International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Comparison of Autoencoder based OFDM Communication System with Wi-Fi

  • Shiho Oshiro (Information Technology Center at University of the Ryukyus) ;
  • Takao Toma (Magna Design Net Inc) ;
  • Tomohisa Wada (Dept. of Engineering at University of the Ryukyus)
  • Received : 2023.05.05
  • Published : 2023.05.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, performance of autoencoder based OFDM communication systems is compared with IEEE 802.11a Wireless Lan System (Wi-Fi). The proposed autoencoder based OFDM system is composed of the following steps. First, one sub-carrier's transmitter - channel - receiver system is created by autoencoder. Then learning process of the one sub-carrier autoencoder generates constellation map. Secondly, using the plural sub-carrier autoencoder systems, parallel bundle is configured with inserting IFFT and FFT before and after the channel to configure OFDM system. Finally, the receiver part of the OFDM communication system was updated by re-learning process for adapting channel condition such as multipath channel. For performance comparison, IEEE802.11a and the proposed autoencoder based OFDM system are compared. For channel estimation, Wi-Fi uses initial long preamble to measure channel condition. but Autoencoder needs re-learning process to create an equalizer which compensate a distortion caused by the transmission channel. Therefore, this autoencoder based system has basic advantage to the Wi-Fi system. For the comparison of the system, additive random noise and 2-wave and 4-wave multipaths are assumed in the transmission path with no inter-symbol interference. A simulation was performed to compare the conventional type and the autoencoder. As a result of the simulation, the autoencoder properly generated automatic constellations with QPSK, 16QAM, and 64QAM. In the previous simulation, the received data was relearned, thus the performance was poor, but the performance improved by making the initial value of reception a random number. A function equivalent to an equalizer for multipath channels has been realized in OFDM systems. As a future task, there is not include error correction at this time, we plan to make further improvements by incorporating error correction in the future.

Keywords

References

  1. Takao Touma and Tomohisa Wada, "A study of OFDM communication system with autoencoder," TECHNICAL REPORT OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS, 2022.5, vol 122, no. SR-12, SR2022-6, pp. 27-33. 
  2. Takao Touma and Tomohisa Wada, "Performance comparisons of OFDM communication system with autoencoder," TECHNICAL REPORT OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS, 2022.11, vol. 122, no. SR-243, SR2022-46, pp.7-14. 
  3. T. O' Shea and J. Hoydis, "An Introduction to Deep Learning for the Physical Layer," in IEEE Trans. Cognitive Communications and Networking, vol. 3, no. 4, pp. 563-575, Dec. 2017, doi: 10.1109/TCCN.2017.2758370. 
  4. A. Felix, S. Cammerer, S. Dorner, J. Hoydis and S. Ten Brink, "OFDM-Autoencoder for End-to-End Learning of Communications Systems," 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2018, pp. 1-5, doi: 10.1109SPAWC.2018.8445920.  https://doi.org/10.1109SPAWC.2018.8445920
  5. F. A. Aoudia and J. Hoydis, "End-to-End Learning of Communications Systems Without a Channel Model," 2018, 52nd Asilomar Conference on Signals, Systems, and Computers, 2018, pp. 298-303, doi: 10.1109/ACSSC.2018.8645416. 
  6. TRICEPS Planning Department, "OFDM Emphasis Technology for Digital Broadcasting/Mobile Communications," TRICEPS, Tokyo, March 2000. 
  7. Tetsuya Shimamura and TRICEPS Planning Department, "MATLAB Program Case Study for Digital Communication Systems," TRICEPS, Tokyo, July 2000. 
  8. Chollet Francois and Queep and Yusuke Sugomori, "Deep Learning with Python and Keras," Mynavi Publishing, Tokyo, May 2018. 
  9. Yasuki Saito, "Theory and Implementation of Deep Learning with Python," O'Reilly Japan, Ohmsha, Tokyo, September 2016. 
  10. Geron Aurelien and Takahiro Nagao and Tomohiro Shimoda, "Practical Machine Learning with Scikit-learn and TensorFlow," O'Reilly Japan, Ohmsha, Tokyo, April 2018. 
  11. Shiro Sakata, "Wireless LAN," Ohmsha, Tokyo, June 2004. 
  12. Masahiro Morikura, "What you want to know about the latest technology, high-speed wireless LAN 802. Introduction to 11n, Impress R&D," Impress Communications (released), Tokyo, September 2007. 
  13. Written by Gulli, Antonio Gulli, Sujit Pal; Translated by Masaya Ogushi, Takahiro Kubo, Koki Nakayama, "Intuition deep learning: A recipe to shape ideas with Python × Keras," O'Reilly Japan; Tokyo: Ohmsha, Tokyo, August 2018.