Recently, a low earth orbit (LEO) satellite network is one of major systems to provide seamless access for terrestrial network systems. In order to provide robust access, efficient handover mechanisms are essential. However, conventional mechanisms may introduce frequent handovers due to the rapid movement of satellites. To deal with this problem, this paper proposes a learning-based auction handover under the consideration of received signal strength and service time between terrestrial users and satellites. The reason why auction-based approach is utilized is that it is generally considered as trustworthy. Our experiment results verify the proposed algorithm achieves desired performance.
This work was supported by Electronics and Telecommunications Research Institute (ETRI) funded by the Korean government [ 21ZH1100 , Research on 3D communication technology for hyper-connectivity].
