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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Intelligent reflecting surfaces (IRSs) technology has been considered apromising solution in visible light communication (VLC) systems due to itspotential to overcome the line-of-sight (LoS) blockage issue and enhancecoverage. Moreover, integrating IRS with a downlink non-orthogonal multipleaccess (NOMA) transmission technique for multi-users is a smart solution toachieve a high sum rate and improve system performance. In this paper, adynamic IRS-assisted NOMA-VLC system is modeled, and an optimization problem isformulated to maximize sum energy efficiency (SEE) and fairness among multiplemobile users under power allocation and IRS mirror orientation constraints. Dueto the non-convex nature of the optimization problem and the non-linearity ofthe constraints, conventional optimization methods are impractical forreal-time solutions. Therefore, a two-agent deep reinforcement learning (DRL)algorithm is designed for optimizing power allocation and IRS orientation basedon centralized training with decentralized execution to obtain fast andreal-time solutions in dynamic environments. The results show the superiorperformance of the proposed DRL algorithm compared to standard DRL algorithmstypically used for resource allocation in wireless communication. The resultsalso show that the proposed DRL algorithm achieves higher performance comparedto deployments without IRS and with randomly oriented IRS elements.

Two-Agent DRL for Power Allocation and IRS Orientation in Dynamic NOMA-based OWC Networks