Özet
Frequency scarcity implies the utilization of higher frequencies for wireless communications; however, spreading loss becomes a dominating issue as the frequency increases to the level of and beyond millimeter waves. To this end, massive multiple-input multiple-output structures introduce mitigation alternatives. However, to make these solutions possible, the channel estimation approach strives to be modified: since Rayleigh distance is very short for conventional systems, the only far-field channel is examined in that context. On the other hand, the implementation of massive antenna arrays in high frequencies increases Rayleigh distance; thus, both near-field and far-field analyses become necessary. Instead of a dual estimation process, it would be effective and efficient to develop hybrid-field channel estimation techniques. Therefore, in this study, a new channel estimation method which is based on convolutional autoencoder (CAE) and orthogonal matching pursuit (OMP) approach, is proposed for hybrid channel estimation. The results indicate that the proposed OMP-CAE method has much better error performance when compared to the conventional OMP algorithm, especially at low signal-to-noise ratio regimes.
Orijinal dil | İngilizce |
---|---|
Ana bilgisayar yayını başlığı | 2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings |
Yayınlayan | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Elektronik) | 9781665454681 |
DOI'lar | |
Yayın durumu | Yayınlandı - 2022 |
Harici olarak yayınlandı | Evet |
Etkinlik | 96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022 - London, United Kingdom Süre: 26 Eyl 2022 → 29 Eyl 2022 |
Yayın serisi
Adı | IEEE Vehicular Technology Conference |
---|---|
Hacim | 2022-September |
ISSN (Basılı) | 1550-2252 |
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022 |
---|---|
Ülke/Bölge | United Kingdom |
Şehir | London |
Periyot | 26/09/22 → 29/09/22 |
Bibliyografik not
Publisher Copyright:© 2022 IEEE.