File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: A Double Deep Q-Network-Enabled Two-Layer Adaptive Work Package Scheduling Approach
| Title | A Double Deep Q-Network-Enabled Two-Layer Adaptive Work Package Scheduling Approach |
|---|---|
| Authors | |
| Issue Date | 5-Aug-2023 |
| Abstract | Adaptive project scheduling is paramount for project success. However, it is challenging for industrialized construction (IC) projects to their fragmentation with spatial-temporal distributed work packages (e.g., tasks in production, transportation, and on-site assembly). To achieve adaptive project scheduling in IC, this study proposes a double deep Q-network (DDQN)-enabled two-layer adaptive work package (D2-TAWP) approach. First, the project scheduling process is transformed into a Markov decision process to model the sequential decision-making process of scheduling; Second, a two-layer adaptive scheduling approach is developed to schedule tasks of work packages dynamically. Finally, the effectiveness of the D2-TAWP approach is validated by experimental simulation. The results indicate that the D2-TAWP approach can effectively perform work package scheduling compared to traditional heuristics, which paves the way for the next-generation distributed scheduling of IC projects. |
| Persistent Identifier | http://hdl.handle.net/10722/338642 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Zhang, Yaning | - |
| dc.contributor.author | Li, Xiao | - |
| dc.contributor.author | Wu, Chengke | - |
| dc.contributor.author | Chen, Zhi | - |
| dc.date.accessioned | 2024-03-11T10:30:24Z | - |
| dc.date.available | 2024-03-11T10:30:24Z | - |
| dc.date.issued | 2023-08-05 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/338642 | - |
| dc.description.abstract | <p>Adaptive project scheduling is paramount for project success. However, it is challenging for industrialized construction (IC) projects to their fragmentation with spatial-temporal distributed work packages (e.g., tasks in production, transportation, and on-site assembly). To achieve adaptive project scheduling in IC, this study proposes a double deep Q-network (DDQN)-enabled two-layer adaptive work package (D<sup>2</sup>-TAWP) approach. First, the project scheduling process is transformed into a Markov decision process to model the sequential decision-making process of scheduling; Second, a two-layer adaptive scheduling approach is developed to schedule tasks of work packages dynamically. Finally, the effectiveness of the D<sup>2</sup>-TAWP approach is validated by experimental simulation. The results indicate that the D<sup>2</sup>-TAWP approach can effectively perform work package scheduling compared to traditional heuristics, which paves the way for the next-generation distributed scheduling of IC projects.<br></p> | - |
| dc.language | eng | - |
| dc.relation.ispartof | 27th International Symposium on Advancement of Construction Management and Real Estate (05/12/2022-06/12/2022, Hong Kong) | - |
| dc.title | A Double Deep Q-Network-Enabled Two-Layer Adaptive Work Package Scheduling Approach | - |
| dc.type | Conference_Paper | - |
| dc.identifier.doi | 10.1007/978-981-99-3626-7_79 | - |
| dc.identifier.spage | 1027 | - |
| dc.identifier.epage | 1041 | - |