ScholarWorks@경상국립대학교

초록

In low-latency and high-reliability communication systems,a channel coding operates within finite blocklengths, makingthe data rate a function of both decoding error probability andblocklength. This paper proposes a deep learning baseduniversal beamforming design for a multi-user downlinksystems, considering finite blocklength transmission. Byleveraging blocklength as a side information in deep neuralnetwork (DNN), we develop an efficient beamforming designthat is universally applicable to the varying blocklengths,aiming to maximize the sum rate under finite blocklength anddecoding error conditions. Through numerical results, wedemonstrate the superiority of the proposed scheme overexisting beamforming design methods.

키워드