GroupSubPlot(monitor, "Loss", "TrainingLoss") Create a dlnetwork for the NN-DPD-Forward and another for the NN-DPD-Train. Custom training loops require dlnetwork objects. Set the memory depth to 5 and degree of nonlinearity to 5. Memory length and degree of nonlinearity determine the input length, as described in the Power Amplifier Characterization (Communications Toolbox) example. NN-DPD has three fully connected hidden layers followed by a fully connected output layer. X = randi(,numDataCarriers,symPerFrame) ĭpdInput = single(ofdmmod(qamRefSym/osf,ofdmParams.fftLength,ofdmParams.cpLength. NullIdx = [1:ofdmParams.NumGuardBandCarrier/2+1. NumDataCarriers = (ofdmParams.fftLength - ofdmParams.NumGuardBandCarrier - 1) OfdmParams = helperOFDMParameters(bw,osf) Osf = 5 % oversampling factor for PA input % OFDM parameters M = 16 % Each OFDM subcarrier contains a 16-QAM symbol As a result, the NN-DPD is trained as the inverse of the PA. Its input signal is the PA output and the training target is the PA input. The NN-DPD-Train is used to update the NN-DPD weights and biases. The input of this NN-DPD is the oversampled communication signal and its output is connected to the PA. The NN-DPD-Forward is used in the signal path to apply digital predistortion to the signals. This diagram shows the online training system. In an online training system, the NN-DPD weights can be updated based on predetermined performance metrics. If the PA characteristics change, the system performance may suffer. In the offline training system, once the training is done, the NN-DPD weights are kept constant. The Neural Network for Digital Predistortion Design - Offline Training (Communications Toolbox) example focuses on the offline training of a neural network DPD. DPD of the transmitted signal is a technique used to compensate for PA nonlinearities that distort the signal. Nonlinear behavior in PAs result in severe signal distortions and cause challenges for error-free reception of the high-frequency and high-bandwidth signals commonly transmitted in 5G NR.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |