Submission Deadline: 31 December 2024 View: 567 Submit to Special Issue
To facilitate effective decision-making in real-world applications, meta-heuristics have been enhanced in various ways to successfully address complex optimization problems. However, these meta-heuristics often face significant performance challenges when dealing with large-scale optimization problems. To address this issue, the utilization of machine learning methods is being explored to improve the optimization effectiveness of meta-heuristics. This special issue aims to bring together both researchers and engineers from the academia and industry to discuss emerging and existing issues regarding modeling, optimizing and applying meta-heuristics and machine learning methods in engineering optimization problems. Specially, this issue focuses on the latest developments in swarm and evolutionary algorithms, meta-heuristics, hybridization with machine learning algorithms, and applications in various complex optimization problems. The potential topics include, but are not limited to:
Evolutionary multi-objective optimization with reinforcement learning
Evolutionary multi-task optimization with reinforcement learning
Surrogate-assisted evolutionary computation with learning strategies
Learning-driven evolutionary transfer optimization
Dynamic optimization with ensemble of meta-heuristic and learning methods
Production scheduling problems in manufacturing systems
Energy-efficiency scheduling and optimization problems in industry
Production and distribution optimization in supply chains
Scheduling and optimization problems in sustainability systems
New applications of ensemble with hybridization of meta-heuristics and machine learning algorithms