Generative neural network based spectrum sharing using linear sum assignment problems

Spectrum management and resource allocation (RA) problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks. The traditional approaches for solving such problems usually consume time and memory, especially for large-size problems. R...

Full description

Saved in:
Bibliographic Details
Published in:China communications Vol. 17; no. 2; pp. 14 - 29
Main Authors: Zaky, Ahmed B., Huang, Joshua Zhexue, Wu, Kaishun, ElHalawany, Basem M.
Format: Journal Article
Language:English
Published: China Institute of Communications 01.02.2020
Benha University,Benha,13511,Egypt
Big Data Institute,Shenzhen University,518060,China
Benha University,Benha,13511,Egypt%Big Data Institute,Shenzhen University,518060,China%Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen University,Shenzhen 518060,China
PCL Research Center of Networks and Communications,Peng Cheng Laboratory,Shenzhen 518060,China%Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen University,Shenzhen 518060,China
Subjects:
autoencoder
Computer architecture
Device-to-device communication
generative models
linear sum assignment problems
Machine learning
Neural networks
Optimization
resource allocation
Resource management
Wireless communication
generative models
autoencoder
resource allocation
linear sum assignment problems
ISSN:1673-5447
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Spectrum management and resource allocation (RA) problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks. The traditional approaches for solving such problems usually consume time and memory, especially for large-size problems. Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems, especially the generative model of the deep neural networks. In this work, we propose a resource allocation deep autoencoder network, as one of the promising generative models, for enabling spectrum sharing in underlay device-to-device (D2D) communication by solving linear sum assignment problems (LSAPs). Specifically, we investigate the performance of three different architectures for the conditional variational autoencoders (CVAE). The three proposed architecture are the convolutional neural network (CVAE-CNN) autoencoder, the feed-forward neural network (CVAE-FNN) autoencoder, and the hybrid (H-CVAE) autoencoder. The simulation results show that the proposed approach could be used as a replacement of the conventional RA techniques, such as the Hungarian algorithm, due to its ability to find solutions of LASPs of different sizes with high accuracy and very fast execution time. Moreover, the simulation results reveal that the accuracy of the proposed hybrid autoencoder architecture outperforms the other proposed architectures and the state-of-the-art DNN techniques.
ISSN:1673-5447
DOI:10.23919/JCC.2020.02.002