Search

Summary: In this manuscript, optimized wireless communication for 6G signals processing using memory‐augmented deep unfolding network (WC‐6G‐SP‐MADUN) is proposed. The aim of this work is to give a memory‐augmented deep unfolding network approach with a focus on belief propagation decoding of error correction codes and multiple‐input multiple‐output (MIMO) wireless systems. In contrast, compares and tabulates the performance of memory‐augmented deep unfolding methodologies with classic principled procedures, which could potentially enable 6G. Here, the wireless communication for 6G signal processing methods was used for a variety of receiver functions, including self‐interference cancelation, signal estimation and detection using memory‐augmented deep unfolding Network (MADUN), and advanced error correction by clouded leopard optimization algorithm (CLOA). Furthermore, outline the general framework of memory‐augmented deep unfolding method for any kind of signal processing application and talk about cutting edge research paths that will make it possible to build communication networks in the future. The proposed approach is implemented in MATLAB; the performance is analyzed with performance metrics such as reliability, complexity, SNR gain, convergence rate, hardware efficiency, and quantization bit width. The proposed approach attains higher SNR gain 17.96%, 24.75%, and 30.09%; lower complexity 17.92%, 23.41%, and 30.13%; and higher convergence 18.01%, 25.41%, and 31.39% when analyzed with existing techniques such as redefined wireless communication for 6G: signal processing meets deep learning and deep unfolding (RWC‐6G‐SP‐DU), lower complication deep unfolded neural network receiver for MIMO under probability data association detector (LC‐DUNN‐MIMO‐PDAD), and deep learning in physical layer communications: evolution with prospects on 5G and 6G networks (DL‐PLC‐6G), respectively. [ABSTRACT FROM AUTHOR]

Orthogonal frequency division multiplexing (OFDM) is considered a crucial and fundamental potential approach because of its significance and role with regards to broadband wireless communication systems. The swarm intelligence optimization approach has been deployed to facilitate frequency offset optimization. An improved artificial bee colony (IABC) based optimization approach is proposed in this work that will enable ultra wideband orthogonal frequency division multiplexing (UWBOFDM) system, which will then be deployed in the carrier frequency offset (CFO) joint estimation and also for sampling frequency offset (SFO). By proper selection of cyclic delay times, correlation existing between adjacent sub carriers, a joint estimation of both CFO and SFO has been derived by employing IABC. The performance of the proposed algorithm is compared with the existing estimators, and this comparison is carried out by MATLAB7.2 simulation, which clearly depicts that the performance of the proposed algorithm is superior in terms of estimation accuracy. The performances are measured in terms of the mean square error (MSE), signal-to-noise ratio (SNR) and normalized mean square error (NMSE). The proposed approach considered for transmitter (t=4) and receiver (r=4) with SNR is 30 dB, which achieves MSE of about 0.35 %. Similarly, when (t=2) and (r=2), the proposed IABC approach achieves MSE of about 0.4 %, whereas particle swam optimization (PSO) and maximum likelihood estimator (MLE) methods achieve 0.42 and 0.44 % MSE values, respectively. On the other hand, considering (t=4) and (r=4) with SNR of 8 dB, the proposed approach achieves NMSE of about 0.0008 %. However, considering (t=2) and (r=2), the NMSE values of IABC approach, PSO, and MLE are observed to be 0.002, 0.008, and 0.08 %, respectively, for Channel Model 4 (CM4). [ABSTRACT FROM AUTHOR]