The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems

End-to-end learning in optical communication systems is a promising technique to solve difficult communication problems, especially for peak to average power ratio (PAPR) reduction in orthogonal frequency division multiplexing (OFDM) systems. The less complex, highly adaptive hardware and advantages in the analysis of unknown or complex channels make deep learning a valid tool to improve system performance. In this paper, we propose an autoencoder network combined with extended selected mapping methods (ESLM-AE) to reduce the PAPR for the DC-biased optical OFDM system and to minimize the bit error rate (BER). The constellation mapping/de-mapping of the transmitted symbols and the phase factor of each subcarrier are acquired and optimized adaptively by training the autoencoder with a combined loss function. In the loss function, both the PAPR and BER performance are taken into account. The simulation results show that a significant PAPR reduction of more than 10 dB has been achieved by using the ESLM-AE scheme in terms of the complementary cumulative distribution function. Furthermore, the proposed scheme exhibits better BER performance compared to the standard PAPR reduction methods.

[1]  Sudha Vaiyamalai,et al.  PAPR Reduction in SLM–OFDM System Using Lehmer Sequence Without Explicit Side Information , 2017, Wirel. Pers. Commun..

[2]  Necmi Taspinar,et al.  A Novel Parallel Artificial Bee Colony Algorithm and Its PAPR Reduction Performance Using SLM Scheme in OFDM and MIMO-OFDM Systems , 2015, IEEE Communications Letters.

[3]  G. Maury,et al.  Decision-directed iterative methods for PAPR reduction in optical wireless OFDM systems , 2017 .

[4]  Vasilis Raptis,et al.  Enhanced PAPR in OFDM without Deteriorating BER Performance , 2011, Int. J. Commun. Netw. Syst. Sci..

[5]  Yan Liu,et al.  Peak-to-average power ratio reduction in orthogonal frequency division multiplexing-based visible light communication systems using a modified partial transmit sequence technique , 2018 .

[6]  Insoo Sohn,et al.  Neural Network Based Simplified Clipping and Filtering Technique for PAPR Reduction of OFDM Signals , 2015, IEEE Communications Letters.

[7]  Jae Hong Lee,et al.  PAPR reduction of OFDM signals using a reduced complexity PTS technique , 2004, IEEE Signal Processing Letters.

[8]  Woongsup Lee,et al.  A Novel PAPR Reduction Scheme for OFDM System Based on Deep Learning , 2018, IEEE Communications Letters.

[9]  Lin Zhang,et al.  Noise Resistant Spreading OOFDM Design for Suppressing PAPR of High Data Rate Wireless Optical Communication System , 2018, 2018 IEEE International Conference on Communications (ICC).

[10]  Stephan ten Brink,et al.  OFDM-Autoencoder for End-to-End Learning of Communications Systems , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[11]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[12]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[13]  Masao Nakagawa,et al.  Fundamental analysis for visible-light communication system using LED lights , 2004, IEEE Transactions on Consumer Electronics.

[14]  Zabih Ghassemlooy,et al.  PAPR reduction scheme for ACO-OFDM based visible light communication systems , 2017 .

[15]  Timothy J. O'Shea,et al.  An Introduction to Machine Learning Communications Systems , 2017, ArXiv.

[16]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[17]  Wei-Wen Hu,et al.  PAPR Reduction for Visible Light Communication Systems Without Side Information , 2017, IEEE Photonics Journal.

[18]  Yong Wang,et al.  A novel improved SLM scheme of the PAPR reduction technology in CO-OFDM systems , 2017 .

[19]  S. Sygletos,et al.  Comparison of Nonlinear Compensation Techniques for 400-Gb/s Coherent Multi-Band OFDM Super-Channels , 2018 .

[20]  Deepak K. Chy,et al.  Evaluation of SNR for AWGN, Rayleigh and Rician Fading Channels Under DPSK Modulation Scheme with Constant BER , 2015 .

[21]  Zhigang Cao,et al.  Channel estimation for OFDM transmission in multipath fading channels based on parametric channel modeling , 2001, IEEE Trans. Commun..

[22]  Giorgos Tatsis,et al.  Preliminary BER Study of a TC - OFDM system operating under noisy conditions , 2016 .

[23]  Lijun Deng,et al.  A novel PAPR reduction scheme for VLC DCO-OFDM systems , 2018 .

[24]  Wei Xu,et al.  PAPR Reduction for DCO-OFDM Visible Light Communications via Semidefinite Relaxation , 2014, IEEE Photonics Technology Letters.

[25]  Jean Armstrong,et al.  Comparison of Asymmetrically Clipped Optical OFDM and DC-Biased Optical OFDM in AWGN , 2008, IEEE Communications Letters.

[26]  Jian Song,et al.  Subcarrier Grouping OFDM for Visible-Light Communication Systems , 2015, IEEE Photonics Journal.

[27]  JoAnne Holliday,et al.  Scheduling methods for multi-user optical wireless asymmetrically-clipped OFDM , 2011, Journal of Communications and Networks.

[28]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[29]  Norbert Hanik,et al.  PAPR reduction techniques for coherent optical OFDM transmission , 2009, 2009 11th International Conference on Transparent Optical Networks.

[30]  H. Haas,et al.  An LED Model for Intensity-Modulated Optical Communication Systems , 2010, IEEE Photonics Technology Letters.

[31]  Zabih Ghassemlooy,et al.  Pilot-Assisted PAPR Reduction Technique for Optical OFDM Communication Systems , 2014, Journal of Lightwave Technology.

[32]  Xiao Zhou,et al.  A Haar Wavelet Decision Feedback Channel Estimation Method in OFDM Systems , 2018 .

[33]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[34]  Joseph M. Kahn,et al.  Modeling of nondirected wireless infrared channels , 1996, Proceedings of ICC/SUPERCOMM '96 - International Conference on Communications.

[35]  Yoshifusa Ito,et al.  Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory , 1991, Neural Networks.

[36]  Huimin Lu,et al.  On the study of the relation between linear/nonlinear PAPR reduction and transmission performance for OFDM-based VLC systems. , 2018, Optics express.

[37]  Insoo Sohn,et al.  A Low Complexity PAPR Reduction Scheme for OFDM Systems via Neural Networks , 2014, IEEE Communications Letters.

[38]  Yongqiang Hei,et al.  Branch and bound methods based tone injection schemes for PAPR reduction of DCO-OFDM visible light communications. , 2017, Optics express.

[39]  Giorgos Tatsis,et al.  Reducing Peak-to-Average Power Ratio of a Turbo Coded OFDM , 2012 .

[40]  Upena D. Dalal,et al.  Abatement of PAPR for ACO-OFDM deployed in VLC systems by frequency modulation of the baseband signal forming a constant envelope , 2017 .

[41]  Francesco Musumeci,et al.  A Survey on Application of Machine Learning Techniques in Optical Networks , 2018, ArXiv.

[42]  Kiran Karra,et al.  Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[43]  Yongqiang Hei,et al.  Improved TKM-TR methods for PAPR reduction of DCO-OFDM visible light communications. , 2017, Optics express.

[44]  Hendrik C. Ferreira,et al.  On the Indoor VLC Link Evaluation Based on the Rician $K$ -Factor , 2018, IEEE Communications Letters.

[45]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.