D-LoRa: a Distributed Parameter Adaptation Scheme for LoRa Network

TL;DR

D-LoRa is a distributed reinforcement learning-based scheme that dynamically adapts LoRa network parameters to optimize performance metrics like delivery rate and energy efficiency in varying environments.

Contribution

It introduces a novel distributed parameter adaptation method using Multi-Armed Bandit models for improved LoRa network performance.

Findings

Packet delivery rate increased by up to 28.8%

Demonstrates superior adaptability across metrics

Effective in diverse channel conditions

Abstract

The deployment of LoRa networks necessitates joint performance optimization, including packet delivery rate, energy efficiency, and throughput. Additionally, multiple LoRa parameters for packet transmission must be dynamically configured to tailor the performance metrics prioritization across varying channel environments. Because of the coupling relationship between LoRa parameters and metrics, existing works have opted to focus on certain parameters or specific metrics to circumvent the intricate coupling relationship, leading to limited adaptability. Therefore, we propose D-LoRa, a distributed parameter adaptation scheme, based on reinforcement learning towards network performance. We decompose the joint performance optimization problem into multiple independent Multi-Armed Bandit (MAB) problems with different reward functions. We have also built a comprehensive analytical model for the LoRa network that considers path loss, quasi-orthogonality of spreading factor, and packet collision. Experimental results show that our scheme can increase packet delivery rate by up to 28.8% and demonstrates superior adaptability across different performance metrics.