Towards Efficient and Portable Software Modulator via Neural Networks for IoT Gateways

Abstract

A physical-layer modulator is crucial for IoT gateways, but current solutions face issues like limited extensibility and platform-specificity due to soldered chipsets for specific technologies or diverse software toolkits for software radios. With the rapid expansion of the Internet of Things (IoT), such limitations are hard to ignore as the demand for versatile wireless technologies has increased. This paper introduces a novel approach using neural networks as an abstraction layer for these modulators in IoT gateways, termed NN-defined modulators. This method overcomes the challenges of extensibility and portability across different hardware platforms. The NN-defined modulator employs a model-driven approach based on mathematical principles, resulting in a lightweight, hardware-acceleration-friendly structure. These modulators are containerized with necessary runtime, facilitating agile deployment on varied platforms. We tested NN-defined modulators on platforms like Nvidia Jetson Nano and Raspberry Pi, showing they perform comparably to traditional modulators while offering efficiency improvements. The implementation is memory-efficient and adds minimal latency. Additionally, we demonstrate real-world applications of our NN-defined modulators in generating ZigBee and WiFi packets, compatible with standard TI CC2650 (ZigBee) and Intel AX201 (WiFi NIC) devices.