A Dynamic Routing Switching Method Based on Graph Neural Network for Fire Rescue Site Command Battle Network

Unlike traditional wireless network routing switching protocols or methods that use a single indicator threshold (RSRP, DTR, DTD) to determine network routing switching and reorganization, graph neural network methods are introduced into the construction process of command and combat networks in this paper. Graph neural network models are constructed based on the networking nodes and the connection relationships between nodes in the network, and are take into account the overall business performance of the network and achieving dynamic and real-time switching of network routing.