Ultra-reliable millimeter-wave communications using an artificial intelligence-powered reflector
Soorki, Mehdi Naderi; Saad, Walid; Bennis, Mehdi (2020-02-27)
M. N. Soorki, W. Saad and M. Bennis, "Ultra-Reliable Millimeter-Wave Communications Using an Artificial Intelligence-Powered Reflector," 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, 2019, pp. 1-6, https://doi.org/10.1109/GLOBECOM38437.2019.9013431
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2020050424878
Tiivistelmä
Abstract
In this paper, a novel framework for guaranteeing ultra-reliable millimeter-wave (mmW) communications using a smart, artificial intelligence (AI)-powered mmW reflector is proposed. The use of an AI-powered reflector allows changing the propagation direction of mmW signals and, thus, improving coverage particularly for non-line-of-sight (LoS) areas. However, due to the possibility of stochastic blockage over mmW links, designing an intelligent phase shift-control policy for the mmW reflector to guarantee ultra-reliable mmW communications becomes very challenging. In this regard, first, based on the framework of risk-sensitive reinforcement learning, a parametric risk-sensitive episodic return is proposed to maximize the expected bit rate while mitigating the risk of non-LoS mmW link in the presence of future stochastic blockage over the mmW links. Then, a closed-form approximation for the gradient of the risk- sensitive episodic return is analytically derived. To \emph{directly} find the optimal policy for the proposed phase-shift controller, a parametric functional-form policy is implemented using a deep recurrent neural network (RNN). Then, based on the derived closed-form gradient of risk-sensitive episodic return, the deep RNN-based parametric functional-form policy is trained. The efficiency of the proposed AI-powered reflector is evaluated in an office environment. Simulation results show that the root-mean- square errors between the optimal and approximate phase shift-control policies of the proposed deep RNN is 1.35% in the worst case. Moreover, on average, the mean value and variance of the achievable rates resulting from the deep RNN-based policy are only 1% and 2% less than the optimal solution for different unknown mobile users’ trajectories, respectively.
Kokoelmat
- Avoin saatavuus [34546]