Deep Reinforcement Learning Based Mode Selection for Coexistence of D2D-U and Wi-Fi
暂无分享,去创建一个
The use of unlicensed bands on Device to Device (D2D) communication provides support for shortage of spectrum resources. However, significant impact on the traditional unlicensed networks caused by D2D-Unlicensed (D2D-U) is not negligible. Fair unlicensed spectrum sharing is very important for the D2D-Unlicensed/Wi-Fi coexistence scheme. D2D should choose a suitable coexistence mode to ensure the performance of the entire network in different communication environments. We proposed a deep reinforcement learning (DRL)-based algorithm for the mode selection to solve the coexistence problem of D2D-U and Wi-Fi. Simulation results show that the proposed DRL-based algorithm provides a considerable performance of the whole network while ensuring performance requirements of Wi-Fi.