A self-learning genetic algorithm based on reinforcement learning for flexible job-shop scheduling problem

Chen, Ronghua; Yang, Bo; Li, Shi; Wang, Shilong

doi:10.1016/j.cie.2020.106778

Cited by 312 publications

(86 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Objective function: (19) and (20) represent the minimized configuration of AGVs and picking stations; (21) represents the minimization of equipment operation cost in the unmanned warehouse; (22) indicates that the total completion time of the actual task needs to meet the demand for retrieval efficiency; (23) and (24) respectively represent the resource constraints of AGVs and picking stations; (25) is the value range of the variable.…”

Section: Equipment Optimal Configuration and Layout Modelmentioning

confidence: 99%

“…Scheduling problems are often solved by intelligent algorithms, a genetic algorithm is widely used in NP-hard problems [17][18][19]. Ronghua Chen [20] proposed a self-learning genetic algorithm based on GA is proposed to solve the jobshop scheduling problem. Jafarzadeh et al [21] introduced a genetic algorithm combined with nearest-neighbor domain search, which can greatly improve the solving quality and solving time of generalized travel agent problem; Carlos E. Andrade [22] present the Multi-Parent Biased Random-Key Genetic Algorithm with Implicit Path Relinking (BRKGA-MP-IPR) with its real-world applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Equipment Configuration Optimization of AGV Unmanned Warehouse

et al. 2021

View full text Add to dashboard Cite

To improve the throughput performance of the autonomous guide vehicle (AGV) unmanned storage system, a two-stage mathematical model was established. The model also considers the equipment configuration of the AGV unmanned storage system and the AGV-picking stations dual resource coordination scheduling problem. In the equipment-task scheduling phase, the model aims at the shortest order completion time, while the equipment configuration and layout model aims at the minimum equipment configuration and operating cost. To solve the two-stage model, a two-layer genetic algorithm was designed. The inner layer algorithm was used to optimize the task scheduling order of AGVs and picking stations. The results of the inner layer algorithm are fed back to the outer model to optimize configuration of the equipment and the picking station's layout. The inner and outer loops are combined to obtain the optimal equipment configuration scheme. Through the simulation study of an enterprise AGV unmanned storage case, the optimal equipment configuration combination and picking stations layout scheme are obtained. Compared with the equipment configuration scheme based on the principle the task scheduling in operation is another key link that affects the picking efficiency of an unmanned warehouse of random task scheduling and the principle of shortest job time first; The model can improve the efficiency of warehouse retrieval and minimize the number of equipment configurations. Finally, the improved genetic algorithm is used to solve the model, and the performance is compared with that of LINGO to verify the effectiveness of the improved algorithm.

show abstract

Section: Equipment Optimal Configuration and Layout Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on Equipment Configuration Optimization of AGV Unmanned Warehouse

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In Chen et al (2020) , 14 benchmark test problems are used to demonstrate the efficiency of a self-learning GA based on reinforcement learning in the FJSP. A fuzzy version of the FJSP is studied in Vela et al (2020) , where an evolutionary algorithm is proposed, using a TS again for optimizing a due-date cost.…”

Section: State Of the Art Of Fjspmentioning

confidence: 99%

A global-local neighborhood search algorithm and tabu search for flexible job shop scheduling problem

Serna¹,

Seck-Tuoh-Mora²,

Medina-Marín³

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

The Flexible Job Shop Scheduling Problem (FJSP) is a combinatorial problem that continues to be studied extensively due to its practical implications in manufacturing systems and emerging new variants, in order to model and optimize more complex situations that reflect the current needs of the industry better. This work presents a new metaheuristic algorithm called the global-local neighborhood search algorithm (GLNSA), in which the neighborhood concepts of a cellular automaton are used, so that a set of leading solutions called smart-cells generates and shares information that helps to optimize instances of the FJSP. The GLNSA algorithm is accompanied by a tabu search that implements a simplified version of the Nopt1 neighborhood defined in Mastrolilli & Gambardella (2000) to complement the optimization task. The experiments carried out show a satisfactory performance of the proposed algorithm, compared with other results published in recent algorithms, using four benchmark sets and 101 test problems.

show abstract

“…Genetic algorithms (GAs) [23] are a subset of evolutionary algorithms [24], that have emerged as flexible and efficient metaheuristic methods for solving optimization problems and achieving a high level of problem-solving efficacy in most research domains, e.g., aircraft design [25], battery systems [26], resource allocation [27], job-shop scheduling [28], virtual machine placement [29], cloud task scheduling [30], quadratic assignment [31], and vehicle…”

Section: Genetic Algorithmsmentioning

confidence: 99%

A Novel Many-Objective Recommendation Algorithm for Multistakeholders

Wang

Chen

2020

IEEE Access

View full text Add to dashboard Cite

Most traditional recommender systems focus specifically on increasing consumer satisfaction by providing a list of relevant content to consumers. However, the perspectives of other multisided marketplace stakeholders are also equally important, i.e., the exposure for suppliers or providers and profit for the platform. The suppliers want their products to be presented to users, and the objective of the platform is to maximize their profit. Nevertheless, because consumers' preferences and the objectives of providers as well as the platform may conflict with each other, it degrades the utility of the recommendation methods by only considering users' views. Therefore, in this work, we use a many-objective optimization method to maintain a tradeoff among five objectives for three stakeholders and obtain multiple Pareto front solutions in a single run. We first combine customer lifetime value and user purchase preference to create a new similarity model (Sim_RFMP) to increase the recommendation accuracy of the recommendation list. Furthermore, we propose a many-objective model (NBHXMAOEA) for multistakeholder recommendation. In NBHXMAOEA, we present a novel N-block heuristic crossover operator (NBHX) that recombines blocks of chromosomes based on heuristics. Through extensive experiments, the results demonstrate that our proposed NBHXMAOEA achieves superior performance in terms of average accuracy, diversity, novelty, provider coverage, and platform profit to its competing methods. INDEX TERMS Many-objective, recommender systems, similarity model, stakeholders.

show abstract

A self-learning genetic algorithm based on reinforcement learning for flexible job-shop scheduling problem

Cited by 312 publications

References 46 publications

Research on Equipment Configuration Optimization of AGV Unmanned Warehouse

Research on Equipment Configuration Optimization of AGV Unmanned Warehouse

A global-local neighborhood search algorithm and tabu search for flexible job shop scheduling problem

A Novel Many-Objective Recommendation Algorithm for Multistakeholders

Contact Info

Product

Resources

About