Polar Coded Integrated Data and Energy Networking: A Deep Neural Network Assisted End-to-End Design

Wireless sensors are everywhere. To address their energy supply, we proposed an end-to-end design for polar-coded integrated data and networking (IDEN), where the conventional signal processing modules, such as modulation/demodulation channel decoding, replaced by deep neural networks (DNNs). Moreover, input-output relationship of harvester (EH) is also modelled a DNN. By jointly optimizing both transmitter receiver autoencoder (AE), minimize bit-error-rate (BER) maximize harvested IDEN system, while satisfying transmit power budget constraint determined normalization layer in transmitter. Our simulation results demonstrate that DNN aided conceived outperforms its model-based counterpart terms BER.