Date of Award
Dissertation - Open Access
Doctor of Philosophy in Electrical Engineering & Computer Science
College of Engineering
Houbing Song, Ph.D.
First Committee Member
Tianyu Yang, Ph.D.
Second Committee Member
Richard S. Stansbury, Ph.D.
Third Committee Member
Hever Y. Moncayo, Ph.D.
Fourth Committee Member
Radu F. Babiceanu, Ph.D.
Fueled by the advancement of 5G new radio (5G NR), rapid development has occurred in many fields. Compared with the conventional approaches, beamforming and network slicing enable 5G NR to have ten times decrease in latency, connection density, and experienced throughput than 4G long term evolution (4G LTE). These advantages pave the way for the evolution of Cyber-physical Systems (CPS) on a large scale. The reduction of consumption, the advancement of control engineering, and the simplification of Unmanned Aircraft System (UAS) enable the UAS networking deployment on a large scale to become feasible. The UAS networking can finish multiple complex missions simultaneously. However, the limitations of the conventional approaches are still a big challenge to make a trade-off between the massive management and efficient networking on a large scale.
With 5G NR and machine learning, in this dissertation, my contributions can be summarized as the following:
- I proposed a novel Optimized Ad-hoc On-demand Distance Vector (OAODV) routing protocol to improve the throughput of Intra UAS networking. The novel routing protocol can reduce the system overhead and be efficient.
- To improve the security, I proposed a blockchain scheme to mitigate the malicious basestations for cellular connected UAS networking and a proof-of-traffic (PoT) to improve the efficiency of blockchain for UAS networking on a large scale.
- Inspired by the biological cell paradigm, I proposed the cell wall routing protocols for heterogeneous UAS networking. With 5G NR, the inter connections between UAS networking can strengthen the throughput and elasticity of UAS networking.
- With machine learning, the routing schedulings for intra- and inter- UAS networking can enhance the throughput of UAS networking on a large scale. The inter UAS networking can achieve the max-min throughput globally edge coloring. I leveraged the upper and lower bound to accelerate the optimization of edge coloring.
This dissertation paves a way regarding UAS networking in the integration of CPS and machine learning. The UAS networking can achieve outstanding performance in a decentralized architecture. Concurrently, this dissertation gives insights into UAS networking on a large scale. These are fundamental to integrating UAS and National Aerial System (NAS), critical to aviation in the operated and unmanned fields. The dissertation provides novel approaches for the promotion of UAS networking on a large scale. The proposed approaches extend the state-of-the-art of UAS networking in a decentralized architecture. All the alterations can contribute to the establishment of UAS networking with CPS.
Scholarly Commons Citation
Wang, Jian, "Machine Learning for Unmanned Aerial System (UAS) Networking" (2021). Doctoral Dissertations and Master's Theses. 622.
Digital Communications and Networking Commons, Electrical and Electronics Commons, Other Computer Engineering Commons, Other Electrical and Computer Engineering Commons, Systems and Communications Commons