Review of Construction Project Scheduling Optimization Based on Network Graph Model

Abstract

At the current stage of the construction industry, effective planning and swift project execution are crucial. Traditional planning methods rely on classical network planning and management models. Due to the lack of research on applying machine learning to network planning, a method has been proposed to transform an applied construction planning model for using both classical and machine learning methods. This study reviews the optimization problem of construction project scheduling and develops an algorithm for converting an applied project into a network graph model. The main rules and principles for model transformation, considering practical constraints in production, are formulated. The construction industry today faces significant challenges in improving the efficiency of project planning and execution speed. Existing methodologies typically rely on classical network planning models. However, there is a gap in research regarding the use of machine learning for network planning. To address this, the proposed method enhances construction management by integrating classical and machine learning approaches for transforming planning models. This research reviews construction project scheduling optimization and introduces an algorithm to convert projects into network graph models, outlining essential transformation rules and principles to accommodate industry constraints.