Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning

Following the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides a significant gain (almost 40%) with 10.7% compared to the linear model with the lowest RMSE (Root Mean Squared Error) 17.01%. The solution can be adopted as a part of the data allocation algorithm implemented in the telemetry devices equipped with the 4G radio interface, or, after the adjustment, the NB-IoT (Narrowband Internet of Things), to maximize the reliability of the services in harsh indoor or urban environments. Presented results also prove the existence of the inverse proportional dependence between the number of hidden layers and the number of historical samples in terms of the obtained RMSE. The increase of the historical data memory allows using models with fewer hidden layers while maintaining a comparable RMSE value for each scenario, which reduces the total computational cost.

Improvement of Pilot Symbol Orthogonal Sequences in 2×2 to 4×4 MIMO Wireless Communication Systems with Channel State Estimation

MIMO wireless communication systems with channel state estimation, in which 2 to 4 transmit-receive antenna pairs are employed, are simulated. The channel estimation is fulfilled by the orthogonal pilot signal approach, where the Walsh Hadamard-ordered sequences are commonly used for piloting. The signal is modulated by applying the quaternary phase shift keying method. Maximum 250 000 packets are transmitted through flat-fading Rayleigh channels, to which white Gaussian noise is added. Based on simulating 10 subcases of the frame length and number of pilot symbols per frame, it is ascertained that pilot symbol orthogonal sequences in 2×2 to 4×4 MIMO systems can be improved by substituting Walsh functions with partially unsymmetrical binary functions constituting the eight known orthogonal bases. The benefit is that the bit-error rate is substantially decreased, especially for 2×2 MIMO systems. Considering three cases of the pilot signal de-orthogonalization caused by two indefinite and definite pilot sequence symbol errors, the relative decrement varies from 0.123 % to 14.7 %. However, the decrement becomes less significant as the number of transmit-receive antenna pairs is increased.

Hierarchical Data Decision Aided 2-Source BPSK H-MAC Channel Phase Estimator with Feed-Back Gradient Solver for WPNC Networks and Its Equivalent Model

This paper focuses on the channel state estimation (CSE) problem in parametrized Hierarchical MAC (H-MAC) stage in Wireless Physical Layer Network Coding (WPNC) networks with Hierarchical Decode and Forward (HDF) relay strategy. We derive a non-pilot based H-MAC channel phase estimator for 2 BPSK alphabet sources. The CSE is aided only by the knowledge of H-data decisions. At HDF relay, there is no information on individual source symbols available. The estimator is obtained by a marginalization over the hierarchical dispersion. The estimator uses a gradient additive update solver and the indicator function (gradient) is derived in exact closed form and in approximations for low and high SNR. We analyze the properties of the equivalent solver model, particularly the equivalent gradient detector characteristics and its main stable domain properties, and also the detector gain and equivalent noise properties under a variety of channel parameterization scenarios.

Optimization of Iterative Channel State Estimation Algorithms in SCMA System

Optimization of iterative algorithms for channel state estimation in a sparse coding multiple-access system (SCMA) is performed to reduce computational costs of the receiver. It is shown that when a signal-to-noise ratio (SNR) does not exceed 10 dB, one iteration of the algorithm is sufficient, and an increase in the number of iterations does not lead to an increase in spectral efficiency. Simulation demonstrates a possibility of a reasonable choice of the total number of decoder iterations and their distribution between different stages of the channel estimation. For an uncoded system, iterative re-estimation of the channel is proposed, as well as ways to reduce computational costs during its calculation. In the coded system, at a low SNR the achieved spectral efficiency values are approximately similar to those with pilot-only channel estimation. The article provides recommendations for the placement of data symbols and pilot signals in re-source blocks to increase the system spectral efficiency.