LoRaDRL — Deep RL for LoRaWAN Parameter Selection

Overview

A deep reinforcement learning algorithm (DDQN) that selects PHY-layer transmission parameters in LoRaWAN networks. Existing rule-based algorithms cause packet collisions in dense LPWAN deployments; this DRL approach reduces collisions and improves Packet Delivery Ratio by up to 500% in some scenarios. Published at IEEE LCN 2020 with a follow-up paper. Outcome: Demonstrated up to 500% PDR improvement over state-of-the-art LoRaWAN parameter selection, with peer-reviewed publications in IEEE venues.

Architecture & Pipeline

flowchart LR
    n0["
LoRaWAN Sim Env
Custom Python simulator
"] n1["
Network State
PHY-layer conditions
"] n2["
DDQN Agent
TensorFlow
"] n3["
Action
PHY parameters
"] n4["
PDR Reward
Up to 500% improvement
"] n5["
Updated Policy
Production parameter selection
"] n0 --> n1 n1 --> n2 n2 --> n3 n3 --> n4 n4 --> n5 classDef step0 fill:#f1f5f9,stroke:#64748b,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step1 fill:#ecfeff,stroke:#06b6d4,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step2 fill:#f0fdfa,stroke:#0d9488,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step3 fill:#ecfdf5,stroke:#10b981,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step4 fill:#fffbeb,stroke:#f59e0b,color:#1e293b,stroke-width:2px,rx:10,ry:10; class n0 step0; class n1 step1; class n2 step2; class n3 step2; class n4 step3; class n5 step4;

End-to-end flow derived from this project's scope and tech stack. Tap View Fullscreen for a larger view, or scroll horizontally on small screens.

Key Features

  • Double Deep Q-Network (DDQN) algorithm
  • Custom Python simulation environment for LoRaWAN
  • Validated against state-of-the-art baselines
  • Two peer-reviewed IEEE publications
  • Tech Stack:** Python, TensorFlow