Deep Reinforcement Learning for Improving Downlink mmWave Communication Performance

07/10/2017

∙

by   Brian L. Evans, et al.

∙

0

∙

share

We propose a method to improve the DL SINR for a single cell indoor base station operating in the millimeter wave frequency range using deep reinforcement learning. In this paper, we use the deep reinforcement learning model to arrive at optimal sequences of actions to improve the cellular network SINR value from a starting to a feasible target value. While deep reinforcement learning has been discussed extensively in literature, its applications in the cellular networks in general and in mmWave propagations are new and starting to gain attention. We have run simulations and have shown that an optimal action sequence is feasible even against the randomness of the network actions.