IoTligent: First World-Wide Implementation of Decentralized Spectrum Learning for IoT Wireless Networks

We propose the first implementation of learning algorithms on LoRa devices operating in a real LoRaWAN network. The goal of learning intends here to diminish collisions with other RF signals present in the ISM band. We explain that the proposed solution, named IoTligent, add neither network overhead so that no change is required to LoRaWAN, nor processing overhead so that it can be run in the devices. Experimental measurements done in a real LoRa network show that IoTligent device battery life can be extended by a factor 2 in our experiment.