sacuriom/msaga: M-SAGA v1.0.0: LoRaWAN Network Optimization for Smart Cities
Abstract
# 3D-M-SAGA: 3D Memetic Spatial-Aware Genetic Algorithm for LoRaWAN [](https://doi.org/10.5281/zenodo.8454357) ## OverviewThis repository contains the source code, datasets, and supplementary materials for the **3D-M-SAGA** framework. This tool is designed to solve the Gateway Placement Problem (GPP) for large-scale LoRaWAN networks in dense urban environments. Unlike traditional 2D isotropic models, 3D-M-SAGA fuses open-source vector data (OpenStreetMap) with Digital Elevation Models (DEM) to evaluate urban morphology, building penetration (dielectric clutter), and topographical diffraction strictly aligned with **ITU-R recommendations (P.2109 and P.2108)**. The optimization engine uses a Memetic Algorithm coupled with a deterministic "Smart Repair" operator to maximize coverage and network resilience ($K$-coverage) while maintaining strict CAPEX constraints. ## Repository Structure- `data/`: Contains the CSV files generated for each algortihm digital twin generation with topographic al geographic information - `src/`: Contains the main source code of the 3D-M-SAGA framework. - `main.py`: The entry point for running the optimization algorithm. - `propagation_model.py`: Scripts for 3D morphological evaluation and ITU-R penalty calculations. - `memetic_engine.py`: Implementation of the Genetic Algorithm (GA) and the local search (Smart Repair) operators.- `results/`: Directory where the output logs, optimal gateway coordinates, and coverage maps are saved. ## Requirements and DependenciesTo run the framework, you need **Python 3.8+** and the following libraries:- `osmnx` (for extracting and processing urban topology)- `numpy` & `scipy` (for mathematical operations)- `pandas` (for data handling)- `matplotlib` / `folium` (for 3D and geographic visualization)- *[Añade aquí cualquier otra librería clave que hayas usado, ej. `deap` si usaste esa para el algoritmo genético]* You can install the dependencies using:```bashpip install -r requirements.txt
Fields of Study & Subjects
IoT Networks and Protocols
Energy Efficient Wireless Sensor Networks
Millimeter-Wave Propagation and Modeling
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 2 February 2026