NISAC-EKF: An integrated localization deployment algorithm for UAV swarms based on NARX and EKF.

The mobility of both unmanned aerial vehicles (UAVs) and users, often results in frequent interruptions of communication links, affecting network communication performance. This problem can be solved through reasonable UAV location deployment. This paper proposes an integrated NISAC-EKF algorithm to enhance the localization deployment capability of UAV swarms. Initially, the nonlinear autoregressive exogenous model (NARX) is trained on crowd location data in a communication dataset, and integrated sensing and communication (ISAC) techniques are used to achieve communication-aided sensing. Subsequently, the extended Kalman filter (EKF) is enhanced by introducing probabilistic switching weights into the prediction of location errors, using interactive multiple model. Finally, the sequence predicted by NARX guides the EKF inputs, and the movement direction of the ground crowd adjusts the UAV location for effective demand tracking. Simulation results demonstrated that the NISAC-EKF algorithm ensures excellent performance in terms of network communication capacity and communication rate, even in the presence of varying ground demand. [ABSTRACT FROM AUTHOR]