Dynamic parallel machine scheduling with mean weighted tardiness objective by Q-Learning

Zhang, Zhicong; Liu, Zheng; Weng, Meng-Hsiung

doi:10.1007/s00170-006-0662-8

Cited by 62 publications

(25 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unrelated parallel machine scheduling problems exist in industries, such as scheduling operations of a printed wiring board (PWB) manufacturing line [47], scheduling dicing operations of semiconductor wafer manufacturing [21], scheduling drilling operations in a printed circuit board (PCB) industry [18], scheduling the spinning units of acrylic fibers in the textile factory [39], and scheduling the chip attach operations in the back-end semiconductor assembly line [48], etc. Also, during the manufacturing processes, each job is typically released at a different time from its preceding operations.…”

Section: Comparison Of the Tsa With The Gasmentioning

confidence: 99%

Bicriteria scheduling problem for unrelated parallel machines with release dates

Lin

2015

Computers & Operations Research

View full text Add to dashboard Cite

Section: Comparison Of the Tsa With The Gasmentioning

confidence: 99%

Bicriteria scheduling problem for unrelated parallel machines with release dates

Lin

2015

Computers & Operations Research

View full text Add to dashboard Cite

“…4. Assume a solution in which the job sequence on machine 1 (M1) is (1,3,5) and the job sequence on machine 2 (M2) is (2,4). The four neighborhood structures used in the proposed IVT are illustrated as follows.…”

Section: The Proposed Hybrid Metaheuristicmentioning

confidence: 99%

“…Unrelated parallel machine scheduling problems show up in real-world applications, such as PCB fabrication drilling operations [1,2], semiconductor wafer manufacturing dicing [3], the spinning of acrylic fibers for production in the textile industry [4], chip attach operations in the back-end semiconductor assembly line [5], and scheduling jobs in a printed wiring board (PWB) manufacturing environment [6].…”

Section: Introductionmentioning

confidence: 99%

“…However, in real-world cases, the jobs are released at various times, such as in chip-attach operations in back-end semiconductor assembly lines [5]. In recent years, a few researchers have studied the unrelated parallel machines scheduling problem with unequal ready times.…”

Section: Introductionmentioning

confidence: 99%

“…Logendran et al [29] proposed a tabu search algorithm to minimize weighted tardiness for unrelated parallel machine problems with sequence-dependent setup times and unequal ready times. Zhang et al [5] considered a dynamic unrelated parallel machine scheduling problem with sequence-dependent setup times and machine-job qualification. They applied the Q-Learning algorithm to minimize the mean weighted tardiness of all jobs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Iterated hybrid metaheuristic algorithms for unrelated parallel machines problem with unequal ready times and sequence-dependent setup times

Chen¹

2011

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The problem considered in this paper involves a set of independent jobs on unrelated parallel machines with sequence-dependent setup times and unequal ready times, and the objective is to minimize the weighted number of tardy jobs. Iterated hybrid metaheuristic algorithms are proposed to address this problem. The algorithms begin with effective initial solution generators to generate initial feasible solutions; then, hybrid metaheuristics are applied to improve the initial solutions, integrating the principles of the variable neighborhood descent approach and tabu search. If the search becomes trapped at a local optimum, a perturbation operator is developed to help the search escape. To evaluate the performance of the suggested algorithms, heuristic rules and iterated local search algorithms are examined and compared. Computational experimental results show that the proposed algorithms outperform the other heuristics.

show abstract

Gated‐Attention Model with Reinforcement Learning for Solving Dynamic Job Shop Scheduling Problem

Gebreyesus

Fellek

Farid

et al. 2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Job shop scheduling problem (JSSP) is one of the well‐known NP‐hard combinatorial optimization problems (COPs) that aims to optimize the sequential assignment of finite machines to a set of jobs while adhering to specified problem constraints. Conventional solution approaches which include heuristic dispatching rules and evolutionary algorithms has been largely in use to solve JSSPs. Recently, the use of reinforcement learning (RL) has gained popularity for delivering better solution quality for JSSPs. In this research, we propose an end‐to‐end deep reinforcement learning (DRL) based scheduling model for solving the standard JSSP. Our DRL model uses attention‐based encoder of Transformer network to embed the JSSP environment represented as a disjunctive graph. We introduced Gate mechanism to modulate the flow of learnt features by preventing noise features from propagating across the network to enrich the representations of nodes of the disjunctive graph. In addition, we designed a novel Gate‐based graph pooling mechanism that preferentially constructs the graph embedding. A simple multi‐layer perceptron (MLP) based action selection network is used for sequentially generating optimal schedules. The model is trained using proximal policy optimization (PPO) algorithm which is built on actor critic (AC) framework. Experimental results show that our model outperforms existing heuristics and state of the art DRL based baselines on generated instances and well‐known public test benchmarks. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Dynamic parallel machine scheduling with mean weighted tardiness objective by Q-Learning

Cited by 62 publications

References 17 publications

Bicriteria scheduling problem for unrelated parallel machines with release dates

Bicriteria scheduling problem for unrelated parallel machines with release dates

Iterated hybrid metaheuristic algorithms for unrelated parallel machines problem with unequal ready times and sequence-dependent setup times

Gated‐Attention Model with Reinforcement Learning for Solving Dynamic Job Shop Scheduling Problem

Contact Info

Product

Resources

About