Open AccessA Channel Selection Algorithm of Power Line Communication Network Base on Double-layer Cascade Artificial Neural Network
Author(s) -
Beibei Qu,
Hong Wang,
Zhixiong Chen,
Zhong Zheng,
Zhen Han,
Lixia Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2031/1/012041
Subject(s) - channel (broadcasting) , computer science , artificial neural network , cascade , selection (genetic algorithm) , mimo , line (geometry) , power (physics) , algorithm , convergence (economics) , power line communication , layer (electronics) , electronic engineering , computer network , artificial intelligence , engineering , mathematics , physics , geometry , chemistry , organic chemistry , quantum mechanics , chemical engineering , economics , economic growth
A crucial issue in Power Line Communication (PLC) networks is how to improve the performance of power line channel in physical layer. In this paper, a multiple input multiple output (MIMO) PLC channel selection algorithm based on a double-layer cascaded artificial neural network model is proposed. After the model is trained, the best channel combination can be selected directly through the channel estimation information. The results show that compared with the communication system without channel selection, the model can improve the channel by 2-3dB, the probability of selecting the best channel is 95.02%, and the training has fast convergence speed and small amount of calculation.