Machine Learning-Based Channel State Estimators for 5G Wireless Communication Systems

проведено исследованию методов оценки состояния канала связи (CSI) в ортогональном частотно-разделённом мультиплексировании (OFDM), применяемом в современных стандартах беспроводной связи, таких как LTE, Wi-Fi и 5G. Рассматриваются традиционные методы оценки канала, такие как Least Squares (LS) и Minimum Mean Square Error (MMSE), отмечаются их недостатки в сложных условиях, связанных с многолучевым распространением сигнала и высокой мобильностью абонентов. Рассмотрено перспективное направление оценки канала связи — глубокое обучение (DL). Доказано, что применение нейронных сетей позволяет существенно повысить точность оценки канала. Приводятся примеры исследований, использующих свёрточные нейронные сети (CNN) и другие архитектуры нейронных сетей для улучшения качества оценки CSI. Отмечено, что ряд аспектов применения нейронных сетей требует дальнейшего изучения, включая оптимизацию моделей под изменяющиеся условия среды и снижение вычислительной сложности. Предлагаются новые подходы для повышения эффективности оценки канала, среди которых использование рекуррентных нейронных сетей (RNN) и методов сжатия моделей (квантование и прунинг). Результаты экспериментов продемонстрировали потенциал использования RNN для эффективной оценки канала связи и восстановления сигналов в OFDM-системах. Моделирование подтвердило преимущество рекуррентных нейронных сетей над CNN в плане потребления вычислительных ресурсов, при сохранении сопоставимой производительности. Описана важность внедрения глубоких нейронных сетей для совершенствования технологии OFDM и предложены направления дальнейших исследований и разработок we conducted a study of methods for assessing the state of a communication channel (CSI) in orthogonal frequency-divided multiplexing (OFDM), used in modern wireless communication standards such as LTE, Wi-Fi and 5G. We considered traditional channel estimation methods such as Least Squares (LS) and Minimum Mean Square Error (MMSE), and their disadvantages are noted in difficult conditions associated with multipath signal propagation and high subscriber mobility. We considered a promising area of communication channel assessment, deep learning (DL). We proved that the use of neural networks can significantly improve the accuracy of channel estimation. We give examples of studies using convolutional neural networks (CNNs) and other neural network architectures to improve the quality of CSI assessment. We note that a number of aspects of the use of neural networks require further study, including optimizing models for changing environmental conditions and reducing computational complexity. We proposed new approaches to improve the efficiency of channel estimation, including the use of recurrent neural networks (RNNs) and model compression methods (quantization and pruning). The simulation confirmed the advantage of recurrent neural networks over CNNs in terms of computing resource consumption, while maintaining comparable performance. The experimental results demonstrated the potential of using RNN for effective assessment of communication quality and signal recovery in OFDM systems. We proposed the importance of the introduction of deep neural networks for the improvement of OFDM technology is described and the directions of further research and development

In this article, we explore the use of neural networks (NNs) to enhance the performance evaluation of Universal Filtered Multi-Carrier (UFMC) systems, a key technology for modern communication networks such as 5G and beyond. Traditional methods of evaluating the Bit Error Rate (BER) and system efficiency in UFMC system can be computationally intensive and less accurate under dynamic conditions. To address these challenges, we propose a NN based approach that not only improves the accuracy of BER prediction but also significantly optimizes the system's overall efficiency. Channel state estimation (CSE) plays a major role for UFMC system to address the phenomenon of multipath channel fading. In order to achieve a high data rate using UFMC technology, it is necessary to have an effective CSE and very accurate signal detection. Recently, there has been significant interest in utilizing deep learning (DL) to enhance channel estimations. This article introduces a new method for channel estimation (CE) in UFMC system. The suggested approach utilizes DL models to improve the CE. For the UFMC system, we propose a detector based on bidirectional long short-term memory (Bi-LSTM). To identify the transmitted symbols, the suggested detector uses DL training data directly. Currently, a significant drawback of UFMC systems is the presence of a high peak-to-average power ratio (PAPR). The approach aims to reduce the BER and enhances the efficiency of the UFMC system. This is achieved by dynamically setting the constellation mapping and symbol damping on each subcarrier and sub-symbol. The results illustrate that the proposed model can accurately and efficiently recognize UFMC signals. The suggested model is being compared to Least Square (LS), LSTM, and Minimum Mean Square Error (MMSE) channel estimators. Through extensive simulations, our results demonstrate that the NN model reduces BER and enhances efficiency. The proposed model gives more effective performance in terms of enhanced efficiency and reduction of BER. The findings offer valuable insights for the design and optimization of next-generation communication systems, where accurate and efficient performance evaluation is critical.

Vector quantisation for joint source‐channel (JSC) coding over a finite‐state Markov channel (FSMC) is studied. In particular, minimum mean square error (MMSE) decoding of a vector quantised source in the absence of channel state information (CSI) is considered. Based on hidden Markov modelling of the channel output, two decoding strategies are proposed. The first one is a soft‐decoder which estimates the source reconstruction vectors directly from a sequence of channel output samples. The second one is a hard‐decoder based on joint maximum a posteriori (MAP) probability estimation of channel symbols and channel states. An iterative procedure for designing JSC optimised vector quantisers (VQs) is also proposed. Finally, the design of VQs for wireless channels using a finite‐state model is examined. Experimental results are provided for a Gauss‐Markov source and flat‐fading wireless channels. A comparison with an idealised tandem source‐channel coding system is also provided to demonstrate the advantage of the proposed JSC coding approach. Copyright © 2007 John Wiley & Sons, Ltd.

<abstract><p>Advanced wireless communication technologies, such as 5G, are faced with significant challenges in accurately estimating the transmitted signal and characterizing the channel. One of the major obstacles is the interference caused by the delay spread, which results from receiving multiple signal copies through different paths. To mitigate this issue, the orthogonal frequency division modulation (OFDM) technique is often employed. Efficient signal detection and optimal channel estimation are crucial for enhancing the performance of multi-carrier wireless communication systems. To this end, this paper proposes a Long Short Term Memory-Projected Layer (LSTM-PL) deep neural network(DNN) based channel estimator to detect received OFDM signal. The results show that the LSTM-PL algorithm outperforms traditional methods such as Least Squares(LS), Minimum Mean Square Error (MMSE) and other LSTM deep learning channel estimation methods like Long Short Term Memory(LSTM)-DNN and Bidirectional-LSTM(Bi-LSTM)-DNN, as evidenced by Symbol-Error Rate (SER) outcomes.</p></abstract>

With the increasing rate of wireless devices and high bandwidth operations, wireless networking and communications are becoming over crowded. To cope with such crowded and messy situation, massive MIMO is designed to work with hundreds of low-cost serving antennas at a time as well as improve the spectral efficiency at the same time. Time Division Duplexing (TDD) has been used for gaining beamforming which is a major part of massive MIMO, to gain its best improvement to transmit and receive pilot sequences. All the benefits are only possible if the channel state information or channel estimation is gained properly. Least Square (LS), Minimum Mean Square Error (MMSE) and Linear Minimum Mean Square Error (LMMSE) are the estimators commonly used for estimating channel matrices. We have optimized these methods using genetic algorithm to minimize the mean squared error and finding the best channel matrix from existing algorithms with less computational complexity. Our simulation result has shown that the use of Genetic Algorithm (GA) worked well on existing algorithms in a Rayleigh slow fading channel and existence of Additive White Gaussian Noise. We found that the GA optimized LS is better than existing algorithms. GA provides optimal result in some few iterations in terms of Mean Square Error (MSE) with respect to SNRand computational complexity.

Signal detection is crucial in multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, yet classical detection methods often struggle with nonlinear issues in wireless channels. To handle this challenge, we propose a novel signal detection method for MIMO-OFDM system based on the fractional Fourier transform (FrFT), leveraging the robust time series processing capabilities of long short-term memory (LSTM) networks. Our innovative approach, termed IM-LSTMNet, integrates LSTM with convolutional neural networks (CNNs) and incorporates a Squeeze and Excitation Network to emphasize critical information, enhancing neural network performance. The proposed IM-LSTMNet is applied to the FrFT-based MIMO-OFDM system to improve signal detection performance. We compare the detection results of IM-LSTMNet with zero forcing (ZF), minimum mean square error (MMSE), simple LSTM neural network, and CNN–LSTM network by evaluating the bit error rate. Experimental results demonstrate that IM-LSTMNet outperforms ZF, MMSE, LSTM, and other methods, significantly enhancing system signal detection performance. This work offers a promising advancement in MIMO-OFDM signal detection, presenting a deep learning-based solution that effectively improves the system signal detection performance.

This paper studies the effect of channel estimation in WiMAX system. The channel estimation is based on the principle of pilot-symbol-aided channel estimation (PACE) in frequency domain. The algorithms used here are based on the least squares (LS) and the minimum mean squares error (MMSE) approaches. Furthermore we propose a simple method to reduce the computation complexity of MMSE algorithm significantly which has a desirable performance. In the end, our result will quantitatively demonstrate the effect of LS, MMSE and proposed low complexity MMSE algorithms for uncoded IEEE802.16d standard of WiMAX system.

Visible light communication (VLC) has been proposed as a promising way for next generation wireless communication networks to mitigate the scarcity of the radio frequency (RF) spectrum, and has consequently attracted much attention. This paper introduces a single-input single-output (SISO) VLC system under the joint effects of statistical random channel and signal-dependent shot noise (SDSN). Moreover, it estimates the channel of the considered system using maximum likelihood (ML), least square (LS), linear minimum mean square error (LMMSE), maximum posteriori probability (MAP) and minimum mean square error (MMSE) estimators. Furthermore, a Bayesian Cramér-Rao lower bound (BCRLB) is derived for the proposed system and it is compared to the mean square error (MSE) of the proposed estimators. The problem of unknown SDSN factor, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\zeta ^{2}$</tex-math></inline-formula> , at the receiver side is discussed and two solutions are investigated. The receiver of a VLC system under SDSN and random channel gain <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$h$</tex-math></inline-formula> is designed and its BER is studied. Finally, Monte Carlo simulation results of the proposed estimators, which show the dramatic effect of the SDSN on the considered system, are provided. In particular, the presence of noise variance, as well as the SDSN factor, causes an increase in the MSE of the system, while increasing the power reinforces the system performance.

Energy is integral to the socio-economic development of every country. This development leads to a rapid increase in the demand for energy consumption. However, due to the constraints and costs associated with energy generation resources, it has become crucial for both energy generation companies and consumers to predict energy consumption well in advance. Forecasting energy needs through accurate predictions enables companies and customers to make informed decisions, enhancing the efficiency of both energy generation and consumption. In this context, energy generation companies and consumers seek a model capable of forecasting energy consumption both in the short term and the long term. Traditional models for energy prediction focus on either short-term or long-term accuracy, often failing to optimize both simultaneously. Therefore, this research proposes a novel hybrid model employing Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional LSTM (Bi-LSTM) to simultaneously predict both short-term and long-term residential energy consumption with enhanced accuracy measures. The proposed model is capable of capturing complex temporal and spatial features to predict short-term and long-term energy consumption. CNNs discover patterns in data, LSTM identifies long-term dependencies and sequential patterns and Bi-LSTM identifies complex temporal relations within the data. Experimental evaluations expressed that the proposed model outperformed with a minimum Mean Square Error (MSE) of 0.00035 and Mean Absolute Error (MAE) of 0.0057. Additionally, the proposed hybrid model is compared with existing state-of-the-art models, demonstrating its superior performance in both short-term and long-term energy consumption predictions.

An orthogonal frequency division multiplexing (OFDM) is one of the effective techniques used in wireless communications. In OFDM systems, channel impairments due to multipath dispersive wireless channels can cause deep fades in wireless channels. The OFDM receiver also requires an accurate and computationally efficient channel state information when coherent detection is involved. Therefore, it needs a good robust estimation method of the channel in wireless communication for OFDM systems. And one of these channel estimation methods is minimum mean square error (MMSE) channel estimation. MMSE channel estimation one most used method in OFDM systems. In this work we enhanced robustness of MMSE channel estimation by using it in base of quasi-cyclic low density parity check (QC-LDPC) coded OFDM system.

Multipath channels often exhibit sparse structures in multicarrier underwater acoustic (MC-UWA) communication systems. Conventional linear channel estimators, such as least squares (LS) and minimum mean square error (MMSE) are considered as optimal solutions under the assumption of rich multipath. However, they often result in low spectral efficiency due to neglect of the sparsity in multipath channels. In this paper, we propose a novel sparse channel estimation method with compressive sensing. The proposed estimator has better estimation performance and low complexity when compared with the LS estimator. Simulations verified the proposed method with respect to the mean square error (MSE) and the computational complexity. Key words: Underwater acoustic (UWA), orthogonal frequency division multiplexing (OFDM), sparse multipath, compressive sensing (CS), sparse channel estimator.

Multiple-input multiple-output (MIMO) systems can achieve high data-rate and high capacity transmission. In MIMO systems, the scheme that weight substreams based on minimum mean square error (MMSE) criterion at the transmitter using feedback channel state information (CSI) achieves good performance (denoted hereafter as MMSE precoder). However, if the optimum number of substreams is not selected based on CSI and methods for reducing the performance degradation due to feedback delay is not used, MMSE precoder cannot achieve the full performance possible. In this paper, we propose an MMSE precoder with mode selection for MIMO systems, which selects both the number of substreams and the modulation scheme for each substream to minimize the average BER at a fixed rate. We evaluate the BER of the proposed MMSE precoder with two methods for reducing performance degradation due to feedback delay, channel prediction and receive weight robust to feedback delay. We also evaluate the BER of the proposed MMSE precoder with the method that combines channel prediction with receive weight robust to feedback delay. Simulation results show that the BER of the proposed MMSE precoder is improved compared to that of the conventional MMSE precoder using the fixed number of substreams. We also show that the method that combines channel prediction with receive weight robust to feedback delay can achieve good BER even when the large feedback delay exists.

We generalize the multiuser (CDMA spread spectrum) communication systems to the fading environments. We first extend Verdu's (1986) conventional optimum receiver to Rayleigh-fading environments and then evaluate its performance. Having no knowledge of the received power at the receiving end, we therefore need an estimator to efficiently estimate the received signal strength of each user in fading environments. A linear minimum mean square error (LMMSE) unbiased estimator is proposed to attain this goal. By using the minimum mean square error (MMSE) Bayesian estimation, we further propose the LMMSE bit estimator for efficient demodulation. Its performance is close to the optimum multiuser receiver but with a much simpler polynomial complexity. To further reduce the complexity, we extend the LMMSE estimator to the sequential LMMSE estimator. In sequential estimation, we do not need to implement the matched filter banks and to perform the matrix inversion when estimating. In addition, it converges after approximately 2k iterations, where k is the number of users. With this fast convergence property and the simple structure, the sequential LMMSE estimator provides an attractive alternative to the implementation of a multiuser system.

In present days, there has been a race among the communication systems in different schemes and generations. Gradually the transmission rate of data is increasing tremendously and breaking the previous generation's record. Now people are thinking of transmitting data beyond imagination. Using multiple antennas both at transmitter and receiver side, MIMO wireless technology efficiently provides very high spectral efficiency, boost the data transmission rate, enhance link reliability and improve system coverage. While transmitting data over mobile radio channels at high bit rates, the impulse response of the channel can be extended over a lot of symbol periods, leading fading and Inter-symbol interference (lSI). Equalizers are used to minimize Fading and interference effects. The analysis of the paper is studying the performance of Minimum mean square error method in terms of BER for MIMO (2×2) and (3×3) wireless channels. Binary Phase Shift Keying (BPSK) modulation technique was used in Rayleigh flat fading channel. Simulating in MATLAB results show that Minimum mean square error (MMSE) receivers is good for noise free channel and is successful in removing ISI. Successive interference method with optimal ordering outperforms the MMSE however a few problems arise because of iterative nature of the algorithm.

In orthogonal frequency-division multiplexing (OFDM) systems, it is generally assumed that the channel response is static in an OFDM symbol period. However, the assumption does not hold in high-mobility environments. As a result, intercarrier interference (ICI) is induced and the system performance is degraded. A simple remedy for this problem is the application of the zero-forcing (ZF) and minimum mean square error (MMSE) equalizers. Unfortunately, the direct ZF method requires the inversion of an NxN ICI matrix, where N is the number of subcarriers. When N is large, the computational complexity can become prohibitively high. As for the direct MMSE method, in addition to an NxN matrix inverse, it requires an extra NxN matrix multiplication, making the required computational complexity higher compared to the direct ZF method. In this dissertation, we first propose a low-complexity ZF method to solve the problem in single-input-single-output (SISO) OFDM systems. The main idea is to explore the special structure inherent in the ICI matrix and to apply Newton's iteration for matrix inversion. With our formulation, fast Fourier transforms (FFTs) can be used in the iterative process, reducing the complexity from O(N^3) to O(Nlog_2 N) . Also, the required number of the iteration is typically one or two. We also analyze the convergence behavior of the proposed method and derive the theoretical output signal-to-interference-noise-ratio (SINR). For the MMSE method, we first reformulate the MMSE solution in a way that the extra matrix multiplication can be avoided. Similar to the ZF method, we then exploit the structure of the ICI matrix and apply Newton's iteration to reduce the complexity of the matrix inversion. For a multiple-input-multiple-output (MIMO) OFDM system, the required complexity of the ZF and MMSE methods becomes more intractable. We then manage to extend the proposed ZF and MMSE methods for SISO-OFDM systems to MIMO-OFDM systems. It turns out that the computational complexity can be reduced even more significantly. Simulation results show that the performance of the proposed methods is almost as good as that of the direct ZF and MMSE methods, while the required computational complexity is reduced dramatically. Finally, we explore the application of the proposed methods in mobility-induced ICI mitigation for OFDM multiple access (OFDMA) systems, and in carrier frequency offset (CFO) induced ICI mitigation for OFDMA uplink systems. As that in OFDM systems, the proposed methods can reduce the required computational complexity, effectively.