AUV-Aided Deep-Sea Internet of Things: A Machine Learning Perspective

The deep-sea Internet of Things (DS-IoT) enhances massive data acquisition capabilities and augments the safety of industrial operations, serving as a powerful technology for exploiting rich and precious natural resources. However, the unique physical environment of the deep sea poses significant challenges in establishing a DS-IoT network. In this article, to improve the capabilities of deep-sea information collection, transmission, and processing, we conceive a six-layer system architecture for the future DS-IoT, which consists of layers for environment sensing, information collection, long-distance information transmission, control and information aggregation, fusion and processing, and application and service. Then, considering the complexity of the deep-sea environment that harms the stability of underwater networks, traditional networking techniques will falter, which motivates this article to propose machine learning-aided key techniques, focusing on communication, sensing, processing, and network aspects. Furthermore, we discuss the research on efficient trajectory planning and task scheduling for multi-autonomous underwater vehicles collaboration. The simulation results indicate that our method achieves reductions of 66.84% and 89.23% in scheduling route length and reasoning time, respectively, compared to traditional methods. Finally, we present the challenges faced by the DS-IoT and potential research trends.