Node trajectory prediction method in unmanned aerial vehicle ad hoc network

Abstract

The invention relates to the technical field of unmanned aerial vehicle ad hoc network communication, in particular to a node trajectory prediction method in an unmanned aerial vehicle ad hoc network. The prediction method comprises the following steps: collecting flight data of different types of unmanned aerial vehicles, and extracting flight feature data of the unmanned aerial vehicles; performing filling of missing data in the extracted flight features and deleting abnormal data by using a K nearest neighbor algorithm; training a gating cycle unit network by using the processed flight features of the unmanned aerial vehicle; adopting a particle swarm optimization algorithm to adjust and optimize weight parameters in the gating circulation unit network; and inputting the flight data of the unmanned aerial vehicle to be measured into the gating circulation unit network after weight parameter optimization, and outputting a node trajectory in the unmanned aerial vehicle self-organizing network. According to the invention, more reasonable flight features are extracted through the K nearest neighbor algorithm; the data training GRU model is used to predict the flight path of the unmanned aerial vehicle; and the routing reconfiguration times can be effectively reduced, and the system data transmission time delay is reduced.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle ad hoc network communication, in particular to a GRU-based node trajectory prediction method in an unmanned aerial vehicle ad hoc network. Background technique [0002] With the increasing maturity of information technologies such as artificial intelligence, mobile Internet and wireless communication, and the increasing requirements for unmanned aerial vehicles in the future battlefield and other aspects, single unmanned aerial vehicles, whether in the military field or the civil field, have their own limitations. Larger and no longer meets people's needs. Compared with a single UAV or a simple multi-UAV system, UAV swarms have unparalleled advantages and are an inevitable trend in the development of UAV technology in the future. Clustered UAVs can avoid multi-UAV collisions in a limited space, assign an overall task to the clustered UAVs, and the cluster will decompose by itself ...

AI Technical Summary

Problems solved by technology

Unlike MANET nodes that are restricted by terrain factors, FANET nodes are not disturbed by terrain when moving in the air, but their speed is generally faster than traditional MANET nodes, and the network topology changes more frequently

Images