TY - GEN
T1 - A deep reinforcement learning based approach for dynamic job shop scheduling considering variable processing time
AU - Yang, Shuai
AU - Guo, Hongwei
AU - Huang, Jiaqi
AU - Han, Kexian
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2024/10/4
Y1 - 2024/10/4
N2 - The job shop scheduling problem is a common challenge in intelligent manufacturing. In a real workshop environment, parameters like processing time often change dynamically. Scheduling strategies must be adjusted flexibly and quickly to match the current state. However, traditional methods only find the optimal solution for a specific instance. When environment parameters change, recalculations are required, leading to high time costs. To address these problems, a scheduling method called S2S-AC, based on deep reinforcement learning, is proposed to efficiently solve the dynamic job shop scheduling problem with variable processing times. In the proposed method, JSSP is modeled as a sequential decision-making problem using a Markov Decision Process. A new state set model, including four static states and two dynamic states, is designed with operations as the action set. An end-to-end framework that combines the Pointer Network model with the A2C algorithm is used to construct the DRL network, which is trained with multiple samples. The trained network directly outputs the scheduling strategy for new instances without requiring retraining. In static experiments, the effectiveness of S2S-AC is verified by comparing its solution results with those of SPT, LPT, MTWR, and the genetic algorithm on benchmark instances. In dynamic experiments, S2SAC achieved the best solution results in all randomly generated test instances based on instance ft10, compared to the above methods, with relatively short solution times.
AB - The job shop scheduling problem is a common challenge in intelligent manufacturing. In a real workshop environment, parameters like processing time often change dynamically. Scheduling strategies must be adjusted flexibly and quickly to match the current state. However, traditional methods only find the optimal solution for a specific instance. When environment parameters change, recalculations are required, leading to high time costs. To address these problems, a scheduling method called S2S-AC, based on deep reinforcement learning, is proposed to efficiently solve the dynamic job shop scheduling problem with variable processing times. In the proposed method, JSSP is modeled as a sequential decision-making problem using a Markov Decision Process. A new state set model, including four static states and two dynamic states, is designed with operations as the action set. An end-to-end framework that combines the Pointer Network model with the A2C algorithm is used to construct the DRL network, which is trained with multiple samples. The trained network directly outputs the scheduling strategy for new instances without requiring retraining. In static experiments, the effectiveness of S2S-AC is verified by comparing its solution results with those of SPT, LPT, MTWR, and the genetic algorithm on benchmark instances. In dynamic experiments, S2SAC achieved the best solution results in all randomly generated test instances based on instance ft10, compared to the above methods, with relatively short solution times.
KW - Deep reinforcement learning
KW - Dynamic scheduling
KW - Job shop scheduling
KW - Pointer network
UR - http://www.scopus.com/inward/record.url?scp=85212587515&partnerID=8YFLogxK
U2 - 10.1145/3690931.3690993
DO - 10.1145/3690931.3690993
M3 - Conference contribution
AN - SCOPUS:85212587515
T3 - ACM International Conference Proceeding Series
SP - 368
EP - 374
BT - Proceedings of 2024 4th International Conference on Artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024
PB - Association for Computing Machinery
T2 - 4th International Conference on Artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024
Y2 - 19 July 2024 through 21 July 2024
ER -