Study of Platform Passenger Evacuation Simulation Based on GPU

DOI

10.2991/nceece-15.2016.13How to use a DOI?

Keywords

GPGPU; CUDA; Pedestrian Evacuation; Parallel Computing; Simulation

Abstract

Pedestrian Evacuation Simulation can be used to support developing the evacuation solutions for subway stations. Although the pedestrian evacuation based on general purpose processors acquire good effect when the simulation scale is very large. We investigated the effect of the layout of subway stations on the pedestrian evacuation time through simulation. Based on the cellular automaton model, we partitioned the platform space into a two-dimensional grid structure. The walking path of pedestrians can be represented as movement on the grid according to a specified rule. Although the weighted shortest path algorithm is an appropriate routing rule for pedestrians, it puts pressure on the CPU simulation performance. To solve this problem, we introduced GPGPU as the parallel computing hardware to accelerate the simulation process. Experimental results show that the computation time of each time-step of the simulation on GPU is 20 times faster than on CPU. The real time simulation can support rapid decision-making and department response to emergencies.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhiyong Cai
AU  - Qianni Deng
PY  - 2015/12
DA  - 2015/12
TI  - Study of Platform Passenger Evacuation Simulation Based on GPU
BT  - Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 64
EP  - 70
SN  - 2352-5401
UR  - https://doi.org/10.2991/nceece-15.2016.13
DO  - 10.2991/nceece-15.2016.13
ID  - Cai2015/12
ER  -