Improved temperature and power dependent Convolutional NN-based PA model
This article presents an innovative PA behavioral model method valid for a range of different ambient temperatures and input power levels. This work presents a novel input image layer for a Real-Valued Time-Delay Convolutional Neural Network (RVTDCNN). This image layer uses pre-processed ambient temperature and dissipated power. The pre-processed temperature and power, as well as the present samples are placed in a central position inside the image layer. This maximizes the number of convolution operations that they are included in thereby magnifying the importance of these inputs in the feature maps. The newly proposed method delivers, in comparable conditions, an NMSE improvement of over 3 dB compared to a previously published method.