DOI QR코드

DOI QR Code

Performance Analysis of Deep Learning Based Transmit Power Control Using SINR Information Feedback in NOMA Systems

NOMA 시스템에서 SINR 정보 피드백을 이용한 딥러닝 기반 송신 전력 제어의 성능 분석

  • Kim, Donghyeon (School of Electronic and Electrical Engineering, Hankyong National University) ;
  • Lee, In-Ho (School of Electronic and Electrical Engineering, Hankyong National University)
  • Received : 2021.03.11
  • Accepted : 2021.03.29
  • Published : 2021.05.31

Abstract

In this paper, we propose a deep learning-based transmit power control scheme to maximize the sum-rates while satisfying the minimum data-rate in downlink non-orthogonal multiple access (NOMA) systems. In downlink NOMA, we consider the co-channel interference that occurs from a base station other than the cell where the user is located, and the user feeds back the signal-to-interference plus noise power ratio (SINR) information instead of channel state information to reduce system feedback overhead. Therefore, the base station controls transmit power using only SINR information. The use of implicit SINR information has the advantage of decreasing the information dimension, but has disadvantage of reducing the data-rate. In this paper, we resolve this problem with deep learning-based training methods and show that the performance of training can be improved if the dimension of deep learning inputs is effectively reduced. Through simulation, we verify that the proposed deep learning-based power control scheme improves the sum-rate while satisfying the minimum data-rate.

본 논문에서는 하향링크 비직교 다중 접속 시스템에서 최소 데이터 전송률을 만족하며 데이터 전송률의 총합을 최대화 할 수 있는 딥러닝 기반의 송신 전력 제어 기법을 제안한다. 하향링크 비직교 다중 접속 시스템에서 사용자가 위치한 셀 이외의 기지국으로부터 발생할 수 있는 동일 채널 간섭을 고려하고, 시스템 피드백 오버헤드를 줄이기 위하여 사용자는 채널 상태 정보 대신에 신호 대 간섭 및 잡음비 정보를 피드백 한다. 따라서 기지국은 신호 대 간섭 및 잡음비 정보만을 이용하여 송신 전력을 제어한다. 함축적 신호 대 간섭 및 잡음비 정보의 이용은 정보 차원을 감소시키는 장점은 있지만 데이터 전송률을 감소시킬 수 있는 단점이 있다. 본 논문에서는 딥러닝 기반의 학습 방식으로 이 문제를 해결하고, 딥러닝 입력의 차원을 효과적으로 축소할 경우 학습의 성능을 향상시킬 수 있음을 보여준다. 시뮬레이션을 통해서 제안된 딥러닝 기반의 송신 전력 제어 기법이 최소 데이터 전송률을 만족하며 데이터 전송률의 총합을 향상시킬 수 있음을 입증한다.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education (Grant number: NRF-2018R1D1A1B07042499).

References

  1. W. Lee, M. Kim, and D. Cho, "Deep power control: transmit power control scheme based on convolutional neural network," IEEE Communications Letters, vol. 22, no. 6, pp. 1276-1279, Jun. 2018. https://doi.org/10.1109/lcomm.2018.2825444
  2. D. Kim and I. H. Lee, "Deep learning-based power control scheme for perfect fairness in device-to-device communication systems," Electronics, vol. 9, no. 10, pp. 1606, Oct. 2020. https://doi.org/10.3390/electronics9101606
  3. S. Ioffe and C. Szegedy, "Batch normalization: accelerating deep network training by reducing internal covariate shift," Proceedings of the 32nd International Conference on Machine Learning, Lille: France, pp. 448-456, 2015.
  4. W. Lee, M. Kim, and D. Cho, "Transmit power control using deep neural network for underlay device-to-device communication," IEEE Wireless Communication Letters, vol. 8, no. 1, pp. 141-144, Feb. 2019. https://doi.org/10.1109/lwc.2018.2864099
  5. N. Yang, H. Zhang, K. Long, H. Hsieh, and J. Liu, "Deep neural network for resource management in NOMA networks," IEEE Transactions Vehicular Technology, vol. 69, no. 1, pp. 876-886, Jan. 2020. https://doi.org/10.1109/tvt.2019.2951822
  6. W. Lu, M. Liu, S. Lin, and L. Li, "Fully decentralized optimal power flow of multi-area interconnected power systems based on distributed interior point method," IEEE Transactions Power Systems, vol. 33, no. 1, pp. 901-910, Jan. 2018. https://doi.org/10.1109/TPWRS.2017.2694860
  7. L. Tian, C. Fan, Y. Ming, and Y. Jin, "Stacked PCA Network (SPCANet): An effective deep learning for face recognition," Proceedings of the IEEE International Conference on Digital Signal Processing, Singapore, pp. 1039-1043, 2015.
  8. J. Shlens. (2014) "A tutorial on principal component analysis," [Internet]. Available: https://arxiv.org/abs/1404.1100.
  9. D. P. Kingma and J. Ba. (2014) "Adam: A method for stochastic optimization," [Internet]. Available: https://arxiv.org/abs/1412.6980.