Learning-Automata-Based Hybrid Model for Event Detection in LoRaWAN Networks

In recent years, the Internet of Things (IoT) is growing rapidly and gaining ground in a variety of fields. Such fields are environmental disasters, such as forest fires, that are becoming more common as a result of the environmental crisis and there is a need to properly manage them. Therefore, utilizing IoT for event detection and monitoring is an effective solution. A technique for monitoring such events over a large area is proposed in this research. In this work, the developed system makes use of technology based on Long Range Wide Area Network (LoRaWAN) protocol, which is capable to connect low power devices distributed on large geographical areas. A learning-automata-based hybrid MAC model is suggested to reduce the transmission delay, when a small part of the network produces event packets stemming from an event occurrence. The proposed hybrid MAC is evaluated via simulation results, which indicate that it achieves significantly higher performance in terms of packet delay, when compared to traditional LoRaWAN schemes.