skip to main content
research-article

A Real-Time Deep Learning OFDM Receiver

Published:27 December 2021Publication History
Skip Abstract Section

Abstract

Machine learning in the physical layer of communication systems holds the potential to improve performance and simplify design methodology. Many algorithms have been proposed; however, the model complexity is often unfeasible for real-time deployment. The real-time processing capability of these systems has not been proven yet. In this work, we propose a novel, less complex, fully connected neural network to perform channel estimation and signal detection in an orthogonal frequency division multiplexing system. The memory requirement, which is often the bottleneck for fully connected neural networks, is reduced by ≈ 27 times by applying known compression techniques in a three-step training process. Extensive experiments were performed for pruning and quantizing the weights of the neural network detector. Additionally, Huffman encoding was used on the weights to further reduce memory requirements. Based on this approach, we propose the first field-programmable gate array based, real-time capable neural network accelerator, specifically designed to accelerate the orthogonal frequency division multiplexing detector workload. The accelerator is synthesized for a Xilinx RFSoC field-programmable gate array, uses small-batch processing to increase throughput, efficiently supports branching neural networks, and implements superscalar Huffman decoders.

REFERENCES

  1. [1] GitHub. n.d. google-research/google-research. Retrieved November 8, 2021 from https://github.com/google-research/google-research.Google ScholarGoogle Scholar
  2. [2] S. Yue, Y. Ma, N. Yi, and R. Tafazolli. 2018. Unsupervised deep learning for MU-SIMO joint transmitter and noncoherent receiver design. IEEE Wireless Communications Letters 8, 1 (2018), 177–180. https://doi.org/10.1109/LWC.2018.2865563Google ScholarGoogle Scholar
  3. [3] IEEE. 2019. 754-2019—IEEE Standard for Floating-Point Arithmetic. IEEE, Los Alamitos, CA. https://doi.org/10.1109/IEEESTD.2019.8766229Google ScholarGoogle Scholar
  4. [4] 3GPP. 2019. 3GPP TR 21.915. Technical Report 3GPP TR 21.915 V15.0.0 (2019-09). Retrieved November 8, 2021 from https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=3389.Google ScholarGoogle Scholar
  5. [5] 3GPP. 2020. 3GPP TR 36.912. Technical Report 3GPP TR 36.912 V16.0.0 (2020-07-14). Retrieved November 8, 2021 from https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2584.Google ScholarGoogle Scholar
  6. [6] 3GPP. 2021. 3GPP TR 36.211. Technical Report 3GPP TR 36.211 V16.6.0 (2021-06-30). Retrieved November 8, 2021 from https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2425.Google ScholarGoogle Scholar
  7. [7] Abdelfattah Mohamed S., Hagiescu Andrei, and Singh Deshanand. 2014. Gzip on a chip: High performance lossless data compression on FPGAs using OpenCL. In Proceedings of the International Workshop on OpenCL 2013 & 2014 (IWOCL’14). ACM, New York, NY, 19. https://doi.org/10.1145/2664666.2664670 Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. [8] Aggarwal Charu C.. 2018. Neural Networks and Deep Learning: A Textbook. Springer International, Cham, Switzerland. https://doi.org/10.1007/978-3-319-94463-0 Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Aspar Z., Yusof Z. Mohd, and Suleiman I.. 2000. Parallel Huffman decoder with an optimized look up table option on FPGA. In Proceedings of the 2000 TENCON Proceedings on Intelligent Systems and Technologies for the New Millennium (Cat. No. 00CH37119), Vol. 1. https://doi.org/10.1109/TENCON.2000.893543Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Aydonat Utku, O’Connell Shane, Capalija Davor, Ling Andrew C., and Chiu Gordon R.. 2017. An OpenCL deep learning accelerator on Arria 10. In Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA’17). ACM, New York, NY, 5564. https://doi.org/10.1145/3020078.3021738Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. [11] Chiueh Tzi-Dar and Tsai Pei-Yun. 2007. OFDM Baseband Receiver Design for Wireless Communications. John Wiley & Sons. Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. [12] B. C. Csáji and others. 2001. Approximation with artificial neural networks. Faculty of Sciences 24, 48 (2001), 7.Google ScholarGoogle Scholar
  13. [13] Dorner S., Cammerer S., Hoydis J., and Brink S. ten. 2018. Deep learning based communication over the air. IEEE Journal of Selected Topics in Signal Processing 12, 1 (Feb. 2018), 132143. https://doi.org/10.1109/JSTSP.2017.2784180Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] ElWazeer Khaled, Khairy Mohamed M., Fahmy Hossam A. H., and Habib S. E. D.. 2009. FPGA implementation of an improved channel estimation algorithm for mobile WiMAX. In Proceedings of the 2009 International Conference on Microelectronics (ICM’09). 280283. https://doi.org/10.1109/ICM.2009.5418629Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Felix A., Cammerer S., Dorner S., Hoydis J., and Brink S. ten. 2018. OFDM-autoencoder for end-to-end learning of communications systems. In Proceedings of the 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC’18). 15. https://doi.org/10.1109/SPAWC.2018.8445920Google ScholarGoogle ScholarCross RefCross Ref
  16. [16] Gao Xuanxuan, Jin Shi, Wen Chao-Kai, and Li Geoffrey Ye. 2018. ComNet: Combination of deep learning and expert knowledge in OFDM receivers. IEEE Communications Letters 22, 12 (Dec. 2018), 26272630. https://doi.org/10.1109/LCOMM.2018.2877965Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Goodfellow Ian, Bengio Yoshua, and Courville Aaron. 2016. Deep Learning. MIT Press, Cambridge, MA. Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Guo Yunhui. 2018. A survey on methods and theories of quantized neural networks. arXiv:1808.04752 [cs, stat] (Dec. 2018). http://arxiv.org/abs/1808.04752. Google ScholarGoogle Scholar
  19. [19] Han Song, Liu Xingyu, Mao Huizi, Pu Jing, Pedram Ardavan, Horowitz Mark A., and Dally William J.. 2016. EIE: Efficient inference engine on compressed deep neural network. arXiv:1602.01528 [cs] (Feb. 2016). http://arxiv.org/abs/1602.01528. Google ScholarGoogle Scholar
  20. [20] Han Song, Mao Huizi, and Dally William J.. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv:1510.00149 [cs] (Oct. 2015). http://arxiv.org/abs/1510.00149. Google ScholarGoogle Scholar
  21. [21] GitHub. 2020. haoyye/OFDM_DNN. Retrieved November 8, 2021 from https://github.com/haoyye/OFDM_DNN. Google ScholarGoogle Scholar
  22. [22] He Hengtao, Jin Shi, Wen Chao-Kai, Gao Feifei, Li Geoffrey Ye, and Xu Zongben. 2019. Model-driven deep learning for physical layer communications. IEEE Wireless Communications 26, 5 (Oct. 2019), 7783. https://doi.org/10.1109/MWC.2019.1800447Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Inc. Xilinx2018. Zynq UltraScale+ RFSoC Data Sheet: Overview. Retrieved November 8, 2021 from https://www.xilinx.com/support/documentation/data_sheets/ds889-zynq-usp-rfsoc-overview.pdf.Google ScholarGoogle Scholar
  24. [24] Inc. Xilinx2019. DPU for Convolutional Neural Network v3.0, DPU IP Product Guide. Retrieved November 8, 2021 from https://www.xilinx.com/support/documentation/ip_documentation/dpu/v3_0/pg338-dpu.pdf.Google ScholarGoogle Scholar
  25. [25] Inc. Xilinx2020. UltraScale Architecture-Based FPGAs Memory IP v1.4 LogiCORE IP Product Guide. Retrieved November 8, 2021 from https://www.xilinx.com/support/documentation/ip_documentation/ultrascale_memory_ip/v1_4/pg150-ultrascale_memory-ip.pdf.Google ScholarGoogle Scholar
  26. [26] Jacob Benoit, Kligys Skirmantas, Chen Bo, Zhu Menglong, Tang Matthew, Howard Andrew, Adam Hartwig, and Kalenichenko Dmitry. 2017. Quantization and training of neural networks for efficient integer-arithmetic-only inference. arXiv:1712.05877 [cs, stat] (Dec. 2017). http://arxiv.org/abs/1712.05877. Google ScholarGoogle Scholar
  27. [27] Kingdom MathWorks United. 2021. Equalize OFDM Data Using Channel Estimates. Retrieved November 8, 2021 from https://uk.mathworks.com/help/wireless-hdl/ref/ofdmequalizer.html.Google ScholarGoogle Scholar
  28. [28] Kingdom MathWorks United. 2021. Estimate Channel Using Input Data and Reference Subcarriers. Retrieved November 8, 2021 from https://uk.mathworks.com/help/wireless-hdl/ref/ofdmchannelestimator.html.Google ScholarGoogle Scholar
  29. [29] Laplante Phillip A.. 2012. Real-Time Systems Design and Analysis: Tools for the Practitioner (4th ed.). Wiley. http://www.ezproxy.is.ed.ac.uk/login?url=http://onlinelibrary.wiley.com/book/10.1002/9781118136607. Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. [30] Ledwon Morgan, Cockburn Bruce F., and Han Jie. 2020. High-throughput FPGA-based hardware accelerators for deflate compression and decompression using high-level synthesis. IEEE Access 8 (2020), 6220762217. https://doi.org/10.1109/ACCESS.2020.2984191Google ScholarGoogle ScholarCross RefCross Ref
  31. [31] Letaief Khaled B., Chen Wei, Shi Yuanming, Zhang Jun, and Zhang Ying-Jun Angela. 2019. The roadmap to 6G: AI empowered wireless networks. IEEE Communications Magazine 57, 8 (Aug. 2019), 8490. https://doi.org/10.1109/MCOM.2019.1900271Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Lin H.. 2015. Flexible configured OFDM for 5G air interface. IEEE Access 3 (2015), 18611870. https://doi.org/10.1109/ACCESS.2015.2480749Google ScholarGoogle ScholarCross RefCross Ref
  33. [33] Ltd. Alpha Data n.d. ADM-XRC-9R1: FPGA COTS board: Xilinx Zynq —8x 14-bit 4/5Gsps ADCs, 8x 14-bit 6.5/10Gsps DACs. Retrieved November 8, 2021 from https://www.alpha-data.com/esp/products.php?product=adm-xrc-9r1.Google ScholarGoogle Scholar
  34. [34] Ma Yufei, Suda Naveen, Cao Yu, Vrudhula Sarma, and Seo Jae-sun. 2018. ALAMO: FPGA acceleration of deep learning algorithms with a modularized RTL compiler. Integration, the VLSI Journal 62 (June 2018), 1423. https://doi.org/10.1016/j.vlsi.2017.12.009Google ScholarGoogle ScholarDigital LibraryDigital Library
  35. [35] Mao Qian, Hu Fei, and Hao Qi. 2018. Deep learning for intelligent wireless networks: A comprehensive survey. IEEE Communications Surveys Tutorials 20, 4 (2018), 25952621. https://doi.org/10.1109/COMST.2018.2846401Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Molisch Andreas F.. 2012. Wireless Communications. John Wiley & Sons. Google ScholarGoogle ScholarDigital LibraryDigital Library
  37. [37] O’Shea Timothy J., Erpek Tugba, and Clancy T. Charles. 2017. Deep learning based MIMO communications. arXiv:1707.07980 [cs, math] (July 2017). http://arxiv.org/abs/1707.07980. Google ScholarGoogle Scholar
  38. [38] O’Shea T. and Hoydis J.. 2017. An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking 3, 4 (Dec. 2017), 563575. https://doi.org/10.1109/TCCN.2017.2758370Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Pal Chandrajit, Pankaj Sunil, Akram Wasim, Acharyya Amit, and Biswas Dwaipayan. 2018. Modified Huffman based compression methodology for deep neural network implementation on resource constrained mobile platforms. In Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS’18). 15. https://doi.org/10.1109/ISCAS.2018.8351234Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Posewsky Thorbjörn and Ziener Daniel. 2016. Efficient deep neural network acceleration through FPGA-based batch processing. In Proceedings of the 2016 International Conference on ReConFigurable Computing and FPGAs (ReConFig’16). 18. https://doi.org/10.1109/ReConFig.2016.7857167Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Posewsky Thorbjorn and Ziener Daniel. 2018. Throughput optimizations for FPGA-based deep neural network inference. Microprocessors and Microsystems 60 (July 2018), 151161. https://doi.org/10.1016/j.micpro.2018.04.004arXiv: 1810.00722.Google ScholarGoogle ScholarCross RefCross Ref
  42. [42] Qiu Jiantao, Song Sen, Wang Yu, Yang Huazhong, Wang Jie, Yao Song, Guo Kaiyuan, et al. 2016. Going deeper with embedded FPGA platform for convolutional neural network. In Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA’16). ACM, New York, NY, 2635. https://doi.org/10.1145/2847263.2847265 Google ScholarGoogle ScholarDigital LibraryDigital Library
  43. [43] Sesia Stefania, Toufik Issam, and Baker Matthew. 2011. LTE—The UMTS Long Term Evolution: From Theory to Practice. John Wiley & Sons. Google ScholarGoogle ScholarDigital LibraryDigital Library
  44. [44] Shawahna A., Sait S. M., and El-Maleh A.. 2019. FPGA-based accelerators of deep learning networks for learning and classification: A review. IEEE Access 7 (2019), 78237859. https://doi.org/10.1109/ACCESS.2018.2890150Google ScholarGoogle ScholarCross RefCross Ref
  45. [45] Shlezinger Nir, Eldar Yonina C., Farsad Nariman, and Goldsmith Andrea J.. 2019. ViterbiNet: Symbol detection using a deep learning based Viterbi algorithm. In Proceedings of 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC’19). 15. https://doi.org/10.1109/SPAWC.2019.8815457Google ScholarGoogle ScholarCross RefCross Ref
  46. [46] Leeuwen Jan Van. 1976. On the construction of Huffman trees. In Third International Colloquium on Automata, Languages and Programming, University of Edinburgh, UK, July 20–23, 1976. Edinburgh University Press, Edinburgh, Germany, 382410.Google ScholarGoogle Scholar
  47. [47] Wang Tianqi, Wen Chao-Kai, Wang Hanqing, Gao Feifei, Jiang Tao, and Jin Shi. 2017. Deep learning for wireless physical layer: Opportunities and challenges. China Communications 14, 11 (Nov. 2017), 92111. https://doi.org/10.1109/CC.2017.8233654Google ScholarGoogle ScholarCross RefCross Ref
  48. [48] Yao Miao, Sohul Munawwar, Marojevic Vuk, and Reed Jeffrey H.. 2019. Artificial intelligence defined 5G radio access networks. IEEE Communications Magazine 57, 3 (March 2019), 1420. https://doi.org/10.1109/MCOM.2019.1800629 Google ScholarGoogle ScholarDigital LibraryDigital Library
  49. [49] Ye Hao, Li Geoffrey Ye, and Juang Biing-Hwang. 2018. Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters 7, 1 (Feb. 2018), 114117. https://doi.org/10.1109/LWC.2017.2757490Google ScholarGoogle ScholarCross RefCross Ref
  50. [50] Zeng Hanqing, Chen Ren, Zhang Chi, and Prasanna Viktor. 2018. A framework for generating high throughput CNN implementations on FPGAs. In Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA’18). ACM, New York, NY, 117126. https://doi.org/10.1145/3174243.3174265 Google ScholarGoogle ScholarDigital LibraryDigital Library
  51. [51] Zhang Chen, Li Peng, Sun Guangyu, Guan Yijin, Xiao Bingjun, and Cong Jason. 2015. Optimizing FPGA-based accelerator design for deep convolutional neural networks. In Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA’15). 161–170. https://doi.org/10.1145/2684746.2689060 Google ScholarGoogle ScholarDigital LibraryDigital Library
  52. [52] Zhang Chaoyun, Patras Paul, and Haddadi Hamed. 2019. Deep learning in mobile and wireless networking: A survey. arXiv:1803.04311 [cs] (Jan. 2019). http://arxiv.org/abs/1803.04311. Google ScholarGoogle Scholar
  53. [53] Zhang Lin, Liang Ying-Chang, and Niyato Dusit. 2019. 6G Visions: Mobile ultra-broadband, super Internet-of-Things, and artificial intelligence. China Communications 16, 8 (Aug. 2019), 114. https://doi.org/10.23919/JCC.2019.08.001Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. A Real-Time Deep Learning OFDM Receiver

              Recommendations

              Comments

              Login options

              Check if you have access through your login credentials or your institution to get full access on this article.

              Sign in

              Full Access

              • Published in

                cover image ACM Transactions on Reconfigurable Technology and Systems
                ACM Transactions on Reconfigurable Technology and Systems  Volume 15, Issue 3
                September 2022
                353 pages
                ISSN:1936-7406
                EISSN:1936-7414
                DOI:10.1145/3508070
                • Editor:
                • Deming Chen
                Issue’s Table of Contents

                Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

                Publisher

                Association for Computing Machinery

                New York, NY, United States

                Publication History

                • Published: 27 December 2021
                • Accepted: 1 October 2021
                • Revised: 1 September 2021
                • Received: 1 June 2021
                Published in trets Volume 15, Issue 3

                Permissions

                Request permissions about this article.

                Request Permissions

                Check for updates

                Qualifiers

                • research-article
                • Refereed
              • Article Metrics

                • Downloads (Last 12 months)208
                • Downloads (Last 6 weeks)14

                Other Metrics

              PDF Format

              View or Download as a PDF file.

              PDF

              eReader

              View online with eReader.

              eReader

              Full Text

              View this article in Full Text.

              View Full Text

              HTML Format

              View this article in HTML Format .

              View HTML Format
              About Cookies On This Site

              We use cookies to ensure that we give you the best experience on our website.

              Learn more

              Got it!