Guest Editors:
Xin Liu: Dalian University of Technology, China
Jing Jiang: University of Northumbria, UK
Zhengguo Sheng: University of Sussex, Brighton, UK
Qiuming Zhu: Nanjing University of Aeronautics and Astronautics, China
Soufiene Djahel: University of Huddersfield, UK
Submission Status: Closed | Submission Deadline: Closed
This collection is no longer accepting submissions.
With the rapid development of industrial production, Internet of Things (IoT) will experience significant expansion in both spatial scope and communication content. Various IoT services will cover diverse areas such as oceans, sky, deep space, and beyond. However, deploying large-scale base stations in wide-area ground 5G networks comes with high construction and maintenance costs. Additionally, the ground network faces challenges in providing coverage to remote areas. The Space-Air-Ground Integrated IoT is a concept that refers to the integration of satellite networks, aviation networks, and ground networks to create a comprehensive and interconnected IoT ecosystem. This integrated approach aims to overcome the limitations of traditional IoT deployments, particularly in remote and challenging environments. The Space-Air-Ground Integrated IoT envisions a network of interconnected devices, sensors, and systems that can communicate and share data seamlessly across different dimensions, including space, air, and ground. This integration allows for a wide range of applications and use cases, ranging from environmental monitoring, disaster management, transportation, agriculture, logistics, and beyond. However, due to the distinct structural characteristics of space, air, and ground networks, the signal processing for Space-Air-Ground Integrated IoT is more complex compared to ground networks. Artificial intelligence (AI) is considered a promising solution for addressing these complex network problems.
AI-enabled signal fusion can be employed to integrate signals from multiple sources, such as satellite-based sensors, airborne drones, and ground-based sensors, to obtain a more comprehensive and accurate understanding of the environment. AI-enabled anomaly detection can analyze the vast amount of data generated by Space-Air-Ground Integrated IoT systems to identify abnormal behavior, events, or patterns that may indicate potential security threats or system malfunctions. AI-enabled predictive maintenance can analyze sensor data from space, air, and ground-based devices to predict equipment failures, optimize maintenance schedules, and reduce downtime. AI-enabled energy management can optimize the energy consumption of IoT devices by dynamically adjusting their communication parameters, scheduling transmissions, and managing energy resources based on changing environmental conditions. AI-enabled spectrum management can dynamically allocate and optimize space-air-ground integrated spectrum resources based on real-time traffic patterns, interference conditions, and network requirements, enabling efficient spectrum utilization and avoiding interference.