Makale detayı · 2022
Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO
- Yıl
- 2022
- Tür
- article
Veri kaynağı ayrımı
- YÖKSİS YÖKSİS makale kaydı
- YÖKSİS dergi adı IEEE Transactions on Wireless Communications
- Katalog eşleşmesi (ISSN) IEEE Transactions on Wireless Communications
- OpenAlex OpenAlex zenginleştirmesi (özet, atıf, konular)
Özet
OpenAlex · İngilizce
Machine learning (ML) has attracted a great research interest for physical layer design problems, such as channel estimation, thanks to its low complexity and robustness. Channel estimation via ML requires model training on a dataset, which usually includes the received pilot signals as input and channel data as output. In previous works, model training is mostly done via centralized learning (CL), where the whole training dataset is collected from the users at the base station (BS). This approach introduces huge communication overhead for data collection. In this paper, to address this challenge, we propose a federated learning (FL) framework for channel estimation. We design a convolutional neural network (CNN) trained on the local datasets of the users without sending them to the BS. We develop FL-based channel estimation schemes for both conventional and RIS (intelligent reflecting surface) assisted massive MIMO (multiple-input multiple-output) systems, where a single CNN is trained for two different datasets for both scenarios. We evaluate the performance for noisy and quantized model transmission and show that the proposed approach provides approximately 16 times lower overhead than CL, while maintaining satisfactory performance close to CL. Furthermore, the proposed architecture exhibits lower estimation error than the state-of-the-art ML-based schemes.
Konular
Atıflar
OpenAlex cited_by_count. WoS veya Scopus atıf sayısı değildir; o kaynaklar için ayrı kolon yoktur.
145 atıf
OpenAlex cited_by_count (önbellek / veritabanı)
Yerel katalogda bu makaleye atıf yapan 12 yayın (OpenAlex referans eşleşmesi; tam dünya listesi değildir).
- A Hybrid Architecture for Federated and Centralized Learning 2022
- A Hybrid Architecture for Federated and Centralized Learning 2022
- Near-Field Terahertz Communications: Model-Based and Model-Free Channel Estimation 2023
- Terahertz-Band Channel and Beam Split Estimation via Array Perturbation Model 2023
- Federated Multi-Task Learning For THZ Wideband Channel And DOA Estimation 2023
- Wireless communications empowered by reconfigurable intelligent surfaces: Model-based vs model-free channel estimation 2023
- A framework for Gaussian Q approximation with BSA and its application to RIS-assisted systems 2024
- A framework for Gaussian Q approximation with BSA and its application to RIS-assisted systems 2024
- Machine Learning for Metasurfaces Design and Their Applications 2023
- Beam-Squint-Aware Channel Estimation for Dual-Wideband UPA-Type RIS-Aided Massive MIMO 2024