Learning to schedule heuristics for the simultaneous stochastic optimization of mining complexes
From MaRDI portal
Abstract: The simultaneous stochastic optimization of mining complexes (SSOMC) is a large-scale stochastic combinatorial optimization problem that simultaneously manages the extraction of materials from multiple mines and their processing using interconnected facilities to generate a set of final products, while taking into account material supply (geological) uncertainty to manage the associated risk. Although simulated annealing has been shown to outperform comparing methods for solving the SSOMC, early performance might dominate recent performance in that a combination of the heuristics' performance is used to determine which perturbations to apply. This work proposes a data-driven framework for heuristic scheduling in a fully self-managed hyper-heuristic to solve the SSOMC. The proposed learn-to-perturb (L2P) hyper-heuristic is a multi-neighborhood simulated annealing algorithm. The L2P selects the heuristic (perturbation) to be applied in a self-adaptive manner using reinforcement learning to efficiently explore which local search is best suited for a particular search point. Several state-of-the-art agents have been incorporated into L2P to better adapt the search and guide it towards better solutions. By learning from data describing the performance of the heuristics, a problem-specific ordering of heuristics that collectively finds better solutions faster is obtained. L2P is tested on several real-world mining complexes, with an emphasis on efficiency, robustness, and generalization capacity. Results show a reduction in the number of iterations by 30-50% and in the computational time by 30-45%.
Recommendations
- Progressive hedging applied as a metaheuristic to schedule production in open-pit mines accounting for reserve uncertainty
- A framework for adaptive open-pit mining planning under geological uncertainty
- Optimizing mining complexes with multiple processing and transportation alternatives: an uncertainty-based approach
- Stochastic optimization in mine planning scheduling
- Production scheduling with uncertain supply: a new solution to the open pit mining problem
Cites work
- A simulated annealing hyper-heuristic methodology for flexible decision support
- An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time
- Block simulation of multiple correlated variables
- Equation of state calculations by fast computing machines
- scientific article; zbMATH DE number 1302201 (Why is no real title available?)
- scientific article; zbMATH DE number 3340881 (Why is no real title available?)
- Hyper-heuristic approaches for strategic mine planning under uncertainty
- Hyper-Heuristics: An Emerging Direction in Modern Search Technology
- Least squares quantization in PCM
- Machine learning for combinatorial optimization: a methodological tour d'horizon
- Optimization by simulated annealing
- Optimizing mining complexes with multiple processing and transportation alternatives: an uncertainty-based approach
- Production scheduling with uncertain supply: a new solution to the open pit mining problem
- Reinforcement learning. An introduction
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
This page was built for publication: Learning to schedule heuristics for the simultaneous stochastic optimization of mining complexes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6047903)
