dynamictpolicy-lora

Energy-Efficient Transmission Selection in LoRa

https://github.com/juanaznarp94/dynamictpolicy-lora

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: sciencedirect.com
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Energy-Efficient Transmission Selection in LoRa

Basic Info
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation Support

README.md

Dynamic Transmission Policy for Enhancing LoRa Networks Performance: A Deep Reinforcement Learning Approach

Abstract

Long Range (LoRa) communications, operating through the LoRaWAN protocol, have received increasing attention from the low-power and wide-area networks community. Efficient energy consumption and reliable communication performance are critical concerns in LoRa-based applications. However, current scientific literature tends to mainly focus on minimizing energy consumption while disregarding channel changes affecting communication performance. On the other hand, other works attain the appropriate communication performance without adequately considering energy expenditure. To fill this gap, we propose a novel solution to strike a balance between energy consumption and communication performance metrics. In particular, we characterize the problem as a Markov Decision Process and solve it using Deep Reinforcement Learning algorithms to dynamically select the transmission parameters that jointly satisfy energy and performance requirements over time. We evaluate the performance of the proposed algorithm in three different scenarios by comparing it with the traditional Adaptive Data Rate (ADR) mechanism of LoRaWAN.

Available models

Available trained models are ready to be used in the log folder.

Requirements

  • Python 3.10
  • gym 0.21.0
  • matplotlib 3.5.1
  • numpy 1.23.4
  • pandas 1.4.3
  • scikit-learn 1.2.1
  • seaborn 0.12.2
  • stable-baselines3 1.7.0

Paper published

Acosta-Garcia, Laura, et al. "Dynamic transmission policy for enhancing LoRa network performance: A deep reinforcement learning approach." Internet of Things 24 (2023): 100974. Link to the published paper

Owner

  • Name: Juan Aznar
  • Login: juanaznarp94
  • Kind: user
  • Location: Innsbruck, Tirol, Austria
  • Company: University of Innsbruck

Postdoctoral Researcher - University of Innsbruck (UIBK)

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Acosta-García"
  given-names: "Laura"
  orcid: "https://orcid.org/0009-0005-8185-8782"
- family-names: "Aznar-Poveda"
  given-names: "Juan"
  orcid: "https://orcid.org/0000-0002-0879-6651"
- family-names: "García-Sánchez"
  given-names: "Antonio-Javier"
  orcid: "https://orcid.org/0000-0001-5095-3035"
- family-names: "García-Haro"
  given-names: "Joan"
  orcid: "https://orcid.org/0000-0003-0741-7530"
- family-names: "Fahringer"
  given-names: "Thomas"
  orcid: "https://orcid.org/0000-0003-4293-1228"
title: "Dynamic Transmission Policy for Enhancing LoRa
Networks Performance: A Deep Reinforcement Learning
Approach"
version: 1.0.0
doi: ------
date-released: 2023-07-04
url: "https://github.com/juanaznarp94/LoRaRL"

GitHub Events

Total
  • Issues event: 4
  • Delete event: 4
  • Issue comment event: 6
  • Push event: 1
  • Pull request event: 1
  • Create event: 1
Last Year
  • Issues event: 4
  • Delete event: 4
  • Issue comment event: 6
  • Push event: 1
  • Pull request event: 1
  • Create event: 1