KNIGCN: Key Node Identification in UAV Swarm Networks Using a Graph Convolutional Network

In the field of Internet of Things (IoT), uncrewed aerial vehicle (UAV) swarms are widely used to assist IoT communication due to their simple deployment, high mobility and high cost effectiveness to help improve IoT network coverage and topological flexibility. However, due to the openness of UAV swarm network, UAV nodes are vulnerable to malicious attacks and fail, especially some key nodes, which will seriously degrade the network performance. To solve this problem, a key node identification model based on graph convolutional network (GCN), named KNIGCN, is proposed. Specifically, the topology model of UAV cluster network is first built based on flying ad hoc network (FANET) communication architecture and Dijkstra’s algorithm, then node criticality labels in the network are made by means of traffic statistics, and finally KNIGCN model is used to predict the criticality scores of each node and sort them so as to screen out a certain number of key nodes. The experimental results show that the model has good performance of key node identification. Compared with traditional methods, the proposed method makes a more reasonable judgment of node criticality, and the key nodes identified have a more important impact on network performance. Moreover, the proposed scheme can effectively improve the identification speed of key nodes in large-scale, complex or dynamically changing topology of UAV cluster networks. It can provide an effective scheme for maintaining the security and stability of UAV swarm network communication.