Deep Reinforcement Learning for Minimizing Tardiness in Parallel Machine Scheduling With Sequence Dependent Family Setups
نویسندگان
چکیده
Parallel machine scheduling with sequence-dependent family setups has attracted much attention from academia and industry due to its practical applications. In a real-world manufacturing system, however, solving the problem becomes challenging since it is required address urgent frequent changes in demand due-dates of products. To minimize total tardiness problem, we propose deep reinforcement learning (RL) based framework which trained neural networks (NNs) are able solve unseen problems without re-training even when such occur. Specifically, state action representations whose dimensions independent production requirements jobs while accommodating setups. At same time, an NN architecture parameter sharing was utilized improve training efficiency. Extensive experiments demonstrate that proposed method outperforms recent metaheuristics, rule-based, other RL-based methods terms tardiness. Moreover, computation time for obtaining schedule by our shorter than those metaheuristics methods.
منابع مشابه
Minimizing total tardiness for scheduling identical parallel machines with family setups
This paper presents several procedures for scheduling identical parallel machines with family setups when the objective is to minimize total tardiness. These procedures are tested on several problem sets with varying numbers of families, jobs and machines, varying setup time distributions and various levels of due date tightness and variability. The results show that genetic algorithms are the ...
متن کاملParallel-machine Scheduling with Load-balancing and Sequence-dependent Setups
In many practical manufacturing environments, setups consume a significant amount of industrial resources. Therefore, reducing setups in a non-identical parallel machine environment will significantly enhance a company’s performance level. In this thesis, the problem of minimizing total completion time with load balancing and sequence-dependent setups in a non-identical parallel machine environ...
متن کاملWeighted Tardiness Scheduling with Sequence-Dependent Setups: A Benchmark Library
This report details a set of benchmark problem instances that we have generated for the weighted tardiness scheduling with sequence-dependent setups problem. The version of the problem without setup times is NP-Hard. The problem is further complicated by the sequence-dependent nature of the setups. Given that the weighted tardiness objective and the sequence-dependent setups constraint are both...
متن کاملMinimizing Total Tardiness in Parallel-Machine Scheduling with Release Dates
The considered problem is the scheduling of a set of N jobs on M identical parallel machines in order to minimize the total tardiness without any preemption or splitting. Each job has its own processing time, release date and due date. All the machines are considered identical (with same speed) and available during all the scheduling period. This problem is NP-hard. An exact resolution, an Ant ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2021
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2021.3097254