{"ID":2894748,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10063","arxiv_id":"2507.10063","title":"Deep Learning-Based Beamforming Design Using Target Beam Patterns","abstract":"This paper proposes a deep learning-based beamforming design framework that directly maps a target beam pattern to optimal beamforming vectors across multiple antenna array architectures, including digital, analog, and hybrid beamforming. The proposed method employs a lightweight encoder-decoder network where the encoder compresses the complex beam pattern into a low-dimensional feature vector and the decoder reconstructs the beamforming vector while satisfying hardware constraints. To address training challenges under diverse and limited channel station information (CSI) conditions, a two-stage training process is introduced, which consists of an offline pre-training for robust feature extraction using an auxiliary module, followed by online training of the decoder with a composite loss function that ensures alignment between the synthesized and target beam patterns in terms of the main lobe shape and side lobe suppression. Simulation results based on NYUSIM-generated channels show that the proposed method can achieve spectral efficiency close to that of fully digital beamforming under limited CSI and outperforms representative existing methods.","short_abstract":"This paper proposes a deep learning-based beamforming design framework that directly maps a target beam pattern to optimal beamforming vectors across multiple antenna array architectures, including digital, analog, and hybrid beamforming. The proposed method employs a lightweight encoder-decoder network where the encod...","url_abs":"https://arxiv.org/abs/2507.10063","url_pdf":"https://arxiv.org/pdf/2507.10063v2","authors":"[\"Hongpu Zhang\",\"Shu Sun\",\"Hangsong Yan\",\"Jianhua Mo\"]","published":"2025-07-14T08:49:08Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[]","has_code":false}