A Deep Reinforcement Learning based Adaptive Transmission Strategy in Space-Air-Ground Integrated Networks

Space-air-ground integrated network (SAGIN) is an emerging architecture for future wireless communication systems, by exploiting the advantages of combined satellite, aerial and terrestrial communications. In such an integrated system, there may exist intra-cell, inter-cell and inter-system interferences, leading to unsatisfactory system performance. On the other hand, it is very challenging to optimize the system performance due to the unique characteristics of SAGINs, such as time-varying links, heterogeneous resources, and three-dimensional network architecture. In this paper, we propose a deep reinforcement learning based intelligent adaptive transmission strategy. We first formulate the adaptive transmission strategy problem (ATSP) with the aim to maximize the system throughput while meeting the delay and reliability requirements of packets. The re-parameterization method based deep deterministic policy gradient (RPDDPG) algorithm is proposed for achieving better performance compared with the relaxation-based DDPG algorithm. Numerical results demonstrate the performance improvement of the RPDDPG algorithm compared with the conventional relaxation-based DDPG algorithm and a heuristic algorithm.