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

Reconfigurable intelligent surface (RIS) is considered as a promisingsolution for next-generation wireless communication networks due to a varietyof merits, e.g., customizing the communication environment. Therefore,deploying multiple RISs helps overcome severe signal blocking between the basestation (BS) and users, which is also a practical and effective solution toachieve better service coverage. However, reaping the full benefits of amulti-RISs aided communication system requires solving a non-convex,infinite-dimensional optimization problem, which motivates the use oflearning-based methods to configure the optimal policy. This paper adopts anovel heterogeneous graph neural network (GNN) to effectively exploit the graphtopology in the wireless communication optimization problem. First, wecharacterize all communication link features and interference relations in oursystem with a heterogeneous graph structure. Then, we endeavor to maximize theweighted sum rate (WSR) of all users by jointly optimizing the activebeamforming at the BS, the passive beamforming vector of the RIS elements, aswell as the RISs association strategy. Unlike most existing work, we consider amore general scenario where the cascaded link for each user is not fixed butdynamically selected by maximizing the WSR. Simulation results show that ourproposed heterogeneous GNNs perform about 10 times better than otherbenchmarks, and a suitable RISs association strategy is also validated to beeffective in improving the quality services of users by 30%.

Cooperative Beamforming and RISs Association for Multi-RISs Aided Multi-Users MmWave MIMO Systems through Graph Neural Networks