READ ME File For Data for Multi-User Full Duplex Transceiver Design for mmWave Systems Using Learning-Aided Channel Prediction



ReadMe Author: Satyanarayana Katla, University of Southampton ORCID ID https://orcid.org/0000-0002-5411-3962


This dataset supports the publication:
AUTHORS: K. Satyanarayana, M. El-Hajjar,  Alain Mourad  and L. Hanzo,
TITLE: Multi-User Full Duplex Transceiver Design for mmWave Systems Using Learning-Aided Channel Prediction
JOURNAL: IEEE Access
PAPER DOI IF KNOWN


 

Paper Abstract:
Millimeter Wave (mmWave) technology coupled with full duplex (FD) communication has the potential of increasing the spectral efficiency. However, the self interference (SI) encountered in the FD mode and the ubiquitous multi-user interference (MI) contaminates the signal. Furthermore, the system
performance may also be limited by channel aging that arises because of the time-varying nature of the channel. Therefore, in this paper, we conceive FD hybrid beamforming (HBF) for K-user multiple-input
multiple-output (MIMO) aided orthogonal frequency division multiplexing (OFDM) using learning-aided channel prediction. We first derive a joint precoder and combiner design for full duplex K-user MIMO-
OFDM interference channels, where we aim for minimizing both the residual SI and the MI, followed by an iterative hybrid decomposition technique developed for OFDM systems. Then, we propose a learning-
aided channel prediction technique for systems suffering from channel aging relying on a radial basis neural network, where we show by simulation that upon using sufficient training, learning-assisted channel
prediction can faithfully estimate the current channel. Furthermore, we demonstrate by simulations that our proposed joint hybrid precoder and combiner design outperforms the popular eigen beamforming (EBF)
technique by about 5 dB for a 128 × 32-element MIMO aided OFDM system having 32 sub-carriers.
 
* 

Project: 
The fiscal support of InterDigital as well as that of the EPSRC projects EP/Noo4558/1, EP/PO34284/1, of the Royal Society�s GRFC Grant and of the European Research Council�s Advanced Fellow Grant QuantCom.
 
* 

This DOI contains the datasets of Figures  6, 10, 11, and 12 of the aforementioned paper. 
Each folder is named according to its content, where the curves of each figure are stored in text files.  
To regenerate the results, please use the Graphics Layout Engine (GLE), using the command "gle Figure.gle"

* 
The  embedded folders are as follows:
  
- Figure-7: Contains the dataset of Figure 7. Pictorial representation of outdated, current and predicted channel estimates.
   
  
- Figure-8: Contains the dataset of Figure 8. Amplitude and phase of the outdated channel, of the current channel and of the predicted channel.

- Figure-9: Contains the dataset of Figure 9.  Amplitude of the predicted channel and the current channel for different Doppler spread values.
  

  
- Figure-11: Contains the dataset of Figure 11. Characterizing the BER performance for Doppler spreads of 0.01 and 0.005 with predicted channel, outdated channel and current channel. In this simulation,
BER performance is studied using predicted channel with both 100 and 200 training samples for designing the weights of the neural network. Furthermore, in this setting SI and MI is set to 3 dB.
  
- Figure-13: Contains the dataset of Figure 13. Characterizing the sum rate performance of our FD HBF design and of the EBF for different interference configurations. The parameters in Table 2 are used for simu- lations. In this simulation, channel with prediction is used.

- Figure-14: Contains the dataset of Figure 14. Characterizing the sum rate performance of our FD HBF design when pilot overhead is considered. The parameters in Table 2 are used for simulations. In this simulation, channel with prediction is used.


- Figure-15: Contains the dataset of Figure 15. Characterizing the sum rate performance of our FD HBF design and of the EBF for a given SI power with different MI levels. The parameters in Table 2 are used
for simulations. In this simulation, channel with prediction is used.





Information about geographic location of data collection: University of Southampton, U.K.

Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/


Date that the file was created: May, 2019