Non-Uniform Quantization System Based on SOM Filter Multicarrier Modulation Optical Communication System

Abstract

The invention discloses a non-uniform quantization system of an SOM-based filter multi-carrier modulation optical communication system, which includes a SOM training module and an SOM quantization module. In the pre-training mode, the SOM training module is used for the training of the SOM model of the filter multi-carrier modulation signal. This module first initializes the model parameters and the training set, and then normalizes, competes for learning, and adjusts the weights. Wait until the operation is iterated to converge, and input the obtained SOM model weight as the quantization level into the SOM quantization module; the quantization module does not work. In the working mode, the SOM training module is used to learn signal characteristics on the basis of the original SOM model, and adjust the quantization level in real time; the SOM quantization module quantizes the input data sequence according to the quantization level. The SOM non-uniform quantization algorithm of the invention reduces the system quantization error, improves the bit error rate performance of the system, and saves the cost.

Description

technical field [0001] The invention belongs to the technical field of optical communication, and in particular relates to a non-uniform quantization system of an SOM-based filter multi-carrier modulation optical communication system. Background technique [0002] In recent years, with the emergence of emerging technologies such as machine learning, social networking, and cloud computing, people's demand for the size and type of access bandwidth is also increasing year by year, which requires the future transmission network system to be able to meet high-capacity, Diverse requirements such as asynchronous transmission and high spectral efficiency. Intensity Modulation Direct Detection (IMDD) technology is favored in the application of short-distance optical fiber links because of its simple structure and easy implementation. In addition, multi-carrier modulation technology, especially Universal filter multi-carrier (Universal filter Multi-Carrier (UFMC) technology balances ...

AI Technical Summary

Problems solved by technology

However, this method still has the problem that the number of samples used for fitting is huge, and the computational complexity and storage complexity increase sharply with the increase of quantization digits.

Images