In this paper, an intensity modulation and direct detection (IM-DD) discrete multi-tone (DMT) interconnection system employing polar coded and deep learning-assisted forward error correction decoding probabilistic shaping 16 quadrature amplitude modulation (PS-16QAM) is studied. By employing many-to-one (MTO) based PS to achieve signal Gaussian distribution model, the proposed optical DMT system is with the advantages of shaping overhead free profile, and optimized polar coded modulation architecture. To overcome the ambiguous problem for the overlapping symbol decision in PS, a deep learning assisted forward error correction decoding is proposed for belief propagation (BP) based polar decoding. The computational complexity of deep learning assisted polar decoding is superior to the original BP decoding one, and with faster rate convergence and better optical transmission performance. Simulation results in a 100Gb/s optical DMT transmission system present that, the deep learning assisted polar coded PS-16QAM signal achieves 0.38-dB superior receiver power sensitivity compared with conventional polar coded system over 10-km standard single mode fiber transmission.
KEYWORDS: Optical interconnects, Deep learning, Optical transmission, Neural networks, Data transmission, Signal processing, Digital signal processing, Bias correction, Telecommunications
In this paper, an intensity modulation direct detection interconnection system employing modeling-driven neural network (MDNN) assisted low-density parity-check code (LDPC) is proposed and experimentally demonstrated. The weights and biases are utilized to optimize the decoder parameters through model-driven deep learning LDPC decoding processing. Compared with traditional schemes that employ LDPC decoding with high computational complexity and redundancy, the proposed scheme has the advantages of a relatively lower complexity decoder and higher decoding gains. The results show that the MDNN signals can provide a 0.28-dB improvement in receiver power sensitivity and a 46% reduction in complexity in a 10-km IMDD optical four-pulse amplitude modulation interconnection system.
Compared with the traditional separated source-channel coding model, the performance of the joint source-channel coding will be better in the actual communication system. In addition, the typical decoding algorithms all belong to the algorithms of separated source-channel model. Therefore, the joint coding and decoding algorithm is particularly important and it will be recognized as of great significance in future communication. In this paper, in order to meet the future communication requirements, a scheme of polar code in joint coding is proposed. At the transmitter of the system, the source polarization is constructed by the Bhattacharyya parameter construction method and encoded by non- systematic polar code. For channel polarization, polarization weight construction method is used, which was independent of signal to noise ratio. A joint Belief Propagation (BP) decoder with a simple structure is adopted in the receiver, which includes a channel decoder and a source decoder. The joint decoder performs external iteration only through a few iterations, thus reducing the complexity and improving the efficiency of the communication system. Simulation results show that compared with the channel BP decoder, the performance gain of J-BP decoder is about 1.8dB.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.