Abstract
In this article, a series of convolutional-type predictive neural networks are proposed for the issue of fading channel forecasting for orthogonal frequency-division multiplexing (OFDM) transmission systems in a multiple-input and multiple-output (MIMO) mode via a noisy channel. The proposed neural networks all employ convolutional connections that operate in a translation-invariant manner in the frequency domain of the time-varying channel transfer function, which effectively tackles the essential challenges of high dimensionality and denoising. Each of the proposed convolutional-type neural networks is built on a specific overall network architecture and functions as an independent predictor that offers advantages regarding a specific aspect such as accuracy over a certain prediction span or computational effort. Comparative evaluations against common prediction methods such as the Kalman filtering scheme and the standard long-short term memory units (LSTMs) are provided on the basis of transmission simulations over dispersive fading channels with Rayleigh components according to the well-established 3GPP Long Term Evolution (LTE) standards.
Highlights
D YNAMIC radio resource management and adaptive modulation and coding schemes are essential parts of modern cellular networks
In accordance with the loss function defined in (6) which is optimised through training, the performance of each considered predictor is measured by the mean squared error (MSE) of the prediction
In order to assess and compare the capability of different predictors, in this work, each of the proposed predictive neural networks is treated as a time-invariant model and trained offline on a dataset associated with certain propagation conditions, which implicitly assumes a weak form of homogeneity in time of the observation and target time series Hest, Htrue
Summary
D YNAMIC radio resource management and adaptive modulation and coding schemes are essential parts of modern cellular networks. In order to maximise spectral efficiency, it is necessary for these schemes to be adapted to the current channel transmission properties. Since scheduling and coding have to be performed before the actual transmission, it is necessary to anticipate the channel quality ahead of time. In the presence of multipath propagation and moving receivers, time variance in the channel transfer function and frequency selective fading significantly increase the complexity of the issue of channel quality forecasting which requires a powerful predictive model. A big challenge when forecasting noisy time series in such a context consists in the high dimensionality issue arising in the multi-subcarrier setting. This work aims to design predictive models that are parsimonious but still complex enough to capture the essential characteristics of such highdimensional noisy time series
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.
