Unlock instant, AI-driven research and patent intelligence for your innovation.

Receiver equalization method and system based on low-complexity lstm

A low-complexity, equalization method technology, applied in the field of optical communication transmission, can solve the problem of high computational complexity, achieve the effect of simplifying the calculation process, reducing the computational complexity, and simplifying the equalization structure

Active Publication Date: 2022-08-05
PEKING UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the computational complexity of LSTM is much higher than that of traditional cyclic neural networks, so how to reduce the computational complexity of LSTM-based equalizers is a very important issue.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Receiver equalization method and system based on low-complexity lstm
  • Receiver equalization method and system based on low-complexity lstm
  • Receiver equalization method and system based on low-complexity lstm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described in further detail below through specific embodiments and accompanying drawings.

[0024] This embodiment discloses a low-complexity LSTM-based receiver equalization method, which includes two stages of training and equalization, and is specifically described as follows:

[0025] 1. In the training phase, the processing flow of this training phase is called the standard mode.

[0026] 1.1. The optical signal at the receiving end of the optical fiber communication transmission system is digitally processed by the front end to obtain the received symbol. The processing method includes dispersion compensation, phase recovery, etc., and the corresponding left and right eigenvectors are generated according to the received symbols in the training set. as a label. nth received symbol S n the left eigenvector of consists of itself and its first k adjacent received symbols, the right eigenvector consists of itself and the following k ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a receiving end equalization method and system based on low-complexity LSTM, belonging to the field of optical communication transmission. By training a low-complexity LSTM equalizer, the low-complexity LSTM equalizer has a simplified equalization structure, and is based on the low-complexity LSTM equalizer. The complexity LSTM equalizer equalizes the received symbols to be equalized, and adopts a simplified calculation process during equalization. On the premise that the low-complexity LSTM equalizer has similar equalization performance compared with the traditional LSTM equalizer, the computational complexity of the equalization process can be significantly reduced.

Description

technical field [0001] The invention belongs to the field of optical communication transmission, and relates to a method and system for equalization of a receiving end of an optical communication transmission system, in particular to a method and system for equalization of a receiving end based on a low-complexity long short-term memory network. Background technique [0002] Optical fiber communication transmission system has the advantages of large capacity and low cost. Overcoming the linear and nonlinear damage of optical signals during transmission has become the primary problem to further improve the capacity of optical fiber communication transmission systems. To solve this problem, there are two types of traditional solutions, one is Time Domain Equalization (TDE) and the other is Frequency Domain Equalization (FDE). [0003] In recent years, neural networks have been successfully applied to optical fiber communication transmission systems due to their powerful fitti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/063G06N3/04G06N3/08G06K9/62
CPCG06N3/063G06N3/08G06N3/044G06F18/214
Inventor 张帆明浩
Owner PEKING UNIV