Re-Learning EXP3 Multi-Armed Bandit Algorithm for Enhancing the Massive IoT-LoRaWAN Network Performance

Sensors

Ibrahim Gomaa¹  Ahmed Yahya²  Zaki Matar²  Samar Adel Almarzoqi² 

[1] Computers & Systems Department, National Telecommunication Institute (NTI-Egypt), Ministry of Communications and Information Technology, Cairo 11112, Egypt;Department of Electrical Engineering, Faculty of Engineering, Al-Azhar University, Cairo 11651, Egypt;

关键词: IoT;    LoRaWAN;    LPWAN;    MAB;    wireless node;   

DOI  :  10.3390/s22041603

来源: DOAJ

【 摘 要 】

Long-Range Wide Area Network (LoRaWAN) is an open-source protocol for the standard Internet of Things (IoT) Low Power Wide Area Network (LPWAN). This work’s focal point is the LoRa Multi-Armed Bandit decentralized decision-making solution. The contribution of this paper is to study the effect of the re-learning EXP3 Multi-Armed Bandit (MAB) algorithm with previous experts’ advice on the LoRaWAN network performance. LoRa smart node has a self-managed EXP3 algorithm for choosing and updating the transmission parameters based on its observation. The best parameter choice needs previously associated distribution advice (expert) before updating different choices for confidence. The paper proposes a new approach to study the effects of combined expert distribution for each transmission parameter on the LoRaWAN network performance. The successful transmission of the packet with optimized power consumption is the pivot of this paper. The validation of the simulation result has proven that combined expert distribution improves LoRaWAN network’s performance in terms of data throughput and power consumption.

【 授权许可】

Unknown