Abstract
This paper proposes online-learning complex-valued neural networks (CVNNs) to predict future channel states in fast-fading multipath mobile communications. CVNN is suitable for dealing with a fading communication channel as a single complex-valued entity. This framework makes it possible to realize accurate channel prediction by utilizing its high generalization ability in the complex domain. However, actual communication environments are marked by rapid and irregular changes, thus causing fluctuation of communication channel states. Hence, an empirically selected stationary network gives only limited prediction accuracy. In this paper, we introduce regularization in the update of the CVNN weights to develop online dynamics that can self-optimize its effective network size by responding to such channel-state changes. It realizes online adaptive, highly accurate and robust channel prediction with dynamical adjustment of the network size. We demonstrate its online adaptability in simulations and real wireless-propagation experiments.
Highlights
Performance of mobile communications always suffers from signal degradation, namely fading, due to path loss, shadowing, interference and channel state changes caused by movement of users [1]
Before demodulation of orthogonal frequency-division multiplexing (OFDM) and quadrature phase shift keying (QPSK), the received signals are compensated by the predicted channel states using multiple prediction methods, namely, methods based on a linear prediction directly in the time domain, an AR model using channel characteristics estimated by Chirp Z-transform (CZT), a long short-term memory (LSTM) network [53], [54], the conventional complex-valued neural networks (CVNNs), and the proposed CVNN with the L1-norm and L2,1-norm penalties
In this article, we proposed online adaptive channel prediction methods based on multiple-layer complex-valued neural network (ML-CVNN) with self-optimizing dynamic structures
Summary
Performance of mobile communications always suffers from signal degradation, namely fading, due to path loss, shadowing, interference and channel state changes caused by movement of users [1]. We proposed a prediction method based on a multiple-layer complex-valued neural network (ML-CVNN) by focusing rotary motion of the channel state in the complex plane In this method, an online training scheme was introduced in order to follow time varying channel states [13]. The major contributions of our study can be summarized as follows: 1) Proposal of complex-valued update schemes that self-adjust network structures to provide suitable network size by responding complicated channel states; 2) Design of new channel prediction methods based on dynamic ML-CVNNs with the proposed network structures and BPTS for an adaptive prediction; 3) Verification of the fact that the proposed fast fading prediction has a performance superior to other approaches on simulated and experimentally observed channel states.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
