
Research Article
Design and Implementation of SF Selection Based on Distance and SNR Using Autonomous Distributed Reinforcement Learning in LoRa Networks
@INPROCEEDINGS{10.1007/978-3-031-29126-5_3, author={Ikumi Urabe and Aohan Li and Minoru Fujisawa and Song-Ju Kim and Mikio Hasegawa}, title={Design and Implementation of SF Selection Based on Distance and SNR Using Autonomous Distributed Reinforcement Learning in LoRa Networks}, proceedings={Artificial Intelligence for Communications and Networks. 4th EAI International Conference, AICON 2022, Hiroshima, Japan, November 30 - December 1, 2022, Proceedings}, proceedings_a={AICON}, year={2023}, month={3}, keywords={IoT LoRaWAN Lightweight Distributed Reinforcement Learning SF Selection}, doi={10.1007/978-3-031-29126-5_3} }
- Ikumi Urabe
Aohan Li
Minoru Fujisawa
Song-Ju Kim
Mikio Hasegawa
Year: 2023
Design and Implementation of SF Selection Based on Distance and SNR Using Autonomous Distributed Reinforcement Learning in LoRa Networks
AICON
Springer
DOI: 10.1007/978-3-031-29126-5_3
Abstract
LoRaWAN, one of Low-Power-Wide-Area (LPWA), has been deployed in many IoT applications due to its ability to communicate over long distances and low power consumption. However, the scalability and communication performance of LoRaWAN is highly dependent on Spreading Factor (SF) and Channel (CH) allocation. In particular, it is important to configure SF appropriately according to the distance of the LoRa device from the GateWay (GW) and the environment. In this paper, we implement and evaluate lightweight distributed reinforcement learning-based SF selection methods. This method allows each IoT device to make appropriate parameter selections without requiring any prior information, but only utilizing ACKnowledge obtained from its own transmissions. We then conducted real experiments in a small area indoors to verify that each LoRa device can autonomously and decentralized perform appropriate SF selection in response to the distance from the GW and SNR that varies depending on the surrounding environment. The results show that the implemented methods can select appropriate SF and achieve a better Frame Success Rate (FSR) than other lightweight approaches.