Parallel Simulation of Complex Evacuation Scenarios with Adaptive Agent Models

Abstract

Simulation study on evacuation scenarios has gained tremendous attention in recent years. Two major research challenges remain along this direction: (1) how to portray the effect of individuals' adaptive behaviors under various situations in the evacuation procedures and (2) how to simulate complex evacuation scenarios involving huge crowds at the individual level due to the ultrahigh complexity of these scenarios. In this study, a simulation framework for general evacuation scenarios has been developed. Each individual in the scenario is modeled as an adaptable and autonomous agent driven by a weight-based decision-making mechanism. The simulation is intended to characterize the individuals' adaptable behaviors, the interactions among individuals, among small groups of individuals, and between the individuals and the environment. To handle the second challenge, this study adopts GPGPU to sustain massively parallel modeling and simulation of an evacuation scenario. An efficient scheme has been proposed to minimize the overhead to access the global system state of the simulation process maintained by the GPU platform. The simulation results indicate that the "adaptability" in individual behaviors has a significant influence on the evacuation procedure. The experimental results also exhibit the proposed approach's capability to sustain complex scenarios involving a huge crowd consisting of tens of thousands of individuals. Site. He is the Founder of the IEEE International Symposium on High Performance Distributed Computing (HPDC) and the cofounder of the IEEE International Conference on Autonomic Computing. His current research focuses on autonomic computing, high performance distributed computing, design and analysis of high speed networks, benchmarking and evaluating parallel and distributed systems, developing software design tools for high performance computing and communication systems, and network-centric applications. He is co-author/editor of four books on parallel and distributed computing: Autonomic

JND-based spatial parameter quantization of multichannel audio signals

“…In particular, we are interested in advanced technologies for perceptual sensitivity analysis of complex multivariate spatial parameters [38,39] as well as promising computing schemes for optimal 3D audio reproduction in sophisticated applications in practice [40][41][42].…”

Increasing the Simulation Performance of Large-Scale Evacuations Using Parallel Computing Techniques Based on Domain Decomposition

“…Domain decomposition was the chosen parallelisation strategy for this implementation as it favours the Distributed Memory (DM) model of parallel processing and was the strategy adopted in other parallel implementations [30,[32][33][34][35]. In PC parlance this is a network (or cluster) of PCs linked together via some form of Local Area Network (LAN).…”

“…There are three commonly used approaches to representing agent behaviour within microscopic evacuation models: Cellular Automata (CA) [24], Social Forces based models [25][26][27], and rule based models [9-12, 28, 29]. CA methods have been parallelised across multiple processors [30] but CA methods are particularly well suited to parallelisation on a SIMD (Single Instruction Multiple Data) platform [31] such as a General Purpose Graphical Processing Unit (GPGPU) [30,32,33] or a Field Programmable Gate Array (FPGA) [32] due to each grid cell being computed in the same fashion but with different data. However if complex interactions/behaviours are to be represented involving agents utilising information obtained from beyond their immediate vicinity the effectiveness of SIMD parallelism will be affected.…”

“…Given the differences in the formulation of rule based evacuation models and the computational costs associated with rule based models compared with CA and Social Force models, it is unclear how effective parallelisation can be for this type of model. Furthermore, most of the earlier parallel implementations were simply concerned with reducing the execution time of the simulation [30,33,34] but not necessarily as part of a live incident, where significantly faster than real time performance is required. Two implementations were specifically concerned with running faster than real time for use in a live incident [32,35].…”

“…Using this strategy, many computers will potentially be responsible for handling the movement of a particular agent through the environment. This was the strategy adopted in other parallel implementations [30,[32][33][34][35].…”