Edge computing driven forest fire spread simulation: An energy-aware study

doi:10.1016/j.jocs.2025.102605

Return

Edge computing driven forest fire spread simulation: An energy-aware study

2025-06-01

DOI：10.1016/j.jocs.2025.102605

Original

Save

View PDF

Abstract

En 中文

An accurate and fast prediction of forest fire evolution is a crucial issue to minimize its impact. One of the challenges facing forest fire spread simulators is the uncertainty surrounding the input data. While highperformance computing (HPC) platforms help reduce these uncertainties, their accessibility during emergencies is limited due to infrastructure constraints. real time data collection using sensors onboard Unmanned Aerial Vehicles (UAVs) in real time can significantly reduce their uncertainty. However, transmitting this data to HPC environments and returning the results to firefighters remains difficult, especially in areas with poor connectivity. We propose using Edge Computing to address these challenges, leveraging low-consumption GPU-accelerated embedded systems for in situ data processing and wildfire spread simulation. For simulation purposes, the FARSITE forest fire spread simulator has been used. This work aims to demonstrate the feasibility of leveraging Embedded Systems with low-consumption GPUs to simulate short-term forest fire spread evolution (up to 5 hours) at high resolution (5 meters). The obtained results highlight that these devices can gather data, simulate the hazard, and deliver prediction results in situ, even without connectivity, opening up the possibility of monitoring and predicting fire behavior at high resolution without employing HPC platforms. (This paper is an extension version of the best poster paper award in ICCS-2024 entitled From HPC to Edge Computing: A new Paradigm in Forest Fire Spread Simulation.)

Keywords:

Embedded systems

Low-consumption GPUs

Energy-efficient computing

Wildfire simulation

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.