A tactical wireless network (TWN) is a military radio communication network supporting mission-critical applications. Hence, a tactical wireless network demands more reliability, availability, robustness, and security than a commercial wireless network. The tactical wireless network must operate in a hostile environment, where the environment changes rapidly and is prone to attack. To maintain the required quality of services (QoS), the network must intelligently adapt to the hostile environment. Since thousands of nodes in remote areas cannot be managed by military personnel, they must identify neighbors within the communication range and configure the network autonomously. In addition, the network should cope with self-healing and self-reconfiguring. Wherefore, a suitable self-organization algorithm considering network scalability should be designed. Clustering has been traditionally proposed to solve the scalability issue in flat adhoc networks and prolong their lifetime. Clustering involves the creation of a hierarchical network where the network is divided into clusters, with certain nodes in each cluster being chosen as clusterheads.

Keywords: Clustering, Tactical wireless network, Graph theory, Geometric deep learning,

non -euclidean data