Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Verification of Deep Learning based Transmit Power Control

딥러닝 기반 송신전력 조절방안의 성능검증

  • Lee, Woongsup (Department of Information and Communication Engineering, Institute of Marine Industry, Gyeongsang National University) ;
  • Kim, Seong Hwan (Department of Information and Communication Engineering, Institute of Marine Industry, Gyeongsang National University) ;
  • Ryu, Jongyeol (Department of Information and Communication Engineering, Institute of Marine Industry, Gyeongsang National University) ;
  • Ban, Tae-Won (Department of Information and Communication Engineering, Institute of Marine Industry, Gyeongsang National University)
  • Received : 2019.01.15
  • Accepted : 2019.01.22
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the deep learning technology has gained lots of attention which leads to its application to various fields. Especially, there are recent attempts to overcome the limit of wireless communications systems through the use of the deep learning. In this paper, we have verified the performance of deep learning based transmit power control scheme. Unlike previous transmit power control schemes where the optimal transmit power is derived by solving the optimization problem explicitly, in the deep learning based transmit power control, the general solver for the optimization problem is derived through the deep neural network (DNN). Especially, by using the spectral efficiency as the loss function of DNN, the training can be performed without needing labels. Through simulation based on Tensorflow, we confirm that the transmit power control based on deep learning can achieve the optimal performance while reducing the computational complexity by 1/200.

최근 딥러닝 기술이 큰 관심을 받으며 다양한 분야에 적용되고 있다. 특히 다양한 무선통신기술에 딥러닝을 접목하여 기존 통신시스템의 한계를 뛰어넘으려는 시도가 이루어지고 있다. 본 논문에서는 딥러닝 기반 무선통신 시스템 송신전력 조절방안의 성능검증을 수행하였다. 딥러닝 기반 송신전력 조절방안에서는 수학적 최적화 문제를 직접 풀어서 최적의 전력을 결정하는 기존 방식과 달리 심층신경망 구조를 학습시켜서 채널에 따라 최적의 송신전력을 찾는 General solver를 도출하여 이를 이용한다. 특히 시스템의 주파수 효율을 심층신경망 학습의 손실함수로 사용함으로써 라벨없이 학습을 가능케 한다. 본 논문에서는 Tensorflow 기반 성능분석을 통해 딥러닝 기반 송신전력 조절방안과 최적방안의 성능이 일치함을 보였고, 또한 제안 방안이 기존의 방식에 비해서 1/200의 계산복잡도로 송신전력을 찾을 수 있음을 보임으로써 실제 무선통신시스템에서의 적용가능성을 검증하였다.

Keywords

HOJBC0_2019_v23n3_326_f0001.png 이미지

Fig. 1 Considered system model for transmit power control.

HOJBC0_2019_v23n3_326_f0002.png 이미지

Fig. 2 Considered DNN structure to derive optimal transmit power.

HOJBC0_2019_v23n3_326_f0003.png 이미지

Fig. 3 Spectral efficiency vs. number of layers.

HOJBC0_2019_v23n3_326_f0004.png 이미지

Fig. 4 Spectral efficiency vs. number of weights.

HOJBC0_2019_v23n3_326_f0005.png 이미지

Fig. 5 Spectral efficiency vs. number of users.

HOJBC0_2019_v23n3_326_f0006.png 이미지

Fig. 6 Computation time vs. number of users.

References

  1. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp.436-444, May. 2015. https://doi.org/10.1038/nature14539
  2. W. Lee, S. H. Kim, J. Ryu, and T.-W. Ban, "Fast Detection of Disease in Livestock based on Deep Learning," Journal of the Korea Institute of Information and Communication Engineering, vol. 21, no. 5, pp. 1009-1015, May 2017. https://doi.org/10.6109/JKIICE.2017.21.5.1009
  3. W. Lee, T.-W. Ban, S. H. Kim, and J. Ryu, "Neighbor Discovery for Mobile Systems based on Deep Learning," Journal of the Korea Institute of Information and Communication Engineering, vol. 12, no. 3, pp. 527-533, Mar. 2018.
  4. M. Kim, W. Lee, and D. Cho, "A Novel PAPR Reduction Scheme for OFDM System based on Deep Learning," IEEE Communications Letters, vol. 22, no. 3, pp.510-513, Mar. 2018. https://doi.org/10.1109/LCOMM.2017.2787646
  5. M. Kim, N. Kim, W. Lee, and D. Cho, "Deep Learning Aided SCMA," IEEE Communications Letters, vol. 22, no. 4, pp.720-723, Apr. 2018. https://doi.org/10.1109/LCOMM.2018.2792019
  6. T. J. O'Shea, J. Corgan, and T. C. Clancy, "Convolutional radio modulation recognition networks," in Proc. of International Conference on Engineering Applications of Neural Network, Aberdeen, UK, Sep. 2016.
  7. H. Sun, X. Chen, Q. Shi, M. Hong, X. Fu, and N. D. Sidiropoulos, "Learning to Optimize: Training Deep Neural Networks for Interference Management," IEEE Transactions on Signal Processing, vol. 66, no. 20, pp.5438-5453, Aug. 2018. https://doi.org/10.1109/TSP.2018.2866382
  8. 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
  9. Q. Shi, M. Razaviyayn, Z.-Q. Luo, and C. He, "An iteratively weighted MMSE approach to distributed sum-utility maximization for a MIMO interfering broadcast channel," IEEE Transitions on Signal Processing, vol. 59, no. 9, pp. 4331-4340, Sep. 2011. https://doi.org/10.1109/TSP.2011.2147784
  10. S. Ioffe, and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," in Proceeding of International Conference on Machine Learning, Lille: France, pp. 448-456, 2015.