Improving aerial image transmission quality using trajectory-aided OLSR in flying ad hoc networks

• Published in: EURASIP journal on wireless communications and networking 2020-07, Vol.2020 (1), p.1-21, Article 140
• Main Authors: Hou, Chen, Xu, Zhexin, Jia, Wen-Kang, Cai, Jianyong, Li, Hui
• Format: Article
• Language: English
• Subjects: Ad hoc networks; Battlefields; Communications Engineering; Engineering; Flying ad hoc network; Image quality; Image transmission; Information Systems Applications (incl.Internet); Machine Learning and Deep Learning Methods for Wireless Network Applications; Mapping; Military applications; Mission planning; Networks; Progressive transmission; Q-learning; Search and rescue missions; Signal,Image and Speech Processing; Space missions; Store and forward; Trajectory-OLSR; Unmanned aerial vehicles
• ISSN: 1687-1499; 1687-1472; 1687-1499
• DOI: 10.1186/s13638-020-01707-3

UAVs have been widely used in various applications. Auto coordination of multiple UAVs through AI or mission planning software can provide significant improvements in many applications, including battlefield reconnaissance, topographical mapping, and search and rescue missions. Under such circumstances, the trajectory information is known for a set amount of time, and the system’s performance relies on the network between UAVs and their base. Here, a new protocol is proposed that takes the trajectory of UAVs as a known factor and uses it to improve optimized link state routing (OLSR). In this protocol, Q -learning is adopted to find the best route for the system. Additionally, a packet forwarding arrangement is described that addresses the common problem of deteriorating image quality often faced by UAVs. The simulation results show significant improvements over OLSR and GPSR under a sparsely distributed scenario, with the packet delivery ratio improved by over 30% and over 40 s reduction in the end-to-end delay.