AEHO: Apriori-Based Optimized Model for Building Construction to Time-Cost Tradeoff Modeling

Time and cost are the two most crucial aspects to consider in planning any building project. The project’s overall objective is to complete the projects on schedule, under cost, and to meet other project goals. In reality, construction managers have a demanding job that regularly monitors progress, evaluates goals, and takes necessary steps. Optimization is a deliberate attempt to increase profit margins and get the best outcomes under given conditions. Finding optimal planning and good administration is required for the project to be completed on time. There are several optimizing tools and strategies available. Maximizing the performance of the various approaches utilized at one point during the construction project might not be advantageous if the strategies applied do not increase efficiency. In this work, a model is developed using an Apriori-based swarm intelligence method, with the non-dominated solutions to the separation of Elephant Herding Optimization technique, named the AEHO model. This modeling approach follows the Apriori algorithm to generate the rules and then the EHO algorithm that contains population initialization, selection, and fitness evaluation for input parameters. This strategy optimizes construction time, cost, & environmental effects in an actual construction project. For this purpose, a case study of a building construction project has been employed to show the usability of the proposed method. The simulation was done in MATLAB to collect sixty construction projects in Iraq between 2008 and 2016. This study intends to minimize time and cost for construction projects that include repetitive project activities by using the learning curve phenomenon, which reduces time and cost savings when considering the project’s start and finish dates. Also, a comparison has been made to the usefulness of the proposed AEHO model in optimal design over the existing PSO model. This comparison is demonstrated by measuring many performance measures and a comparison with an already existing PSO optimization model. In addition, a coefficient value plot is established for visualizing the provided objectives, and an Apriori method is presented for selecting one solution from the Pareto-optimal front that has been generated.