Enhancing multi-objective evolutionary algorithms with machine learning for scheduling problems: recent advances and survey

Frontiers in Industrial Engineering, Journal Year: 2024, Volume and Issue: 2

Published: Feb. 28, 2024

Multi-objective scheduling problems in workshops are commonly encountered challenges the increasingly competitive market economy. These require a trade-off among multiple objectives such as time, energy consumption, and product quality. The importance of each optimization objective typically varies different time periods or contexts, necessitating decision-makers to devise optimal plans accordingly. In actual production, confront intricate multi-objective that demand balancing clients’ requirements corporate interests while concurrently striving reduce production cycles costs. solving various problems, evolutionary algorithms have attracted attention researchers gradually become one mainstream methods solve these problems. recent years, research combining with machine learning technology has shown great potential, opening up new prospects for improving performance methods. This article comprehensively reviews latest application progress We review techniques employed enhancing algorithms, particularly focusing on types reinforcement Different categories addressed using were also discussed, including flow-shop issues, job-shop challenges, more. Finally, we highlighted faced by field outlined future directions.

Language: Английский

---

A knowledge-driven memetic algorithm for distributed green flexible job shop scheduling considering the endurance of machines

Applied Soft Computing, Journal Year: 2025, Volume and Issue: 170, P. 112697 - 112697

Published: Jan. 6, 2025

Language: Английский

---

A Q-learning grey wolf optimizer for a distributed hybrid flowshop rescheduling problem with urgent job insertion

Journal of Applied Mathematics and Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

Language: Английский

---

Greedy-assisted teaching-learning-based optimization algorithm for cost-based hybrid flow shop scheduling

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126955 - 126955

Published: Feb. 1, 2025

Language: Английский

---

Q-learning based estimation of distribution algorithm for scheduling distributed heterogeneous flexible flow-shop with mixed buffering limitation

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 149, P. 110537 - 110537

Published: March 12, 2025

Language: Английский

---

A trajectory-based algorithm enhanced by Q-learning and cloud integration for hybrid flexible flowshop scheduling problem with sequence-dependent setup times: A case study

Computers & Operations Research, Journal Year: 2025, Volume and Issue: unknown, P. 107079 - 107079

Published: March 1, 2025

Language: Английский

---

A multi-objective sustainable multipath delivery problem in hilly regions with customer-satisfaction using TLBO

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113100 - 113100

Published: April 1, 2025

Language: Английский

---

Novel 3D UAV Path Planning for IoT Services Based on Interactive Cylindrical Vector Teaching–Learning Optimization Algorithm

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2407 - 2407

Published: April 10, 2025

In the 6G-IoT convergence ecosystem, UAV path planning for static environments is systematically investigated as a resource coordination problem where communication demands and terrain constraints are balanced through intelligent trajectory optimization. The innovation of this paper lies in proposal an interactive cylinder vector teaching–learning-based optimization (ICVTLBO) algorithm, points represented cylindrical coordinates, targeted strategies proposed during teacher learner phases to address uncertainty challenges, such elevation fluctuations link instability caused by obstacles environments. ICVTLBO compared with other classical novel algorithms on CEC2022 benchmark function suite, demonstrating its effectiveness reliability solving complex problems. Subsequently, real digital model (DEM) maps utilized establish nine diverse scenarios simulation 3D experimental results show that outperforms methods, providing high-quality paths UAVs

Language: Английский

---

A knowledge-driven many-objective algorithm for energy-efficient distributed heterogeneous hybrid flowshop scheduling with lot-streaming

Swarm and Evolutionary Computation, Journal Year: 2024, Volume and Issue: 91, P. 101771 - 101771

Published: Nov. 14, 2024

Language: Английский

---

Reinforcement Learning-Based Multi-Objective of Two-Stage Blocking Hybrid Flow Shop Scheduling Problem

Processes, Journal Year: 2023, Volume and Issue: 12(1), P. 51 - 51

Published: Dec. 25, 2023

Consideration of upstream congestion caused by busy downstream machinery, as well transportation time between different production stages, is critical for improving efficiency and reducing energy consumption in process industries. A two-stage hybrid flow shop scheduling problem studied with the objective makespan total while taking into consideration blocking restrictions. An adaptive selection-based Q-learning algorithm designed to solve problem. Nine state characteristics are extracted from real-time information about jobs, machines, waiting processing queues. As actions, eight heuristic rules used, including SPT, FCFS, Johnson, others. To address multi-objective optimization problem, an selection strategy based on t-tests making action decisions. This can determine confidence function under current job machine state, achieving coordinated multiple objectives. The experimental results indicate that proposed algorithm, comparison non-dominated sorting genetic has shown average improvement 4.19% 22.7% makespan, 5.03% 9.8% consumption, respectively. generated solutions provide theoretical guidance industries such steel manufacturing. contributes helping enterprises reduce downstream.

Language: Английский

---