RIS-IoT: Towards Resilient, Interoperable, Scalable IoT

With the introduction of ultra-low-power machine learning (TinyML), IoT devices are becoming smarter as they are driven by ML models. However, any loss of communication at the device level can lead to a failure of the entire IoT system or misleading information trans-mission. Since there exist numerous heterogeneous devices within an IoT system, it is not feasible to centrally monitor all devices or explore system logs to determine communication loss. In this work, to maintain the highest possible communication quality and enable devices adapt according to context changes, we implement a lightweight ML-based adaptive strategy (ASB) and deploy it using a memory-optimized approach over the designed Pycom FiPy based multi-protocol IoT hardware. In real-world ex-periments, ASB equipped FiPy board accurately predicted the RSSI of WiFi 4 & WiFi 5 in real-time and switched between protocols - demonstrating interoperability amongst multiple IoT communication protocols and resilience against communication breakdown.