Accessing the accurate downlink channel state information (CSI) is essential to take full advantage of frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems due to its weak channel reciprocity. Meanwhile, great computational burdens will happen, which is accompanied by continuous CSI feedback. The existing compressive sensing (CS)-based and deep learning (DL)-based methods try to solve such problems, but do not achieve desired effect to get ideal CSI feedback or decrease the overhead. An adaptive deep neural network (DNN)-based CSI feedback method is proposed in this paper to address this. A classification block of the compression ratio is adopted and modified to apply to a more complex channel model named Clustered-Delay-Line (CDL), which helps decrease the computational overhead of the network. Besides, the reconstruction accuracy of the CSI feedback is further improved by proposing a new structure of the encoder. Quantization and dequantization modules are also applied to make the whole network more robust and effectively minimize the quantization distortion in the real communication scenario, respectively. The simulation results show that the proposed method performs better than the conventional ones on the CSI reconstruction accuracy in terms of normalized mean square error (NMSE), even though the quantization module is added.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adaptive DNN-based CSI Feedback with Quantization for FDD Massive MIMO Systems


    Contributors:


    Publication date :

    2022-09-01


    Size :

    474695 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adaptive Quantization Threshold Setting Method for Massive MIMO Systems with 1-bit Analog-to-Digital Converter

    Yan, Fei / Li, Guobing / Zhang, Guomei et al. | British Library Online Contents | 2016


    CSI Quantization for FDD Massive MIMO Communication

    Vehkalahti, Roope / Liao, Jialing / Pllaha, Tefjol et al. | IEEE | 2021


    Adaptive Residual Vector Quantization for Dynamic Mode Decomposition-Based CSI Feedback in MIMO Systems

    Zhu, Lingrui / Haddad, Fayad / Bockelmann, Carsten et al. | IEEE | 2024


    Performance of Limited Feedback Strategies with Massive MIMO

    Vook, Frederick W. / Mondal, Bishwarup / Visotsky, Eugene | IEEE | 2015