AI-Driven Aeronautical Ad Hoc Networks for 6G Wireless: Challenges, Opportunities, and the Road Ahead

Creative Commons License

Bilen T., Canberk B., Sharma V., Fahim M., Duong T. Q.

SENSORS, vol.22, no.10, 2022 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 22 Issue: 10
  • Publication Date: 2022
  • Doi Number: 10.3390/s22103731
  • Journal Name: SENSORS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Biotechnology Research Abstracts, CAB Abstracts, Communication Abstracts, Compendex, EMBASE, INSPEC, MEDLINE, Metadex, Veterinary Science Database, Directory of Open Access Journals, Civil Engineering Abstracts
  • Keywords: AANETs, AI-enabled networks, AI-driven AANETs, AANET management, REAL FLIGHT DATA, DELAY, OPTIMIZATION, ACCESS
  • Istanbul Technical University Affiliated: Yes


Aeronautical ad hoc network (AANET) has been considered a promising candidate to complete the vision of "Internet in the sky" by supporting high-speed broadband connections on airplanes for 6G networks. However, the specific characteristics of AANET restrict the applicability of conventional topology and routing management algorithms. Here, these conventional methodologies reduce the packet delivery success of AANET with higher transfer delay. At that point, the artificial intelligence (AI)-driven solutions have been adapted to AANET to provide intelligent frameworks and architectures to cope with the high complexity. The AI-driven AANET can provide intelligent topology formation, sustainability, and routing management decisions in an automated fashion by considering its specific characteristics during the learning operations. More clearly, AI-driven AANETs support intelligent management architectures, overcoming conventional methodologies' drawbacks. Although AI-based management approaches are widely used in terrestrial networks, there is a lack of a comprehensive study that supports AI-driven solutions for AANETs. To this end, this article explores the possible utilization of primary AI methodologies on the road to AI-driven AANET. Specifically, the article addresses unsupervised, supervised, and reinforcement learning as primary AI methodologies to enable intelligent AANET topology formation, sustainability, and routing management. Here, we identify the challenges and opportunities of these primary AI methodologies during the execution of AANET management. Furthermore, we discuss the critical issue of security in AANET before providing open issues.