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

The design of beamforming for downlink multi-user massive multi-inputmulti-output (MIMO) relies on accurate downlink channel state information (CSI)at the transmitter (CSIT). In fact, it is difficult for the base station (BS)to obtain perfect CSIT due to user mobility, and latency/feedback delay(between downlink data transmission and CSI acquisition). Hence, robustbeamforming under imperfect CSIT is needed. In this paper, considering multipleantennas at all nodes (base station and user terminals), we develop amulti-agent deep reinforcement learning (DRL) framework for massive MIMO underimperfect CSIT, where the transmit and receive beamforming are jointly designedto maximize the average information rate of all users. Leveraging thisDRL-based framework, interference management is explored and three DRL-basedschemes, namely the distributed-learning-distributed-processing scheme,partial-distributed-learning-distributed-processing, and central-learningdistributed-processing scheme, are proposed and analyzed. This paper 1)highlights the fact that the DRL-based strategies outperform the randomaction-chosen strategy and the delay-sensitive strategy named assample-and-hold (SAH) approach, and achieved over 90% of the information rateof two selected benchmarks with lower complexity: the zero-forcingchannel-inversion (ZF-CI) with perfect CSIT and the Greedy Beam Selectionstrategy, 2) demonstrates the inherent robustness of the proposed designs inthe presence of channel aging. 3) conducts detailed convergence and scalabilityanalysis on the proposed framework.

Deep Reinforcement Learning for Multi-user Massive MIMO with Channel Aging