Tracking the nonlinear behavior of an RF power amplifier (PA) is challenging. To tackle this problem, we build a connection between residual learning and the PA nonlinearity, and propose a novel residual neural network structure, referred to as the residual real-valued time-delay neural network (R2TDNN). Instead of learning the whole behavior of the PA, the R2TDNN focuses on learning its nonlinear behavior by adding identity shortcut connections between the input and output layer. In particular, we apply the R2TDNN to digital predistortion and measure experimental results on a real PA. Compared with neural networks recently proposed by Liu et al. and Wang et al., the R2TDNN achieves the best linearization performance in terms of normalized mean square error and adjacent channel power ratio with less or similar computational complexity. Furthermore, the R2TDNN exhibits significantly faster training speed and lower training error.
Localization (position and orientation estimation) is envisioned as a key enabler to satisfy the requirements of communication and context-aware services in the sixth generation (6G) communication systems. User localization can be achieved based on delay and angle estimation using uplink or downlink pilot signals. However, hardware impairments (HWIs) distort the signals at both the transmitter and receiver sides and thus affect the localization performance. While this impact can be ignored at lower frequencies where HWIs are less severe, and the localization requirements are not stringent, modeling and analysis efforts are needed for high-frequency 6G bands (e.g., sub-THz) to assess degradation in localization accuracy due to HWIs. In this work, we model various types of impairments for a sub-THz multiple-input-multiple-output communication system and conduct a misspecified Cramér-Rao bound analysis to evaluate HWI-induced performance losses in terms of angle/delay estimation and the resulting 3D position/orientation estimation error. Complementary to the localization analysis, we also investigate the effect of individual and overall HWIs on communication in terms of symbol error rate (SER). Our extensive simulation results demonstrate that each type of HWI leads to a different level of degradation in angle and delay estimation performance. The prominent factors on delay estimation (e.g., phase noise and carrier frequency offset) will have a dominant negative effect on SER, while the impairments affecting only the angle estimation (e.g., mutual coupling and antenna displacement) induce slight degradation in SER performance.
Neural networks (NNs) for multiple hardware impairments mitigation of a realistic direct conversion transmitter are impractical due to high computational complexity. We propose two methods to reduce the complexity without significant performance penalty. First, propose a novel NN with shortcut connections, referred to as shortcut real-valued timedelay neural network (SVDEN), where trainable neuron-wise shortcut connections are added between the input and output layers. Second, we implement a NN pruning algorithm that gradually removes connections corresponding to minimal weight magnitudes in each layer. Simulation and experimental results show that SVDEN with pruning achieves better performance for compensating frequency-dependent quadrature imbalance and power amplifier nonlinearity than other NN-based and Volterrabased models, while requiring less or similar complexity. I. INTRODUCTIONRadio frequency (RF) direct conversion transceivers suffer from multiple hardware impairments due to analog hardware imperfections [2] such as non-ideal digital-to-analog converters (DACs), nonlinear active lowpass filters (LPFs), imperfect local oscillators (LOs), and nonlinear power amplifiers (PAs). These impairments induce various signal distortions which degrade the quality of the transmitted signal, leading to reduced performance in terms of throughput [3]. These impairments can be mitigated separately by different algorithms, but separate optimization of each algorithm makes their combination not globally optimal.PA nonlinearity is one of the major hardware impairments [4]. In the frequency domain, PA nonlinearity materializes as in-band errors and out-of-band emissions due to intermodulation and harmonic products [5]. PAs further exhibit memory effects during operation over large bandwidths [6], i.e., past input signals have nonlinear effects on the instantaneous output of the PA. To linearize the PA, it is customary to apply digital predistortion (DPD) [7], which compensates for the signal distortion caused by the PA nonlinearity, so that the cascade of the DPD and the PA is a linear system. Quadrature (I/Q) imbalance is another major impairment [8],
We study model-based end-to-end learning in the context of integrated sensing and communication (ISAC) under hardware impairments. A monostatic orthogonal frequencydivision multiplexing (OFDM) sensing and multiple-input singleoutput (MISO) communication scenario is considered, incorporating hardware imperfections at the ISAC transceiver antenna array. To enable end-to-end learning of the ISAC transmitter and sensing receiver, we propose a novel differentiable version of the orthogonal matching pursuit (OMP) algorithm that is suitable for multi-target sensing. Based on the differentiable OMP, we devise two model-based parameterization strategies to account for hardware impairments: (i) learning a dictionary of steering vectors for different angles, and (ii) learning the parameterized hardware impairments. For the single-target case, we carry out a comprehensive performance analysis of the proposed model-based learning approaches, a neural-networkbased learning approach and a strong baseline consisting of least-squares beamforming, conventional OMP, and maximumlikelihood symbol detection for communication. Results show that learning the parameterized hardware impairments offers higher detection probability, better angle and range estimation accuracy, lower communication symbol error rate (SER), and exhibits the lowest complexity among all learning methods. Lastly, we demonstrate that learning the parameterized hardware impairments is scalable also to multiple targets, revealing significant improvements in terms of ISAC performance over the baseline.Index Terms-Hardware impairments, integrated sensing and communication (ISAC), joint communication and sensing (JCAS), machine learning, model-based learning, orthogonal matching pursuit (OMP). I. INTRODUCTIONN EXT-generation wireless communication systems are expected to operate at higher carrier frequencies to meet the data rate requirements necessary for emerging use cases such as smart cities, e-health, and digital twins for manufacturing [1]-[4]. Higher carrier frequencies also enable new functionalities, such as integrated sensing and communication (ISAC).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.