University of Oulu

G. Lee, M. Jung, A. T. Z. Kasgari, W. Saad and M. Bennis, "Deep Reinforcement Learning for Energy-Efficient Networking with Reconfigurable Intelligent Surfaces," ICC 2020 - 2020 IEEE International Conference on Communications (ICC), Dublin, Ireland, 2020, pp. 1-6, doi: 10.1109/ICC40277.2020.9149380

Deep reinforcement learning for energy-efficient networking with reconfigurable intelligent surfaces

Saved in:
Author: Lee, Gilsoo1; Jung, Minchae1; Kasgari, Ali Taleb Zadeh1;
Organizations: 1Wireless@VT, Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA
2Centre for Wireless Communications, University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.3 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2020
Publish Date: 2020-10-08


When deployed as reflectors for existing wireless base stations (BSs), reconfigurable intelligent surfaces (RISs) can be a promising approach to achieve high spectrum and energy efficiency. However, due to the large number of RIS elements, the joint optimization of the BS and reflector RIS configuration is challenging. In essence, the BS transmit power and RIS’s reflecting configuration must be optimized so as to improve users’ data rates and reduce the BS power consumption. In this paper, the problem of energy efficiency optimization is studied in an RIS-assisted cellular network endowed with an RIS reflector powered via energy harvesting technologies. The goal of this proposed framework is to maximize the average energy efficiency by enabling a BS to determine the transmit power and RIS configuration, under uncertainty on the wireless channel and harvested energy of the RIS system. To solve this problem, a novel approach based on deep reinforcement learning is proposed, in which the BS receives the state information, consisting of the users’ channel state information feedback and the available energy reported by the RIS. Then, the BS optimizes its action composed of the BS transmit power allocation and RIS phase shift configuration using a neural network. Due to the intractability of the formulated problem under uncertainty, a case study is conducted to analyze the performance of the studied RIS-assisted downlink system by asymptotically deriving the upper bound of the energy efficiency. Simulation results show that the proposed framework improves energy efficiency up to 77.3% when the number of RIS elements increases from 9 to 25.

see all

Series: IEEE International Conference on Communications
ISSN: 1550-3607
ISSN-E: 1938-1883
ISSN-L: 1550-3607
ISBN: 978-1-7281-5089-5
ISBN Print: 978-1-7281-5090-1
Pages: 1 - 6
Article number: 9149380
DOI: 10.1109/ICC40277.2020.9149380
Host publication: 2020 IEEE International Conference on Communications, ICC 2020
Conference: IEEE International Conference on Communications
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This research was supported by the U.S. National Science Foundation under Grants CNS-1814477 and IIS-1633363.
Copyright information: © 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.