首页|Studies from Telecom Paris Provide New Data on Machine Learning (Machine Learnin g Techniques for Blind Beam Alignment in mmWave Massive MIMO)
Studies from Telecom Paris Provide New Data on Machine Learning (Machine Learnin g Techniques for Blind Beam Alignment in mmWave Massive MIMO)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on artificial intelligen ce have been presented. According to news originating from Paris, France, by New sRx correspondents, research stated, "This paper proposes methods for Machine Le arning (ML)-based Beam Alignment (BA), using low-complexity ML models, and achie ves a small pilot overhead." Financial supporters for this research include Telecom Paris, L'institut Polytec hnique De Paris, France. Our news correspondents obtained a quote from the research from Telecom Paris: " We assume a single-user massive mmWave MIMO, Uplink, using a fully analog archit ecture. Assuming large-dimension codebooks of possible beam patterns at U E and B S , this data-driven and model-based approach aims to partially and blindly so und a small subset of beams from these codebooks. The proposed BA is blind (no C SI), based on Received Signal Energies (RSEs), and circumvents the need for exha ustively sounding all possible beams. A sub-sampled subset of beams is then used to train several ML models such as low-rank Matrix Factorization (MF), non-negative MF (NMF), and shallow Multi-Layer Perceptron (MLP). We provide an extensive mathematical description of these models and the algorithms for each of them. O ur extensive numerical results show that, by sounding only 10 % of the beams from the U E and B S codebooks, the proposed ML tools are able to acc urately predict the non-sounded beams through multiple transmitted power regimes ."
NETL
NSTL
