Optimizing time, cost, and carbon in construction: grasshopper algorithm empowered with tournament selection and opposition-based learning

Abstract

The global construction industry plays a pivotal role, yet its unique characteristics pose distinctive challenges. Each construction project, marked by its individuality, substantial value, intricate scale, and constrained adaptability, confronts crucial limitations concerning time and cost. Despite contributing significantly to environmental concerns throughout construction activities and infrastructure operations, environmental considerations remain insufficiently addressed by project managers. This research introduces an improved rendition of the muti-objective grasshopper optimization algorithm (MOGOA), termed eMOGOA, as a novel methodology to tackle time, cost, and carbon dioxide emission trade-off problems (TCCP) in construction project management. To gauge its efficacy, a case study involving 29 activities is employed. eMOGOA amalgamates MOGOA, tournament selection (TS), and opposition-based learning (OBL) techniques to enhance the performance of the original MOGOA. The outcomes demonstrate that eMOGOA surpasses other optimization algorithms, such as MODA, MOSMA, MOALO and MOGOA when applied to TCCP. These findings underscore the efficiency and relevance of the eMOGOA algorithm within the realm of construction project management.