Software-defined Infrastructure

Tran Tuan Chu obtained his PhD from Paris-Est Créteil University (UPEC), France, in 2023. His research focuses on Software-Defined Infrastructure, and IoT–Digital Twins.Mohamed Aymen Labiod is Associate Professor at UPEC, France. His research focuses on 5G and 6G architectures, network slicing, mobile and multiaccess networks and multi-connectivity, among other topics.Brice Augustin is Associate Professor at UPEC, France. His research focuses on Quality of Experience (QoE) in 5G and cloud-based multimedia services, exploring adaptive network mechanisms and edge computing.Abdelhamid Mellouk is Full-time University Professor, Director of the IT4H High School Engineering Department and Head of the TincNET Research Team, UPEC, France. He is also the founder of Network Control Research and Curricula activities at UPEC, President of the Policies and Programs commission at the National Council for Scientific Research and Technologies, a HCERES Expert, a CNU member and Co-President of the DS-AI Systematic Deep Tech Hub.

• Preface ixList of Acronyms xiiiIntroduction xviiChapter 1 Healthcare Internet of Things: The State of the Art 11.1 H-IoT network landscape 21.2 Technology emergence in H-IoT 101.2.1 Edge computing in H-IoT 121.2.2 Software-defined network in H-IoT 161.3. Learned lessons and neglected opportunities 281.3.1 Learned lessons 281.3.2 Neglected opportunities 371.4 Conclusion 38Chapter 2. A Novel Network Infrastructure Concept 392.1 Introduction 392.2 Related work 442.2.1 Software-defined network 452.2.2 5G novel network perspective 452.2.3 Software-defined infrastructure 462.2.4 Software-defined vehicular network 472.2.5 Software-defined unmanned aerial vehicular network 482.2.6 Other potential software-defined hardware blocks 492.3 The evolution of SDI 502.3.1 Research gap 502.3.2 SDI extension 512.3.3 Proposal of our architecture 522.3.4 Suggested technology adjustments 542.3.5 Prospective interaction within the SDI ecosystem 562.3.6 Software-defined infrastructure’s benefit recap 572.4 Unified functional model formalization 582.4.1 Description of the model 582.4.2 Structure of the model 592.5 Description of the experiments 642.5.1 Implementation details 662.5.2 Approach 1: opportunistic coverage enhancement 712.5.3 Approach 2: connection recovery 722.5.4 Approach 3: self-assisted coverage deployment and data transportation 742.5.5 Approach 4: priority orchestration in high-density network 762.6 Improvement evaluation approaches 782.6.1 Opportunistic coverage enhancement 782.6.2 Connection recovery 802.6.3 Self-assisted coverage deployment and data transportation 822.6.4 Priority orchestration in high-density network 832.7 Conclusion 86Chapter 3 SMART Connection Migration 893.1 Introduction 893.2 Related work 923.2.1 Virtual machine migration 933.2.2 Container migration 933.2.3 TCP-based connection migration 943.2.4 QUIC-based connection migration 953.2.5 Motivation 963.3 Solution design 973.3.1 Sequence diagram comparison 973.3.2 System design 983.3.3 Prospective impact 993.4 Performance evaluation 1003.4.1 Experimental environment 1003.4.2 Experiment scenario 1013.4.3 Influence of delay on the connection migration process 1033.4.4 The influence of migration frequency on the connection migration time 1033.5 Conclusion 104Chapter 4 Generic Adaptive Deep Learning-based Multipath Scheduler Selector 1074.1 Introduction 1074.2 Related work 1104.2.1 Multipath transport protocols 1104.2.2 Multipath scheduling algorithms 1114.2.3 Multipath scheduling performance over heterogeneous paths 1134.3 Prototype design 1144.3.1 Scheduler selector paradigm 1144.3.2 Prototype design 1154.4 Simulated evaluation 1174.4.1 Experiment setup 1174.4.2 Initial dataset analysis 1194.4.3 Traditional machine learning’s performance evaluation 1214.4.4 Deep learning’s performance evaluation 1234.5 Practical evaluation 1254.5.1 Brief overview of GADaM 1254.5.2 Extensible modular scheduler evaluating framework 1284.5.3 Experiment environment 1294.5.4 Trial run 1324.5.5 Actual run 1364.5.6 In-house static environment 1384.5.7 Metro line environment 1394.5.8 In-vehicle environment 1404.6 Limitations 1434.7 Conclusion 145Conclusions and Perspectives 147References 151Index 171