Abstract
This article studies fast adaptive beamforming optimization for the signal-to-interference-plus-noise ratio balancing problem in a multiuser multiple-input single-output downlink system. Existing deep learning based approaches to predict beamforming rely on the assumption that the training and testing channels follow the same distribution which may not hold in practice. As a result, a trained model may lead to performance deterioration when the testing network environment changes. To deal with this task mismatch issue, we propose two offline adaptive algorithms based on deep transfer learning and meta-learning, which are able to achieve fast adaptation with the limited new labelled data when the testing wireless environment changes. Furthermore, we propose an online algorithm to enhance the adaptation capability of the offline meta algorithm in realistic non-stationary environments. Simulation results demonstrate that the proposed adaptive algorithms achieve much better performance than the direct deep learning algorithm without adaptation in new environments. The meta-learning algorithm outperforms the deep transfer learning algorithm and achieves near optimal performance. In addition, compared to the offline meta-learning algorithm, the proposed online meta-learning algorithm shows superior adaption performance in changing environments.
Highlights
Multi-antenna techniques have been widely used to improve the spectral efficiency of modern wireless communications systems due to their ability to exploit spatial characteristics of the propagation channel [1], [2]
We propose an offline adaptive learning algorithm based on deep transfer learning (DTL) by combining deep learning (DL) techniques and transfer learning to achieve the adaption to a new environment
Numerical simulations are carried out to evaluate the advantages of the proposed adaptive beamforming optimization algorithms for different wireless communications scenarios
Summary
Multi-antenna techniques have been widely used to improve the spectral efficiency of modern wireless communications systems due to their ability to exploit spatial characteristics of the propagation channel [1], [2]. The direct prediction method may cause high training complexity and low learning accuracy of the neural networks since the number of variables to predict increases significantly as the number of transmit antennas and users increases To overcome this drawback, the authors in [25] exploited the problem structure and proposed a model-based DL framework to optimize the beamforming matrix. We propose the offline and online fast adaptive algorithms using transfer learning and meta learning techniques to solve the mismatch issue of beamforming design in dynamic wireless environments. OFFLINE LEARNING ALGORITHMS we design two offline adaptive learning methods to optimize beamforming: 1) DTL algorithm and 2) meta-learning algorithm These two algorithms aim to achieve fast adaptation in the new test wireless environment with limited channel data whose distribution is different from that in the training environment. We describe the details of these two algorithms
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
