An efficient and reliable OFDM channel state estimator using deep learning convolutional neural networks (original) (raw)
Related papers
Channel estimation for OFDM systems
2011
Orthogonal frequency division multiplexing (OFDM) has attracted a lot of attention because of its high data rate, high spectrum efficiency and robustness against frequency-selective fading channels This paper addresses channel estimation based on time-domain channel statistics. Here the statistical characteristics of AWGN channel is estimated using different methods like LS, MMSE and DFT-CE. The channel autocorrelation matrix and noise variance is obtained by using the noise suppressed channel impulse response. In this paper an efficient and improved channel estimation technique is presented using the MMSE channel estimation method.
Journal of Electrical Engineering
Deep learning (DL) algorithms can enhance wireless communication system efficiency and address numerous physical layer challenges. Channel state estimation (CSE) and signal detection (SD) are essential parts of improving the performance of an OFDM wireless system. In this context, we introduce a DL model as an effective alternative for implicit CSE and SD over Rayleigh fading channels in the OFDM wireless system. The DL model is based on the gated recurrent unit (GRU) neural network. The proposed DL GRU model is trained offline using the received OFDM signals related to the transmitted data symbols and added pilot symbols as inputs. Then, it is implemented online to accurately and directly detect the transmitted data. The experimental results using the metric parameter of symbol error rate show that, the proposed DL GRU-based CSE/SD provides superior performance compared with the traditional least square and minimum mean square error estimation methods. Also, the trained DL GRU mode...
Deep Learning Channel Estimation for OFDM 5G Systems with Different Channel Models
Wireless Personal Communications
At cellular wireless communication systems, channel estimation (CE) is one of the key techniques that are used in Orthogonal Frequency Division Multiplexing modulation (OFDM). The most common methods are Decision‐Directed Channel Estimation, Pilot-Assisted Channel Estimation (PACE) and blind channel estimation. Among them, PACE is commonly used and has a steadier performance. Applying deep learning (DL) methods in CE is getting increasing interest of researchers during the past 3 years. The main objective of this paper is to assess the efficiency of DL-based CE compared to the conventional PACE techniques, such as least-square (LS) and minimum mean-square error (MMSE) estimators. A simulation environment to evaluate OFDM performance at different channel models has been used. A DL process that estimates the channel from training data is also employed to get the estimated impulse response of the channel. Two channel models have been used in the comparison: Tapped Delay Line and Cluste...
Training Based Channel Estimation in OFDM Systems
International Journal of Technical Research & Science, 2018
In this paper the Proposed new scheme in order to implement an MMSE Channel estimator for an OFDM System we know that the time domain maximum likelihood estimators (MSE) Can achieve highly accurate impulse response estimation by using time domain long preamble of an OFDM frame. The Least Square algorithm is easier for the channel estimation. The impulse response estimation based on the minimum mean square error (MMSE) Criterion can achieve superior channel estimation in low SNR conditions.
On Channel Estimation in OFDM Systems
The use of multi-amplitude signaling schemes in wireless OFDM systems requires the tracking of the fading radio channel. This paper addresses channel estimation based on time-domain channel statistics. Using a general model for a slowly fading channel, we present the MMSE and LS estimators and a method for modifications compromising between complexity and performance. The symbol error rate for a 16-QAM system is presented by means of simulation results. Depending upon estimator complexity, up to 4 dB in SNR can be gained over the LS estimator.
Channel Estimation Based on Machine Learning Paradigm for Spatial Modulation OFDM
2021 IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering MI-STA, 2021
In this paper, deep neural network (DNN) is integrated with spatial modulation-orthogonal frequency division multiplexing (SM-OFDM) technique for end-to-end data detection over Rayleigh fading channel. This proposed system directly demodulates the received symbols, leaving the channel estimation done only implicitly. Furthermore, an ensemble network is also proposed for this system. Simulation results show that the proposed DNN detection scheme has a significant advantage over classical methods when the pilot overhead and cyclic prefix (CP) are reduced, owing to its ability to learn and adjust to complicated channel conditions. Finally, the ensemble network is shown to improve the generalization of the proposed scheme, while also showing a slight improvement in its performance.
A low-complexity ML channel estimator for OFDM
IEEE Transactions on Communications, 2003
Orthogonal frequency-division multiplexing with cyclic prefix enables low-cost frequency-domain mitigation of multipath distortion. However, to determine the equalizer coefficients, knowledge of the channel frequency response is required. While a straightforward approach is to measure the response to a known pilot symbol sequence, existing literature reports a significant performance gain when exploiting the frequency correlation properties of the channel. Expressing this correlation by the finite delay spread, we build a deterministic model parametrized by the channel impulse response and, based on this model, derive the maximum-likelihood channel estimator. In addition to being optimal (up to the modeling error), this estimator receives an elegant time-frequency interpretation. As a result, it has a significantly lower complexity than previously published methods.
A Low Complexity Optimal LMMSE Channel Estimator for OFDM System
2021
Linear minimum mean square error (LMMSE) is the optimal channel estimator in the mean square error (MSE) perspective, however, it requires matrix inversion with cubic complexity. In this paper, by exploiting the circulant property of the channel frequency autocorrelation matrix RHH , an efficient LMMSE channel estimation method has been proposed for orthogonal frequency division multiplexing (OFDM) based on fast Fourier transformation (FFT) and circular convolution theorem. Finally, the computer simulation is carried out to compare the proposed LMMSE method with the classical LS and LMMSE methods in terms of performance measure and computational complexity. The simulation results show that the proposed LMMSE estimator achieves exactly same performance as conventional LMMSE estimator with much lower computational complexity.
Comparison And Analysis Of Channel Estimation Algorithms In OFDM Systems
International Journal of Scientific & Technology Research, 2013
: - The channel estimation can be performed for analyzing effect of channel on signal by either inserting pilot tones into all of the subcarriers of OFDM symbols with a specific period or inserting pilot tones into each OFDM symbol. The block type pilot channel estimation has been developed under the assumption of slow fading channel. When the data is transmitted at high bit rates, the channel impulse response can extend over many symbol periods, it leads to inter symbol interference. Orthogonal Frequency Division Multiplexing is one of the promising candidate to mitigate the ISI. This work improved various channel performance measures based on the comparison of various channel estimation algorithms and suggest a new technique which provides better performance. Keywords: - OFDM, Block Pilot symbols, Channel estimation, Linear minimum mean square error (LMMSE), Mean square error (MSE), Bit error rate (BER) ———————————————————— I. I NTRODUCTION Orthogonal Frequency Division Multiplex...
Channel Estimation Techniques in MIMO-OFDM LTE Systems
There is an increasing demand for high data transmission rates with the evolution of the very large scale integration (VLSI) technology. The multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems are used to fulfill these requirements because of their unique properties such as high spectral efficiency, high data rate and resistance towards multipath propagation. MIMO-OFDM systems are finding their applications in the modern wireless communication systems like IEEE 802.11n, 4G and LTE. They also offer reliable communication with the increased coverage area. The bottleneck to the MIMO-OFDM systems is the estimation of the channel state information (CSI). This can be estimated with the help of any one of the Training Based, Semiblind and Blind Channel estimation algorithms. This paper presents various channel estimation algorithms, optimization techniques and their effective utilization in MIMO-OFDM for modern wireless LTE systems.