A Double Deep Q-Network-Enabled Two-Layer Adaptive Work Package Scheduling Approach

Yaning Zhang, Xiao Li (), Chengke Wu and Zhi Chen
Additional contact information
Yaning Zhang: Northwestern Polytechnical University
Xiao Li: The Hong Kong Polytechnic University
Chengke Wu: The Hong Kong Polytechnic University
Zhi Chen: Northwestern Polytechnical University

A chapter in Proceedings of the 27th International Symposium on Advancement of Construction Management and Real Estate, 2023, pp 1027-1041 from Springer

Abstract: 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.

Keywords: industrialized construction; project scheduling; work package schedules; deep reinforcement learning (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-99-3626-7_79

Ordering information: This item can be ordered from
http://www.springer.com/9789819936267

DOI: 10.1007/978-981-99-3626-7_79

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().