV platform
	9.5 OPEN ISSUES
	9.6 CONCLUSION
	References
Chapter 10: Cooperative network paradigm for device-centric nodes
	10.1 INTRODUCTION
	10.2 TYPES OF WIRELESS NODE COOPERATION
		10.2.1 Cooperative relaying
		10.2.2 Cooperative beamforming
		10.2.3 Cooperative sensing
	10.3 SCENARIOS FOR NODE COOPERATION
	10.4 DEVICE COOPERATION
	10.5 CONCLUSION
	References
Chapter 11: Edge computing and edge intelligence
	11.1 INTRODUCTION
	11.2 LITERATURE SURVEY
	11.3 EMERGING ARCHITECTURE
		11.3.1 Near-edge layer
		11.3.2 Mid-edge layer
		11.3.3 Far-edge layer
	11.4 HARDWARE EVOLUTION IN EC/EI
		11.4.1 Data center evolution
	11.5 IoT GATEWAYS/EDGE SERVERS
	11.6 SMART SENSORS/END NODES
	11.7 SOFTWARE EVOLUTION
		11.7.1 IoT edge computing
	11.8 ECN IoT GATEWAY OS AND LIGHTWEIGHT OS
	11.9 CURRENT STATE-OF-THE-ART IN EDGE INTELLIGENCE
	11.10 EDGE COMPUTING ARCHITECTURE FOR INDUSTRY
		11.10.1 Industrial Internet Consortium architecture
	11.11 MULTI-ACCESS EDGE COMPUTING ARCHITECTURE
	11.12 COMPUTATION OFFLOADING IN MEC
		11.12.1 Application of cybertwin for 6G networks
	11.13 TIME ALLOCATION POLICY IN WIRELESS POWERED MOBILE EDGE COMPUTING
	11.14 INTELLIGENT REFLECTING SURFACES FOR MEC IN 6G NETWORKS
	11.15 CONCLUSION AND FUTURE SCOPE
	References
Chapter 12: Network virtualization
	12.1 INTRODUCTION
	12.2 NETWORK FUNCTION VIRTUALIZATION EVOLUTION
		12.2.1 Traditional network
		12.2.2 NFV introduction
	12.3 NETWORK VIRTUALIZATION BACKGROUND
		12.3.1 Network function virtualization
		12.3.2 Software-defined networking
		12.3.3 Multi-access edge computing
		12.3.4 Distributed management task force
	12.4 NETWORK VIRTUALIZATION CHALLENGES
		12.4.1 Network softwarization of SDN/NFV
		12.4.2 5G and network slicing
		12.4.3 Device virtualization for end users
		12.4.4 Security and privacy
	12.5 NETWORK VIRTUALIZATION ARCHITECTURE
		12.5.1 Infrastructure layer
		12.5.2 Control layer
		12.5.3 Application layer
	12.6 NETWORK VIRTUALIZATION IN A 5G NETWORK
	12.7 NETWORK SLICING FOR VIRTUALIZATION
		12.7.1 First/primary block
		12.7.2 Service layer
		12.7.3 Network function layer
		12.7.4 Infrastructure layer
		12.7.5 Second/controller block
	12.8 VIRTUALIZATION IN A 6G NETWORK
		12.8.1 Enhanced network slicing
			12.8.1.1 Role of artificial intelligence in preparation phase
			12.8.1.2 AI for planning
			12.8.1.3 AI for operation
		12.8.2 Edge computing and network function virtualization
		12.8.3 Multi-cloud integration
			12.8.3.1 Architectural challenge
			12.8.3.2 On-premises integration structure maintenance
			12.8.3.3 Agility
			12.8.3.4 Data protection
			12.8.3.5 Containers and microservices
			12.8.3.6 Network automation
	12.9 6G END-TO-END NETWORK AUTOMATION CHALLENGES
	12.10 BENEFITS OF NETWORK VIRTUALIZATION
		12.10.1 Improved resource utilization
		12.10.2 Simplified network management
		12.10.3 Increased security
		12.10.4 Scalability
		12.10.5 Flexibility
	12.11 CONCLUSION
	References