A Model-Driven Deep Learning Method for LED Nonlinearity Mitigation in OFDM-Based Optical Communications
Open Access
- 30 May 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 71436-71446
- https://doi.org/10.1109/access.2019.2919983
Abstract
The nonlinearity of light emitting diodes (LED) has restricted the bit error rate (BER) performance of visible light communications (VLC). In this paper, we propose model-driven deep learning (DL) approach using an autoencoder (AE) network to mitigate the LED nonlinearity for orthogonal frequency division multiplexing (OFDM)-based VLC systems. Different from the conventional fully data-driven AE, the communication domain knowledge is well incorporated in the proposed scheme for the design of network architecture and training cost function. First, a deep neural network (DNN) combined with discrete Fourier transform spreading (DFT-S) is adopted at the transmitter to map the binary data into complex I-Q symbols for each OEDM subcarrier. Then, at the receiver, we divide the symbol demapping module into two subnets in terms of nonlinearity compensation and signal detection, where each subnet is comprised of a DNN. Finally, both the autocorrelation of the learned mapping symbols and the mean square error of demapping symbols are taken into account simultaneously by the cost function for network training. With this approach, the LED nonlinearity and the interference introduced by the multipath channel can be effectively mitigated. The simulation results show that the proposed scheme exhibits better BER performance than some existing methods and further accelerates the training speed, which demonstrates the prospective and validity of DL in the VLC system.Funding Information
- National Natural Science Foundation of China (61801257, 61871119, 61801377)
- Natural Science Foundation of Jiangsu Province (BK20161428)
- Natural Science Foundation of Shandong Province (ZR2019BF001, SAST2016072)
- China Postdoctoral Science Foundation (2019M652322)
This publication has 32 references indexed in Scilit:
- Learning to decode linear codes using deep learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Low-complexity frequency domain nonlinear compensation for OFDM based high-speed visible light communication systems with light emitting diodesOptics Express, 2017
- IEEE 802.15.7r1 Reference Channel Models for Visible Light CommunicationsIEEE Communications Magazine, 2017
- Orthogonal Polynomial-Based Nonlinearity Modeling and Mitigation for LED CommunicationsIEEE Photonics Journal, 2016
- PAPR and PICR Reduction of OFDM Signals with Clipping Noise-based Tone Injection SchemeIEEE Transactions on Vehicular Technology, 2016
- Indoor Positioning for Multiphotodiode Device Using Visible-Light CommunicationsIEEE Photonics Journal, 2015
- Deep learningNature, 2015
- Adaptive Postdistortion for Nonlinear LEDs in Visible Light CommunicationsIEEE Photonics Journal, 2014
- Impact of LED Nonlinearity on Discrete Multitone ModulationJournal of Optical Communications and Networking, 2009
- Non-linearity effects and predistortion in optical OFDM wireless transmission using LEDsInternational Journal of Ultra Wideband Communications and Systems, 2009