| Title |
Machine Learning-based mmWave Channel Estimation and Tracking Algorithm in V2I Communications |
| Authors |
문상미(Sangmi Moon) ; 김현성(Hyeonsung Kim) ; 김진영(Jin Young Kim) ; 황인태(Intae Hwang) |
| DOI |
https://doi.org/10.5573/ieie.2020.57.5.3 |
| Keywords |
Channel estimation and tracking; DNN; LSTM; Machine learning; mmWave. |
| Abstract |
The millimeter-wave (mmWave) is one of the promising technologies that support high data rates for next generation wireless communications. The mmWave possesses shortcomings, such as signal attenuation and reduced transmission distance, owing to their short wavelength and high frequencies. To overcome this issue, mmWave systems adopt beamforming techniques, which require robust channel estimation and tracking algorithms to maintain an adequate quality of service. In this paper, we propose a machine learning-based channel estimation and tracking algorithm for vehicle-to-infrastructure mmWave communications. More specifically, a deep neural network (DNN) is leveraged to learn the mapping function between the received training signals and the mmWave channel for channel estimation. Following channel estimation, long short-term memory (LSTM) is leveraged to track the channel. Simulation results demonstrate that the proposed algorithm efficiently estimates and tracks the mmWave channel with negligible training overhead. |