Genetic Programming and Reinforcement Learning on Learning Heuristics for Dynamic Scheduling: A Preliminary Comparison

IEEE Computational Intelligence Magazine, Journal Year: 2024, Volume and Issue: 19(2), P. 18 - 33

Published: April 5, 2024

Scheduling heuristics are commonly used to solve dynamic scheduling problems in real-world applications. However, designing effective can be time-consuming and often leads suboptimal performance. Genetic programming has been widely automatically learn heuristics. In recent years, reinforcement learning also gained attention this field. Understanding their strengths weaknesses is crucial for developing This paper takes a typical genetic method flexible job shop investigation. The results show that the investigated algorithm outperforms studied examined scenarios. Also, study reveals compared more stable as amount of training data changes, increases. Additionally, highlights potential value applications due its good generalization ability interpretability. Based on results, suggests using when limited required, sufficient high interpretability required.

Language: Английский

---

Production scheduling with multi-robot task allocation in a real industry 4.0 setting

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 13, 2025

The demand for efficient Industry 4.0 systems has driven the need to optimize production systems, where effective scheduling is crucial. In smart manufacturing, robots handle material transfers, making precise essential seamless operations. However, research often oversimplifies Robotic Flexible Job Shop problem by focusing only on transportation time, ignoring resource allocation and robot diversity. This study addresses these gaps, tackling a Multi-Robot (MRFJS) with limited buffers. It involves non-identical parallel machines varying capabilities overseeing handling under blocking conditions. case based real scenario, layout restricts each robotic arm's access, requiring strategic buffer placement part transfers. A Mixed-Integer Programming (MILP) model aims minimize makespan, followed new Genetic Algorithm (GA) using Roy Sussman's Alternative Graph. Computational tests various scales data from manufacturing plant demonstrate GA's efficacy in solving complex problems real-world settings. Based data, Proposed (PGA), an average Relative Deviation (ARD) of 0.25%, performed approximately 34% better compared Basic (BGA), ARD 0.38%. percentage indicates that PGA significantly outperforms problems.

Language: Английский

---

Mathematical model and adaptive simulated annealing algorithm for mixed-model assembly job-shop scheduling with lot streaming

Journal of Manufacturing Systems, Journal Year: 2023, Volume and Issue: 70, P. 484 - 500

Published: Aug. 29, 2023

Language: Английский

---

A framework of cloud-edge collaborated digital twin for flexible job shop scheduling with conflict-free routing

Robotics and Computer-Integrated Manufacturing, Journal Year: 2023, Volume and Issue: 86, P. 102672 - 102672

Published: Oct. 12, 2023

Language: Английский

---

An enhanced memetic algorithm with hierarchical heuristic neighborhood search for type-2 green fuzzy flexible job shop scheduling

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 130, P. 107762 - 107762

Published: Dec. 26, 2023

Language: Английский

---

Graph neural networks for job shop scheduling problems: A survey

Computers & Operations Research, Journal Year: 2024, Volume and Issue: unknown, P. 106914 - 106914

Published: Nov. 1, 2024

Language: Английский

---

A genetic programming based cooperative evolutionary algorithm for flexible job shop with crane transportation and setup times

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112614 - 112614

Published: Dec. 1, 2024

Language: Английский

---

Genetic Programming for Dynamic Flexible Job Shop Scheduling: Evolution With Single Individuals and Ensembles

IEEE Transactions on Evolutionary Computation, Journal Year: 2023, Volume and Issue: 28(6), P. 1761 - 1775

Published: Nov. 21, 2023

Dynamic flexible job shop scheduling is an important but difficult combinatorial optimisation problem that has numerous real-world applications. Genetic programming been widely used to evolve heuristics solve this problem. Ensemble methods have shown promising performance in many machine learning tasks, previous attempts combine genetic with ensemble techniques are still limited and require further exploration. This paper proposes a novel method uses population consisting of both single individuals ensembles. The main contributions include: 1) developing evolves comprising ensembles, allowing breeding between them explore the search space more effectively; 2) proposing construction selection strategy form ensembles by selecting diverse complementary individuals; 3) designing new crossover mutation operators produce offspring from Experimental results demonstrate proposed outperforms existing traditional most scenarios. Further analyses find success attributed enhanced diversity extensive exploration achieved method.

Language: Английский

---

Multi-Tree Genetic Programming with Elite Recombination for dynamic task scheduling of satellite edge computing

Future Generation Computer Systems, Journal Year: 2025, Volume and Issue: unknown, P. 107700 - 107700

Published: Jan. 1, 2025

Language: Английский

---

An enhanced decomposition-based multi-objective evolutionary algorithm with neighborhood search for multi-resource constrained job shop scheduling problem

Swarm and Evolutionary Computation, Journal Year: 2025, Volume and Issue: 93, P. 101834 - 101834

Published: Jan. 10, 2025

Language: Английский

---