QUAT-DEM: Quaternion-DEMATEL based neural model for mutual coordination between UAVs

Networking between autonomously flying aerial vehicles requires efficient control and sustainable path for data transmission. Aerial nodes are extremely dynamic and provide a vast range of applications especially focusing on surveillance and data acquisition. However, these dynamic nodes are prone to unstable connectivity which hinders network operations, and also decreases the network lifetime. Such issues directly influence the control and relaying over aerial vehicles. Thus, it becomes essential to have an efficient strategy for controller selection and autonomous relaying. In this paper, a quaternion based neural model is proposed, which uses Decision Making Trial and Evaluation Laboratory Technique (DEMATEL) for the selection of network controllers and relays. The proposed algorithms are capable of selecting controller with a complexity O(n), and provide cooperative relaying with a complexity O(n × k). The effectiveness of the proposed model is demonstrated by using simulations. The results show that the proposed approach reduces delays by 25% during the selection of controller, and increases the transfer speed by 20% compared to existing approaches.