This book provides a comprehensive examination of Unmanned Aerial Vehicles (UAV) swarm collaboration from a networking perspective. It systematically analyzes key components such as network topology construction, efficient routing algorithms and resource management strategies.

The second chapter addresses adaptive clustering and dynamic network planning, enabling UAV swarms to adjust their topologies and maintain robust structures in fluctuating environments. The third chapter introduces intelligent routing algorithms designed to optimize network resilience and performance metrics, including lifetime, packet delivery rate and throughput. Chapter four investigates resource scheduling challenges proposing virtualization-based strategies for the optimal allocation of computational and communication resources. Chapters five through seven discuss the opportunities and challenges posed by emerging network technologies. It includes encompassing semantic communication for enhanced data transfer efficiency, the application of distributed learning techniques (e.g., federated and reinforcement learning) for intelligent UAV swarm networks and deterministic networking approaches that ensure low-latency, reliable control in UAV precision-critical operations.

Overall, this book serves as an authoritative reference that integrates state-of-the-art technologies and algorithmic designs to address the multifaceted challenges and opportunities in UAV swarm networks. It's designed for advanced-level students, professors, engineers, and researchers learning and working in the fields of the loT Networks. Industry managers, partitioners and government research agencies working in this field will also find this book a useful reference.

Presents a networking perspective for Unmanned Aerial Vehicles (UAV) Swarm Cooperation Discusses the key components of this networking technology including establishing a suitable network topology Implementing efficient routing algorithms and developing resource management strategies

Autorentext

Haipeng Yao (IET Fellow) is a Professor in Beijing University of Posts and Telecommunications. Haipeng Yao received his Ph.D. in the Department of Telecommunication Engineering at University of Beijing University of Posts and Telecommunications in 2011. His research interests include future network architecture, network artificial intelligence, networking, space-terrestrial integrated network, network resource allocation and dedicated networks. He has published more than 200 papers in prestigious peer-reviewed journals and conferences. He won the IEEE ICC 2022 Best Paper Award, IEEE IWCMC 2019, 2021 Best Paper Award, IEEE ICCC 2020 Best Paper Award, IEEE HotICN 2020 Best Student Paper Award, authorized more than 100 national invention patents. He is a fellow of IET, a senior member of IEEE. Dr. Yao has served as an Associate Editor of IEEE Transactions on Mobile Computing, IEEE Transactions on Sustainable Computing, IEEE Network, IEEE ACCESS, and a Guest Editor of IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY and Chain Communication. He has also served as a member of the technical program committee as well as the Symposium Chair for a number of international conferences, including IEEE IWCMC 2019 Symposium Chair, IEEE TrustCom 2021 Symposium Chair and an ACM TUR-C SIGSAC2020 Publication Chair.

Tianle Mai received a Ph.D. degree in the School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing. His research interests include unmanned swarm networks, future network architecture, network artificial intelligence, multi-agent system, space-terrestrial integrated network, network resource allocation and dedicated networks. He has published more than 40 papers in prestigious peer-reviewed journals and conferences. He won the IEEE ICC 2022 Best Paper Award, IEEE IWCMC 2021 Best Paper Award, IEEE ICCC 2020 Best Paper Award, IEEE HotICN 2020 Best Student Paper Award.

Inhalt

1. Introduction of Unmanned Aerial Vehicles Swarm Networks.- 2. Adaptive UAV Swarm Networks Topology Organization.- 2.1. Introduction of Adaptive UAV Swarm Clustering and Networking.- 2.2. Fission Spectral Clustering Strategy for UAV Swarm Networks.- 2.3. Graph Attentional Based Agglomerative Cluster for UAV Swarm Networks.- 2.4. Adaptive State-aware UAV Swarm Networking Organization.- 3. Intelligent UAV Swarm Networks Routing.- 3.1. Introduction of Intelligent UAV Swarm Networks Routing.- 3.2. Evolutionary Game based Dynamic Routing in UAV Swarm Networks.- 3.3. Cooperative Learning based Dynamic Routing UAV Swarm Networks.- 3.4. Multi-agent Reinforcement Learning aided UAV Swarm Routing.- 4. On-demand UAV Network Resource Scheduling.- 4.1. Introduction of UAV Network Resource Scheduling.- 4.2. Graph Transformer Aided Resource Virtualization Embedding.- 4.3. Privacy-Driven Security-Aware Task Scheduling in Swarm Network.- 4.4. Stackelberg Game-Based Offloading Strategy for Swarm Networks.- 5. Semantic Communication Empowered UAV Swarm Networks.- 5.1. Introduction of Semantic Communication.- 5.2. Semantic Communication Aided UAV Swarm Networks.- 5.3. Incentive Semantic-aware UAV Swarm Networks Coordination.- 6. Federated Learning empowered UAV Swarm Networks.- 6.1. Introduction of Federated Learning.- 6.2. Clustered Federated Learning in Heterogeneous UAV Swarms Networks.- 6.3. Automatic Auction for Federated Learning in UAV Swarms Networks.- 7. Deterministic Networking Empowered UAV Swarm.- 7.1. Introduction of Deterministic Networking.- 7.2. Learning-Based Deterministic Traffic Scheduling for UAV Swarm.- 7.3. Hierarchical Scheduling Mechanism for Deterministic Traffic for UAV Swarm.- 8. Conclusions.