AI-enabled cluster head selection through modified density based clustering in Aeronautical Ad Hoc Networks

Abstract

Offering in-flight connectivity has emerged as an essential demand for everyday flights. Such aircraft’s high speed and dynamic characteristics make this task challenging, particularly in distant areas with no ground-to-air link. Aeronautical Ad Hoc Network (AANET), a network of commercial airplanes with air-to-air connectivity, is a viable solution to this problem. However, the instability of air-to-air links results in poor performance of such ad hoc networks. A cluster-based topology formation is an initial step to boost the performance and connectivity in such a network. Selecting a well-connected cluster head is the next stage in enhancing connection and stability. This study presents a new cluster head selection technique for AANETs that calculates the neighbor nodes within a given distance of each node and selects the node with the most connections as the new cluster head. A gateway node is chosen to facilitate connections with other clusters. According to simulations, the proposed method increases packet delivery ratio by 3%, end-to-end delay by 9%, and throughput by up to 10%. In addition, the proposed method reduces cluster head replacements by 17% and increases cluster head longevity by 8%.