Re-Learning EXP3 Multi-Armed Bandit Algorithm for Enhancing the Massive IoT-LoRaWAN Network Performance.
SENSORS 2022;
22:s22041603. [PMID:
35214501 PMCID:
PMC8880409 DOI:
10.3390/s22041603]
[Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Revised: 01/26/2022] [Accepted: 02/09/2022] [Indexed: 11/16/2022]
Abstract
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.
Collapse