Distributed Fire Agent Model based on Ensemble Clustering

DOI

10.2991/978-94-6463-736-6_33How to use a DOI?

Keywords

Fire numerical simulation; Distributed computing; Agent model; Integrated learning; Security management

Abstract

Fire Dynamics Simulation (FDS) is a numerical simulation method based on physical principles, which can reflect the fire development process and its influencing factors relatively realistically. However, FDS also has problems such as large computational volume and long simulation time. And due to the complexity of fire data, single-agent models have limitations and risks in expressing fire characteristics, model complexity, computational time and overfitting. To solve the above problems, an adaptive distributed fire agent model is proposed. Using the Spark distributed computing framework, integrated cluster analysis is used to dynamically select the best agent model for each cluster of data, thus taking full advantage of different agent models and improving the accuracy, robustness and generalization ability of fire prediction. The experimental results show that the distributed fire agent model has advantages in prediction accuracy, adaptability, data security and computation time, which meets the needs of modern fire numerical simulation research.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Huanhuan Chen
PY  - 2025
DA  - 2025/05/22
TI  - Distributed Fire Agent Model based on Ensemble Clustering
BT  - Proceedings of the 2025 4th International Conference on Engineering Management and Information Science (EMIS 2025)
PB  - Atlantis Press
SP  - 287
EP  - 293
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-736-6_33
DO  - 10.2991/978-94-6463-736-6_33
ID  - Chen2025
ER  -