A Model-Driven Deep Learning Method for LED Nonlinearity Mitigation in OFDM-Based Optical Communications
A Model-Driven Deep Learning Method for LED Nonlinearity Mitigation in OFDM-Based Optical Communications
复制标题
用于减轻基于 OFDM 的光通信中 LED 非线性的模型驱动深度学习方法
DOI：
10.1109/access.2019.2919983
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Lin, Chong
中科院分区：
文献类型：
--
作者：
Miao, Pu;Zhu, Bingcheng;Lin, Chong
发光二极管（LED）的非线性特性限制了可见光通信系统的误码率（BER）性能。在本文中，我们提出了使用自编码器（AE）网络的模型驱动深度学习（DL）方法来缓解基于正交频分复用（OFDM）的VLC系统中LED的非线性。与传统的完全数据驱动的AE不同，该方案将通信领域的知识很好地融入到网络架构和训练成本函数的设计中。首先，在发射机处采用深度神经网络（DNN）和离散傅里叶变换扩展（DFT-S）相结合的方法，将二进制数据映射为每个OFDM子载波的复I-Q符号。然后，在接收端，我们根据非线性补偿和信号检测将符号解映射模块划分为两个子网，每个子网由一个DNN组成。最后，通过代价函数同时考虑学习到的映射符号的自相关性和解映射符号的均方误差，进行网络训练。这种方法可以有效地降低LED的非线性和多径通道带来的干扰。仿真结果表明，该方法比现有方法具有更好的误码率性能，并进一步加快了训练速度，证明了深度学习在VLC系统中的应用前景和有效性。
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 OFDM 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.