RIDNet Assisted cGAN Based Channel Estimation for One-Bit ADC mmWave MIMO Systems


Creative Commons License

Karakoca E., Nayir H., Görçin A., Qaraqe K.

97th IEEE Vehicular Technology Conference, VTC 2023-Spring, Florence, Italy, 20 - 23 June 2023, vol.2023-June identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2023-June
  • Doi Number: 10.1109/vtc2023-spring57618.2023.10199774
  • City: Florence
  • Country: Italy
  • Keywords: channel estimation, feature attention, generative adversarial network, massive MIMO, one-bit ADC
  • Yıldız Technical University Affiliated: Yes

Abstract

The estimation of millimeter-wave (mmWave) massive multiple input multiple output (MIMO) channels becomes compelling when one-bit analog-to-digital converters (ADCs) are utilized. Furthermore, as the number of antenna increases, pilot overhead scales up to provide consistent channel estimation, eventually degrading spectral efficiency. This study presents a channel estimation approach that combines a conditional generative adversarial network (cGAN) with a novel blind denoising network with a sparse feature attention mechanism. Performance analysis and simulations show that using a cGAN fused with a feature attention-based denoising neural network significantly enhances the channel estimation performance while requiring less pilot transmission.