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

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.

Christophe MOY

[1] Jacques Palicot,et al. Multi-Armed Bandit Learning in IoT Networks: Learning Helps Even in Non-stationary Settings , 2017, CrownCom.

[2] Peter Auer,et al. Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[3] Christophe Moy,et al. Reinforcement Learning Real Experiments for Opportunistic Spectrum Access , 2014 .

[4] Ananthram Swami,et al. Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret , 2010, IEEE Journal on Selected Areas in Communications.

[5] D. Ernst,et al. Upper Confidence Bound Based Decision Making Strategies and Dynamic Spectrum Access , 2010, 2010 IEEE International Conference on Communications.