A Modular Heuristic-Based Solution for Large-Scale Outage Management in Nuclear Power Plants

Abstract

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.