Applying Partial-ACO to Large-scale Vehicle Fleet Optimisation

TL;DR

This paper demonstrates that Partial-ACO, a variant of Ant Colony Optimization, effectively scales to large fleet optimization problems, significantly reducing traversal times compared to standard ACO and genetic algorithms.

Contribution

The study introduces and evaluates Partial-ACO for large-scale vehicle fleet optimization, showing its superior scalability and performance over existing methods.

Findings

Partial-ACO improves fleet traversal times by over 44% on real-world data.

Partial-ACO outperforms standard ACO and is competitive with genetic algorithms.

The method scales effectively to problems with up to 298 jobs and 32 vehicles.

Abstract

Optimisation of fleets of commercial vehicles with regards scheduling tasks from various locations to vehicles can result in considerably lower fleet traversal times. This has significant benefits including reduced expenses for the company and more importantly, a reduction in the degree of road use and hence vehicular emissions. Exact optimisation methods fail to scale to real commercial problem instances, thus meta-heuristics are more suitable. Ant Colony Optimisation (ACO) generally provides good solutions on small to medium problem sizes. However, commercial fleet optimisation problems are typically large and complex, in which ACO fails to scale well. Partial-ACO is a new ACO variant designed to scale to larger problem instances. Therefore this paper investigates the application of Partial-ACO on the problem of fleet optimisation, demonstrating the capacity of Partial-ACO to successfully scale to larger problems. Indeed, for real-world fleet optimisation problems supplied by a Birmingham based company with up to 298 jobs and 32 vehicles, Partial-ACO can improve upon their fleet traversal times by over 44%. Moreover, Partial-ACO demonstrates its ability to scale with considerably improved results over standard ACO and competitive results against a Genetic Algorithm.