Toward Practical Fluid Antenna Systems: Co-Optimizing Hardware and Software for Port Selection and Beamforming
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909694925209600 |
|---|---|
| author | Xu, Sai Wong, Kai-Kit Du, Yanan Hong, Hanjiang Chae, Chan-Byoung Liu, Baiyang Tong, Kin-Fai |
| author_facet | Xu, Sai Wong, Kai-Kit Du, Yanan Hong, Hanjiang Chae, Chan-Byoung Liu, Baiyang Tong, Kin-Fai |
| contents | This paper proposes a hardware-software co-design approach to efficiently optimize beamforming and port selection in fluid antenna systems (FASs). To begin with, a fluid-antenna (FA)-enabled downlink multi-cell multiple-input multiple-output (MIMO) network is modeled, and a weighted sum-rate (WSR) maximization problem is formulated. Second, a method that integrates graph neural networks (GNNs) with random port selection (RPS) is proposed to jointly optimize beamforming and port selection, while also assessing the benefits and limitations of random selection. Third, an instruction-driven deep learning accelerator based on a field-programmable gate array (FPGA) is developed to minimize inference latency. To further enhance efficiency, a scheduling algorithm is introduced to reduce redundant computations and minimize the idle time of computing cores. Simulation results demonstrate that the proposed GNN-RPS approach achieves competitive communication performance. Furthermore, experimental evaluations indicate that the FPGA-based accelerator maintains low latency while simultaneously executing beamforming inference for multiple port selections. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14035 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Toward Practical Fluid Antenna Systems: Co-Optimizing Hardware and Software for Port Selection and Beamforming Xu, Sai Wong, Kai-Kit Du, Yanan Hong, Hanjiang Chae, Chan-Byoung Liu, Baiyang Tong, Kin-Fai Signal Processing This paper proposes a hardware-software co-design approach to efficiently optimize beamforming and port selection in fluid antenna systems (FASs). To begin with, a fluid-antenna (FA)-enabled downlink multi-cell multiple-input multiple-output (MIMO) network is modeled, and a weighted sum-rate (WSR) maximization problem is formulated. Second, a method that integrates graph neural networks (GNNs) with random port selection (RPS) is proposed to jointly optimize beamforming and port selection, while also assessing the benefits and limitations of random selection. Third, an instruction-driven deep learning accelerator based on a field-programmable gate array (FPGA) is developed to minimize inference latency. To further enhance efficiency, a scheduling algorithm is introduced to reduce redundant computations and minimize the idle time of computing cores. Simulation results demonstrate that the proposed GNN-RPS approach achieves competitive communication performance. Furthermore, experimental evaluations indicate that the FPGA-based accelerator maintains low latency while simultaneously executing beamforming inference for multiple port selections. |
| title | Toward Practical Fluid Antenna Systems: Co-Optimizing Hardware and Software for Port Selection and Beamforming |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2507.14035 |