Robust Beamforming with Gradient-based Liquid Neural Network
arXiv:2405.07291 · doi:10.1109/LWC.2024.3436576
Abstract
Millimeter-wave (mmWave) multiple-input multiple-output (MIMO) communication with the advanced beamforming technologies is a key enabler to meet the growing demands of future mobile communication. However, the dynamic nature of cellular channels in large-scale urban mmWave MIMO communication scenarios brings substantial challenges, particularly in terms of complexity and robustness. To address these issues, we propose a robust gradient-based liquid neural network (GLNN) framework that utilizes ordinary differential equation-based liquid neurons to solve the beamforming problem. Specifically, our proposed GLNN framework takes gradients of the optimization objective function as inputs to extract the high-order channel feature information, and then introduces a residual connection to mitigate the training burden. Furthermore, we use the manifold learning technique to compress the search space of the beamforming problem. These designs enable the GLNN to effectively maintain low complexity while ensuring strong robustness to noisy and highly dynamic channels. Extensive simulation results demonstrate that the GLNN can achieve 4.15% higher spectral efficiency than that of typical iterative algorithms, and reduce the time consumption to only 1.61% that of conventional methods.
Accepted by IEEE Wireless Communications Letters
References in corpus (8)
- The Road Towards 6G: A Comprehensive Survey
- Closed-form Continuous-time Neural Models
- Rethinking WMMSE: Can Its Complexity Scale Linearly With the Number of BS Antennas?
- Robust Beamforming for RIS-aided Communications: Gradient-based Manifold Meta Learning
- A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming
- Energy-efficient Beamforming for RISs-aided Communications: Gradient Based Meta Learning
- Beamforming Inferring by Conditional WGAN-GP for Holographic Antenna Arrays
- Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning