A domain-transformed surrogate-assisted differential evolutionary algorithm for hyperparameter optimisation of satellite handover strategy

Abstract

With the rapid advancement of low-Earth-orbit (LEO) satellite technology, satellite phone calls have become increasingly widespread. However, this progress introduces new challenges: the high velocity of LEO satellites necessitates frequent reconnections between terminals and satellites, which can adversely affect communication quality. Moreover, the frequent signal measurements required to maintain connectivity significantly increase the energy consumption of the terminals. To address these challenges, this paper proposes a terminal measurement and satellite-switching strategy. The strategy aims to minimize energy consumption during switching while preserving a high level of user experience. The strategy is based on predictions of satellite cell visibility time and beam visibility time. To further optimise the hyperparameters of this method, we established a simulation-based hyperparameter optimisation model and designed a domain-transformed surrogate-assisted differential evolutionary algorithm (DT-SADE). The algorithm utilises a radial basis function (RBF) model as a surrogate for global search and a Kriging model for local search, and uses domain transformation to address discrepancies between the simulation and surrogate models. Experimental results demonstrate that the proposed method outperforms comparative algorithms across multiple performance metrics, and that hyperparameter optimisation further enhances its performance, highlighting the significance and effectiveness of hyperparameter optimisation.