English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, deep neural networks have emerged as a solution to solve NP-hardwireless resource allocation problems in real-time. However, multi-layerperceptron (MLP) and convolutional neural network (CNN) structures, which areinherited from image processing tasks, are not optimized for wireless networkproblems. As network size increases, these methods get harder to train andgeneralize. User pairing is one such essential NP-hard optimization problem inwireless communication systems that entails selecting users to be scheduledtogether while minimizing interference and maximizing throughput. In thispaper, we propose an unsupervised graph neural network (GNN) approach toefficiently solve the user pairing problem. Our proposed method utilizes theErdos goes neural pipeline to significantly outperform other scheduling methodssuch as k-means and semi-orthogonal user scheduling (SUS). At 20 dB SNR, ourproposed approach achieves a 49% better sum rate than k-means and a staggering95% better sum rate than SUS while consuming minimal time and resources. Thescalability of the proposed method is also explored as our model can handledynamic changes in network size without experiencing a substantial decrease inperformance. Moreover, our model can accomplish this without being explicitlytrained for larger or smaller networks facilitating a dynamic functionalitythat cannot be achieved using CNNs or MLPs.

Graph Neural Networks-Based User Pairing in Wireless Communication Systems