GPU-Accelerated Slime Mould Algorithm for Urgent Transportation in Disaster Response: A COVID-19 Application

Abstract

In the face of increasing natural disasters, ensuring rapid patient transportation by Emergency Medical Services (EMS) is critical to saving lives. The Ambulance Dispatching and Relocation Problem (ADRP) poses a significant challenge, requiring swift allocation of limited ambulance resources. To address this issue, we propose a GPU-Accelerated Slime Mould Algorithm (GPU-SMA) designed for real-time decision-making in disaster scenarios. Our approach leverages the parallel processing power of GPUs using the Compute Unified Device Architecture (CUDA). This significantly reduces computational time, enabling faster and more effective optimization. Additionally, we introduce a new relocation policy that utilizes real-time ambulance data to maintain optimal ambulance positioning. Our method has been using real-world data from the COVID-19 pandemic in Chicago. The results show a remarkable 23x speedup on GeForce RTX 3090 and RTX A4000 GPUs compared to the serial implementation. GPU-SMA outperforms five leading parallel algorithms (GPU-PSO, GPU-APSO, GPU-HHO, GPU-FA, and GPU-BA) in efficiency and effectiveness. A Friedman test confirms the statistical significance of these results.