Dynamic job shop scheduling using deep reinforcement learning
This FYP project aims to improve on the make span in dynamic job shop scheduling using deep reinforcement learning techniques and testing it with different neural network configurations and comparing the results with heuristic methods. The deep reinforcement learning algorithm is mainly Rainbow Deep...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/177529 |
| _version_ | 1826116818423513088 |
|---|---|
| author | Tan, Hong Ming |
| author2 | Shu Jian Jun |
| author_facet | Shu Jian Jun Tan, Hong Ming |
| author_sort | Tan, Hong Ming |
| collection | NTU |
| description | This FYP project aims to improve on the make span in dynamic job shop scheduling using deep reinforcement learning techniques and testing it with different neural network configurations and comparing the results with heuristic methods. The deep reinforcement learning algorithm is mainly Rainbow Deep Q Learning without multistep learning and distributional Deep Q Learning (RDQN) and testing with a combination of Convolutional 1D neural networks (CNN1D), LSTM, and Dense.
It is found that RDQN with CNN1D gives the best make span when trained with the job shop which closely represents real life process flow and is tested against the job shop with varying process time to the job shop in which it was trained in and a varying number of jobs and machines is also tested. The result is compared with other heuristic methods as well as different configurations for the neural network structure. |
| first_indexed | 2024-10-01T04:17:39Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/177529 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:17:39Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1775292024-06-01T16:51:54Z Dynamic job shop scheduling using deep reinforcement learning Tan, Hong Ming Shu Jian Jun School of Mechanical and Aerospace Engineering MJJShu@ntu.edu.sg Engineering This FYP project aims to improve on the make span in dynamic job shop scheduling using deep reinforcement learning techniques and testing it with different neural network configurations and comparing the results with heuristic methods. The deep reinforcement learning algorithm is mainly Rainbow Deep Q Learning without multistep learning and distributional Deep Q Learning (RDQN) and testing with a combination of Convolutional 1D neural networks (CNN1D), LSTM, and Dense. It is found that RDQN with CNN1D gives the best make span when trained with the job shop which closely represents real life process flow and is tested against the job shop with varying process time to the job shop in which it was trained in and a varying number of jobs and machines is also tested. The result is compared with other heuristic methods as well as different configurations for the neural network structure. Bachelor's degree 2024-05-29T06:39:46Z 2024-05-29T06:39:46Z 2022 Final Year Project (FYP) Tan, H. M. (2022). Dynamic job shop scheduling using deep reinforcement learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177529 https://hdl.handle.net/10356/177529 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Tan, Hong Ming Dynamic job shop scheduling using deep reinforcement learning |
| title | Dynamic job shop scheduling using deep reinforcement learning |
| title_full | Dynamic job shop scheduling using deep reinforcement learning |
| title_fullStr | Dynamic job shop scheduling using deep reinforcement learning |
| title_full_unstemmed | Dynamic job shop scheduling using deep reinforcement learning |
| title_short | Dynamic job shop scheduling using deep reinforcement learning |
| title_sort | dynamic job shop scheduling using deep reinforcement learning |
| topic | Engineering |
| url | https://hdl.handle.net/10356/177529 |
| work_keys_str_mv | AT tanhongming dynamicjobshopschedulingusingdeepreinforcementlearning |