Deep Learning-Based Channel Estimation Algorithm Over Time Selective Fading Channels

Abstract

The research about deep learning application for physical layer has been received much attention in recent years. In this paper, we propose a Deep Learning(DL) based channel estimator under time varying Rayleigh fading channel. We build up, train and test the channel estimator using Neural Network(NN). The proposed DL-based estimator can dynamically track the channel status without any prior knowledge about the channel model and statistic characteristics. The simulation results show the proposed NN estimator has better Mean Square Error(MSE) performance compared with the traditional algorithms and some other DL-based architectures. Furthermore, the proposed DL-based estimator also shows its robustness with the different pilot densities.

Deep Learning-Based Wireless Channel Estimation for MIMO Uncoded Space-Time Labeling Diversity

“…As can be seen, that Equation (15) contains the equivalent noise power; thus, for us to minimize the channel estimation MSE, we can find the minimum or lowest equivalent noise power. So mathematically, this is noted as follows in Equation (17):…”

“…The deep learning-based LDAMP algorithm outperforms the compressed sensing-based algorithms. In [17], a deep learning-based channel estimator is proposed for a time-varying Rayleigh fading channel. Its mean squared error performance is shown to outperform that of the traditional channel estimation algorithms.…”

MIMO Radar Aided mmWave Time-Varying Channel Estimation in MU-MIMO V2X Communications

“…DL has received widespread attention due to its feature self-learning ability and the enhancement of hardware computing power. On this base, DL has penetrated into wireless communications [19], such as channel coding and decoding [20], channel information feedback [21], beam search [22], beamforming [23], modulation recognition [24], channel estimation, and etc [25]- [27]. Aiming at the highly dynamic vehicle scene, deep neural network (DNN) is used for k-step channel prediction of space-time block codes, and then a decision-oriented channel estimation algorithm is proposed to eliminate the need for channel Doppler frequency shift estimation in [25].…”

“…X. Wang et al in [26] proposes two different channel estimation schemes, one is a data-driven end-to-end channel estimator, and the other is a model-driven channel estimator combined with communication knowledge and a small amount of training parameters. In view of the characteristics of rayleigh fading channels, an estimator named SBGRU is proposed in [27], combining RNN structure with sliding window. However, the large amount of training data required for the two schemes leads to the additional training cost.…”

Internet of radio and light: 5G building network radio and edge architecture

“…1 more akin to a radio-light home eNodeB suitable for a single building network rather than an Evolved Packet Core (EPC) suitable for a whole country. All four layers can be deployed inside the 5G Mobile Edge Computing (MEC) server, which can be used for the Artificial Intelligence (AI) and Machine Learning (ML) driven control of the eMBB and URLLC user cases for indoor environments [8] . The service layer is to (1) run server side applications for streaming audio and video, (2) receive and store results on databases and monitor security from a multicore Cloud Home Data Centre Server (CHDCS), and (3) run mobile applications from User Equipment (UE), i.e., smart phones, tablet Personal Computers (PCs), Virtual Reality (VR) and Augmented Reality (AR) headsets, and High Definition Televisions (HDTVs).…”