Generative Neural Network based Spectrum Sharing using Linear Sum Assignment Problems

TL;DR

This paper introduces a deep autoencoder-based generative model for spectrum sharing in D2D communication, solving linear sum assignment problems efficiently and accurately, outperforming traditional algorithms and other neural network architectures.

Contribution

It proposes a novel deep autoencoder framework with three architectures for solving LSAPs in spectrum sharing, demonstrating superior performance over existing methods.

Findings

Hybrid autoencoder outperforms other architectures and state-of-the-art DNN techniques.

The approach achieves high accuracy and fast execution in solving LSAPs.

It can replace conventional RA techniques like the Hungarian algorithm.

Abstract

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.