Özet
Reconfigurable Intelligent Surfaces (RISs) are becoming one of the fundamental building blocks of next-generation wireless communication systems. To that end, RIS phase configuration optimization is an important issue, where finding the most suitable configuration becomes a challenging and resource-consuming task, especially as the number of RIS elements increases. Since exhaustive search is not practical, iterative algorithms are utilized to determine the RIS configuration by sequentially considering all RIS elements, where the best-performing phase shift configuration is obtained for each element. However, each configuration attempt requires receiver performance feedback, leading to higher delay and signaling overhead. Thus, in this paper, a convolutional neural network (CNN) based solution is formulated to rapidly find the phase configurations of the RIS elements. The simulation results for a RIS with 40×40 elements imply that the proposed algorithm reduces the number of steps dramatically e.g., from 3200 to 160 for the particular setup. Furthermore, such improvement in complexity is achieved with a slight degradation in performance.
Orijinal dil | İngilizce |
---|---|
Ana bilgisayar yayını başlığı | 2023 International Symposium on Networks, Computers and Communications, ISNCC 2023 |
Yayınlayan | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Elektronik) | 9798350335590 |
DOI'lar | |
Yayın durumu | Yayınlandı - 2023 |
Etkinlik | 2023 International Symposium on Networks, Computers and Communications, ISNCC 2023 - Doha, Qatar Süre: 23 Eki 2023 → 26 Eki 2023 |
Yayın serisi
Adı | 2023 International Symposium on Networks, Computers and Communications, ISNCC 2023 |
---|
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 2023 International Symposium on Networks, Computers and Communications, ISNCC 2023 |
---|---|
Ülke/Bölge | Qatar |
Şehir | Doha |
Periyot | 23/10/23 → 26/10/23 |
Bibliyografik not
Publisher Copyright:© 2023 IEEE.
Finansman
ACKNOWLEDGMENT This publication was made possible in parts by NPRP13S-0130-200200 and by NPRP14C-0909-210008 from the Qatar National Research Fund (a member of The Qatar Foundation). The statements made herein are solely the responsibility of the authors. We thank to StorAIge project that has received funding from the KDT Joint Undertaking (JU) under Grant Agreement No. 101007321. The JU receives support from the European Union’s Horizon 2020 research and innovation programme in France, Belgium, Czech Republic, Germany, Italy, Sweden, Switzerland, Türkiye, and National Authority TÜB˙TAK with project ID 121N350.
Finansörler | Finansör numarası |
---|---|
National Authority TÜB˙TAK | 121N350 |
Qatar National Research Fund | 101007321 |
Horizon 2020 Framework Programme |