Q-Learning Driven Routing for Aeronautical Ad-Hoc Networks

Bilen, Tuğçe; Canberk, Berk

doi:10.1016/j.pmcj.2022.101724

Cited by 3 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The establishment of AANET by civil aircraft can realize direct communication between aircraft, allowing them to send real-time status information and air perception information to each other so as to improve flight safety, facilitate traffic control, share information, provide Internet services for passengers and other purposes [1]. However, the establishment of AANET will pose new difficulties for routing protocol [2], Qos guarantee [3] and scalability; in addition, the connectivity problem of the aviation ad hoc network will also affect the networking mode and route selection [4]. To solve these problems, researchers proposed a way to divide the network into groups, namely, using clustering algorithms.…”

Section: Introductionmentioning

confidence: 99%

Civil Aeronautical Ad Hoc Network Zero-Overhead Clustering Algorithm Based on Realtime Position Information of the Aircraft

Luo,

Li,

et al. 2024

Electronics

View full text Add to dashboard Cite

Clustering is an important means to solve the poor scalability of aeronautical ad hoc networks (AANET). To improve the stability and performance of AANET and avoid unnecessary waste of resources caused by civil aircraft in communication, we proposed a zero-overhead clustering algorithm according to the real-time position of the aircraft based on the known trajectory. Firstly, the route and trajectory models are used to obtain geographical coordinates by the aircraft positioning algorithm. On this basis, the geographical cluster and cluster head region are divided in order to complete the cluster setting. Considering the aircraft maintenance cluster generation time updates, we use the communication sub-cluster generation algorithm to control the size of the cluster, and also, the flexibility of cluster hops is guaranteed by the subsidiary cluster members. The continuity of communication and the scalability of the cluster are maintained by the gateway node, thereby forming a network structure and increasing the stability of clusters. Finally, the actual route data are used to simulate the performance of the algorithm. The experimental and analytical results show that clustering and maintenance of the algorithm have zero overhead. Additionally, compared with the traditional algorithm, our proposed method can maintain a reasonable number of clusters, reduce the frequency of cluster head replacement, reduce the number of cluster members entering and leaving the cluster and avoid the loss of control of cluster heads to cluster members. So, it has important application value in the field of civil aviation.

show abstract

Section: Introductionmentioning

confidence: 99%