An Improved Red Panda Optimizer for Effective Construction Site Design

Abstract

A properly planned design will minimize travel distance, handling of materials diligence, and operating costs, as well as saving time and ease site congestion. The majority of mathematical optimization approaches discovered thus far are effective for modest problems and frequently fall within global or local optimum solutions, which does not ensure continued convergence. As a result, the motive of this work is to propose an Improved Red Panda Optimizer (IRPO) algorithm inspired by the predatory habits of Red pandas, integrating with the Mutation and crossover strategy of Differential Evolution and Oppositional Based Learning and solving a shortcoming of earlier research. The analysis revealed that the proposed approach can lead to very positive results in connection with enhanced exploitation, convergence, avoiding local optima, and exploration. Additionally, the IRPO method yields better ideal solutions for the great majority of the design and shows that this strategy may be used for a variety of limited issues across different search domains. The results of the ideal site layout optimization method show how well the suggested approach works in real-world situations where search areas are ambiguous.