GMACO-P: GPU assisted Preemptive MACO algorithm for enabling Smart Transportation

TL;DR

This paper introduces GMACO-P, a GPU-accelerated preemptive MACO algorithm designed to optimize traffic routing in VANETs, significantly reducing travel time and congestion in smart urban transportation systems.

Contribution

The paper presents a novel GPU-based enhancement of the MACO-P algorithm, enabling faster computations and improved traffic congestion management in smart transportation networks.

Findings

GMACO-P significantly reduces travel time compared to existing algorithms.

GPU acceleration improves computational efficiency for traffic routing.

The proposed method outperforms Dijkstra, ACO, MACO, and MACO-P in simulations.

Abstract

Vehicular Ad-hoc NETworks (VANETs) are developing at a very fast pace to enable smart transportation in urban cities, by designing some mechanisms for decreasing travel time for commuters by reducing congestion. Inefficient Traffic signals and routing mechanisms are the major factors that contribute to the increase of road congestion. For smoother traffic movement and reducing congestion on the roads, the waiting time at intersections must be reduced and an optimal path should be chosen simultaneously. In this paper, A GPU assisted Preemptive MACO (GMACO-P) algorithm has been proposed to minimize the total travel time of the commuters. GMACO-P is an improvement of MACO-P algorithm that uses the harnessing the power of the GPU to provide faster computations for further minimizing the travel time. The MACO-P algorithm is based on an existing MACO algorithm that avoid the path with the congestion. The MACO-P algorithm reduces the average queue length at intersections by incorporating preemption that ensures less waiting time. In this paper, GMACO-P algorithm is proposed harnessing the power of GPU to improve MACO-P to further reduce the travel time. The GMACO-P algorithm is executed with CUDA toolkit 7.5 using C language and the obtained results were compared with existing Dijkstra, ACO, MACO, MACO-P, parallel implementation of the Dijkstra, ACO and MACO algorithms. Obtained results show the significant reduction in the travel time after using the proposed GMACO-P algorithm.