A Comparative Study of Ant Colony Optimisation, Genetic Algorithm and Hybrid ACO-DRL Models for Greener Logistics

Gupta, Sushmita Ghanshyam (2024) A Comparative Study of Ant Colony Optimisation, Genetic Algorithm and Hybrid ACO-DRL Models for Greener Logistics. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The paper focuses on logistics route optimization by Ant Colony Optimization (ACO), Genetic Algorithm (GA) and a Hybrid (ACO-DRL) Deep Reinforcement Learning model to reduce CO2 emissions. The work presented in the paper uses K-means clustering of the dataset containing the UPS Warehouse location and Drop Box location based on geographic coordinates. ACO performed better than GA and ACO-DRL in most of the clusters and proved to be more efficient in minimizing the travel distance and thus CO2 emission. GA was underperforming in dealing with the optimization and produced the highest emission. The hybrid ACO-DRL model perform well in one of the clusters compared to ACO and GA. ACO is identified as the most accurate model to optimize the routes and incorporating it with DRL is seen to offer better results in certain circumstances and thereby reduce the CO2 emission.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Simiscuka, Anderson UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 Aug 2025 15:35
Last Modified:	18 Aug 2025 15:35
URI:	https://norma.ncirl.ie/id/eprint/8573

Actions (login required)

View Item