| Issue |
EPJ Web Conf.
Volume 302, 2024
Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo (SNA + MC 2024)
|
|
|---|---|---|
| Article Number | 17007 | |
| Number of page(s) | 9 | |
| Section | Artificial Intelligence & Digital in Nuclear Applications - Quantum Computing | |
| DOI | https://doi.org/10.1051/epjconf/202430217007 | |
| Published online | 15 October 2024 | |
https://doi.org/10.1051/epjconf/202430217007
A Modular Heuristic-Based Solution for Large-Scale Outage Management in Nuclear Power Plants
1 Digital Excellence Center, Assystem, Courbevoie, France
2 Digital Transformation Services, Assystem, Courbevoie, France
3 Technology & Innovation, Assystem, Courbevoie, France
* e-mail: kninpan@assystem.com
Published online: 15 October 2024
The Resource Constrained Project Scheduling Problem (RCPSP) is a prominent combinatorial optimization problem in academia. It involves scheduling project activities while considering constraints arising from logical relationships between tasks, resource capacity limitations, and other projectspecific factors. In this paper, we propose a modular heuristic method for efficient outage planning and execution within Nuclear Power Plants (NPPs). The project contains more than 24,000 tasks with specific industrial-oriented constraints such as the notion of prioritization, the event of pausing tasks in progress, handling of resources incompatibility, and adjusting dynamic units of resources based on their availability. The execution speed of the entire solution has been extensively revised to reach an average of 10 to 15 minutes on a standard computer. This enables project managers to promptly evaluate various scenarios with minimal data adjustments, facilitating informed decision-making. The solutions effectiveness has been validated by domain experts, demonstrating its potential for real-world application.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.