RF Sensing-enabled Interference Mitigation for Wi-Fi-based IoT Systems: A Deep Learning Approach

The proliferation of the Internet of Things (IoT) over the 2.4GHz has transformed the way people interact with the world in their daily lives. For emerging applications requiring diverse types of data, using IoT devices from different protocols, such as Wi-Fi, Bluetooth, and ZigBee, for data collection will help fulfill designated objectives. Hence, the increasing use of these IoT devices will form a heterogeneous environment with inevitable wireless coexistence. Due to the dynamic IoT environment, the wireless transmission among heterogeneous IoT devices becomes unknown and notoriously hard to manage, where the network performance is always compromised. This paper leverages the RF sensing information to develop a deep learning-based framework for mitigating the cross-technology interference of the Wi-Fi-based IoT system. Each IoT device can provide detailed Channel State Information (CSI) of the transmission link, by which the gateway uses Generative Adversarial Networks (GAN) for building a detailed environmental RF map. Then, we propose a CSI-inspired gateway topology management strategy to find the optimal gateway location, anticipating reaching the highest network throughput. To enhance the efficiency of the proposed scheme, we also adopt the advanced differentiable augmentation approach to reduce the training data size for gateway deployment. Extensive experimental results have demonstrated both the feasibility and efficiency of our design.