eprintid: 10195807 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/19/58/07 datestamp: 2024-08-15 12:43:41 lastmod: 2024-08-15 12:43:41 status_changed: 2024-08-15 12:43:41 type: article metadata_visibility: show sword_depositor: 699 creators_name: Liang, Kai creators_name: Zheng, Gan creators_name: Li, Zan creators_name: Wong, Kai-Kit creators_name: Chae, Chan-Byoung title: A Data and Model-Driven Deep Learning Approach to Robust Downlink Beamforming Optimization ispublished: inpress divisions: UCL divisions: B04 divisions: F46 keywords: Robust beamforming, deep learning, outage probability constraint, multiuser MISO note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: This paper investigates the optimization of the probabilistically robust transmit beamforming problem with channel uncertainties in the multiuser multiple-input single-output (MISO) downlink transmission. This problem poses significant analytical and computational challenges. Currently, the state-of-the-art optimization method relies on convex restrictions as tractable approximations to ensure robustness against Gaussian channel uncertainties. However, this method not only exhibits high computational complexity and suffers from the rank relaxation issue but also yields conservative solutions. In this paper, we propose an unsupervised deep learning-based approach that incorporates the sampling of channel uncertainties in the training process to optimize the probabilistic system performance. We introduce a model-driven learning approach that defines a new beamforming structure with trainable parameters to account for channel uncertainties. Additionally, we employ a graph neural network to efficiently infer the key beamforming parameters. We successfully apply this approach to the minimum rate quantile maximization problem subject to outage and total power constraints. Furthermore, we propose a bisection search method to address the more challenging power minimization problem with probabilistic rate constraints by leveraging the aforementioned approach. Numerical results confirm that our approach achieves non-conservative robust performance, higher data rates, greater power efficiency, and faster execution compared to state-of-the-art optimization methods. date: 2024-07-31 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: http://dx.doi.org/10.1109/jsac.2024.3431583 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2304406 doi: 10.1109/JSAC.2024.3431583 lyricists_name: Wong, Kai-Kit lyricists_id: KWONG98 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public publication: IEEE Journal on Selected Areas in Communications pagerange: 1-1 issn: 0733-8716 citation: Liang, Kai; Zheng, Gan; Li, Zan; Wong, Kai-Kit; Chae, Chan-Byoung; (2024) A Data and Model-Driven Deep Learning Approach to Robust Downlink Beamforming Optimization. IEEE Journal on Selected Areas in Communications p. 1. 10.1109/JSAC.2024.3431583 <https://doi.org/10.1109/JSAC.2024.3431583>. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10195807/1/A_Data_and_Model-Driven_Deep_Learning_Approach_to_Robust_Downlink_Beamforming_Optimization.pdf