In order to transmit data and transfer energy to the low-power Internet of Things (IoT) devices, integrated data and energy networking (IDEN) system may be harnessed. In this context, we propose a bitwise end-to-end design for polar coded IDEN systems, where the conventional encoding/decoding, modulation/demodulation, and energy harvesting (EH) modules are replaced by the neural networks (NNs). In this way, the entire system can be treated as an AutoEncoder (AE) and trained in an end-to-end manner. Hence achieving global optimization. Additionally, we improve the common NN-based belief propagation (BP) decoder by adding an extra hypernetwork, which generates the corresponding NN weights for the main network under different number of iterations, thus the adaptability of the receiver architecture can be further enhanced. Our numerical results demonstrate that our BP-based end-to-end design is superior to conventional BP-based counterparts in terms of both the BER and power transfer, but it is inferior to the successive cancellation list (SCL)-based conventional IDEN system, which may be due to the inherent performance gap between the BP and SCL decoders.

翻译：为向低功耗物联网设备传输数据并传递能量，可借助集成数据与能量网络系统。在此背景下，我们提出一种面向极化编码集成数据与能量网络的比特级端到端设计方案，其中传统编码/译码、调制/解调及能量采集模块均由神经网络替代。由此，整个系统可被视为一个自动编码器，并通过端到端训练实现全局优化。此外，我们改进了基于神经网络的置信传播译码器，通过引入额外超网络，在不同迭代次数下为主网络生成对应神经网络权重，从而进一步增强接收机架构的适应性。数值结果表明，基于置信传播的端到端设计方案在误码率和能量传输性能上均优于传统置信传播方案，但劣于基于连续消除列表的传统集成数据与能量网络系统——这可能是由于置信传播译码器与连续消除列表译码器固有的性能差异所致。