Convolutional-Type Neural Networks for Fading Channel Forecasting
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9235319/ |
| _version_ | 1818616796298608640 |
|---|---|
| author | Lia Ahrens Julian Ahrens Hans Dieter Schotten |
| author_facet | Lia Ahrens Julian Ahrens Hans Dieter Schotten |
| author_sort | Lia Ahrens |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-16T16:55:29Z |
| format | Article |
| id | doaj.art-a15be5e2e82848deaff49fdca62b6657 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T16:55:29Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a15be5e2e82848deaff49fdca62b66572022-12-21T22:23:53ZengIEEEIEEE Access2169-35362020-01-01819307519309010.1109/ACCESS.2020.30329339235319Convolutional-Type Neural Networks for Fading Channel ForecastingLia Ahrens0https://orcid.org/0000-0002-9382-4732Julian Ahrens1https://orcid.org/0000-0001-8194-5791Hans Dieter Schotten2German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, GermanyGerman Research Center for Artificial Intelligence (DFKI), Kaiserslautern, GermanyGerman Research Center for Artificial Intelligence (DFKI), Kaiserslautern, GermanyIn 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.https://ieeexplore.ieee.org/document/9235319/Wireless communicationsdeep learningconvolutional neural networksLSTMstime series analysisfading channel forecasting |
| spellingShingle | Lia Ahrens Julian Ahrens Hans Dieter Schotten Convolutional-Type Neural Networks for Fading Channel Forecasting IEEE Access Wireless communications deep learning convolutional neural networks LSTMs time series analysis fading channel forecasting |
| title | Convolutional-Type Neural Networks for Fading Channel Forecasting |
| title_full | Convolutional-Type Neural Networks for Fading Channel Forecasting |
| title_fullStr | Convolutional-Type Neural Networks for Fading Channel Forecasting |
| title_full_unstemmed | Convolutional-Type Neural Networks for Fading Channel Forecasting |
| title_short | Convolutional-Type Neural Networks for Fading Channel Forecasting |
| title_sort | convolutional type neural networks for fading channel forecasting |
| topic | Wireless communications deep learning convolutional neural networks LSTMs time series analysis fading channel forecasting |
| url | https://ieeexplore.ieee.org/document/9235319/ |
| work_keys_str_mv | AT liaahrens convolutionaltypeneuralnetworksforfadingchannelforecasting AT julianahrens convolutionaltypeneuralnetworksforfadingchannelforecasting AT hansdieterschotten convolutionaltypeneuralnetworksforfadingchannelforecasting |