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

Link scheduling in device-to-device (D2D) networks is usually formulated as anon-convex combinatorial problem, which is generally NP-hard and difficult toget the optimal solution. Traditional methods to solve this problem are mainlybased on mathematical optimization techniques, where accurate channel stateinformation (CSI), usually obtained through channel estimation and feedback, isneeded. To overcome the high computational complexity of the traditionalmethods and eliminate the costly channel estimation stage, machine leaning (ML)has been introduced recently to address the wireless link scheduling problems.In this paper, we propose a novel graph embedding based method for linkscheduling in D2D networks. We first construct a fully-connected directed graphfor the D2D network, where each D2D pair is a node while interference linksamong D2D pairs are the edges. Then we compute a low-dimensional feature vectorfor each node in the graph. The graph embedding process is based on thedistances of both communication and interference links, therefore withoutrequiring the accurate CSI. By utilizing a multi-layer classifier, a schedulingstrategy can be learned in a supervised manner based on the graph embeddingresults for each node. We also propose an unsupervised manner to train thegraph embedding based method to further reinforce the scalability andgeneralizability and develop a K-nearest neighbor graph representation methodto reduce the computational complexity. Extensive simulation demonstrates thatthe proposed method is near-optimal compared with the existing state-of-artmethods but is with only hundreds of training samples. It is also competitivein terms of scalability and generalizability to more complicated scenarios.

Graph Embedding based Wireless Link Scheduling with Few Training Samples