Application and Research of Intelligent Algorithms in Scheduling Optimization of Civil Engineering Projects

Efficient scheduling optimization is a critical component of resource management in civil engineering projects, which often involve dynamic and complex environments. Traditional scheduling approaches face challenges in addressing large-scale constraints, real-time adaptability, and the combinatorial nature of tasks, leading to resource underutilization and delays. To address these issues, this study proposes a novel Adaptive Scheduling Framework (ASF) integrated with a Dynamic Task Allocation Strategy (DTAS) tailored specifically for civil engineering applications. The ASF employs graph-based task-resource modeling and multi-objective optimization to manage the scalability and flexibility required in construction projects. By representing scheduling problems as bipartite graphs, the framework captures temporal dynamics, task dependencies, and resource constraints to achieve a balance between priority and feasibility. The DTAS enhances scheduling efficiency by introducing dynamic task prioritization, iterative conflict resolution, and real-time feedback-driven refinement. Experimental results, focused on civil engineering scenarios, demonstrate that the proposed methods significantly reduce project completion time, improve resource utilization, and adapt effectively to changes in construction requirements and resource availability. This study underscores the transformative potential of intelligent algorithms in optimizing scheduling for civil engineering project management and other resource-intensive domains.