LSTM-Based Algorithm For Cooperative Communication in Impulse Noise Impaired PLC Channel

In this paper, a Deep Learning algorithm based on Long Short-Term Memory (LSTM) model is proposed to solve the problem of relay selection in cooperative Power Line Communication (PLC) communications. The proposed approach addresses the constraint of impulse noise presence in PLC channel, and it is b...

Full description

Saved in:
Bibliographic Details
Main Authors: Rouissi, F., Sghair, W. B., Gassara, H., Tlili, F.
Format: Conference Proceeding
Language:English
Subjects:
Approximation algorithms
cumulative regret
Decision making
Deep learning
LSTM
Middleton Class-A noise
Power line communications
Prediction algorithms
Predictive models
Relay selection
Relays
UCB
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a Deep Learning algorithm based on Long Short-Term Memory (LSTM) model is proposed to solve the problem of relay selection in cooperative Power Line Communication (PLC) communications. The proposed approach addresses the constraint of impulse noise presence in PLC channel, and it is based on predicting the state of each relay link, whether it is characterized by a Gaussian or impulsive behavior. This prediction is used to establish a precise reward mechanism aimed at enhancing the decision-making process for relay selection. The efficiency of the examined algorithm is shown in terms of reduced accumulated regret and higher percentage of good selection, when compared to the conventional UCB.
ISSN:2768-0940
DOI:10.1109/ISNCC58260.2023.10323771