Adaptive Population-based Simulated Annealing for Uncertain Resource Constrained Job Scheduling

TL;DR

This paper introduces an adaptive population-based simulated annealing algorithm to improve resource-constrained job scheduling under uncertainty, effectively balancing exploration and exploitation, and outperforming existing methods on benchmark problems.

Contribution

The paper presents a novel adaptive population-based simulated annealing algorithm specifically designed for uncertain resource-constrained job scheduling, addressing limitations of prior methods.

Findings

Outperforms existing methods on benchmark instances.

Discovers new best solutions for most instances.

Effectively handles various uncertainty levels.

Abstract

Transporting ore from mines to ports is of significant interest in mining supply chains. These operations are commonly associated with growing costs and a lack of resources. Large mining companies are interested in optimally allocating their resources to reduce operational costs. This problem has been previously investigated in the literature as resource constrained job scheduling (RCJS). While a number of optimisation methods have been proposed to tackle the deterministic problem, the uncertainty associated with resource availability, an inevitable challenge in mining operations, has received less attention. RCJS with uncertainty is a hard combinatorial optimisation problem that cannot be solved efficiently with existing optimisation methods. This study proposes an adaptive population-based simulated annealing algorithm that can overcome the limitations of existing methods for RCJS with uncertainty including the premature convergence, the excessive number of hyper-parameters, and the inefficiency in coping with different uncertainty levels. This new algorithm is designed to effectively balance exploration and exploitation, by using a population, modifying the cooling schedule in the Metropolis-Hastings algorithm, and using an adaptive mechanism to select perturbation operators. The results show that the proposed algorithm outperforms existing methods across a wide range of benchmark RCJS instances and uncertainty levels. Moreover, new best known solutions are discovered for all but one problem instance across all uncertainty levels.