Biologically inspired optimization for multi-objective construction management: the MOGPOO model

Purpose For construction projects to be managed successfully and to provide the best results, it is essential to assess the trade-offs between time, cost, and quality. By creating and implementing a unique strategy, this study aims to advance solutions to the time-cost-quality trade-off (TCQT) problem. The main goal is to present the multi-objective Giant Pacific Octopus Optimizer (MOGPOO), a state-of-the-art optimization system. This method is intended to transform multi-objective optimization (MO) in construction project management, drawing inspiration from the Giant Pacific Octopus’s strategic and adaptable nature. MOGPOO aims to improve decision-making procedures, increase project efficiency and establish a new benchmark for handling intricate trade-offs in this industry by utilizing its special problem-solving skills. Design/methodology/approach The objective of this research is to create a novel hybrid metaheuristic algorithm through the integration of many optimization methods. In particular, the MOGPOO method is the result of combining the advantages of GPOO (Giant Pacific Octopus Optimizer) and MO. Its optimization abilities are improved by a number of methods, including dynamic weight adjustment, adaptive parameter tuning and sophisticated search techniques, which are especially useful for striking a balance between exploration and exploitation. These improvements make solving complicated multi-objective problems simpler and enable faster convergence and more accurate solutions. The TCQT issue will be used to thoroughly assess the algorithm’s performance, and benchmark testing and comparison analysis will be used to confirm its robustness and efficiency. Findings The efficiency of the proposed method was assessed by analyzing two different TCQT problems in building projects. According to the results, MOGPOO outperforms earlier algorithms and produces extremely competitive solutions. In particular, compared to benchmark approaches, the study shows an increase in hyper-volume of 79.3% (case 1) and 80.6% (case 2), a decrease in computational time of 121s (case 1) and 119s (case 2), and an improvement in solution spread of 57.4% and 59.6% for case 1 and case 2, respectively. Setting a new standard for optimization performance in construction project management, these results highlight MOGPOO’s capacity to solve TCQT problems more precisely and efficiently. Research limitations/implications The difficulties of optimization trade-offs in a variety of disciplines have been the subject of a large number of research in recent years. A crucial gap has been brought to light by the increasing complexity and quick evolution of technological requirements in building projects, nevertheless, since current algorithms frequently find it difficult to effectively handle particular, complicated jobs. This emphasizes the need for creating cutting-edge algorithms specifically suited to these particular difficulties. Further supporting the need for a new strategy is the growing dependence on sophisticated optimization models in both research and real-world applications. Strong, well-crafted algorithms not only meet the urgent needs of contemporary construction management, but they are also an invaluable resource for directing decision-making procedures, guaranteeing more successful and efficient project outputs. Originality/value In the area of metaheuristic algorithms, especially as it relates to building project management, this study marks a substantial breakthrough. Among the most important findings is the effective combination of the GPOO and MO, which results in a potent instrument for handling intricate multi-objective problems in intricately linked building projects. The research shows that this innovative hybrid strategy not only improves optimization performance but also offers a scalable and practical way to handle the complex trade-offs that come with building projects. The possibility of merging multi-objective frameworks with biologically inspired algorithms to address real-world issues more accurately and effectively is shown by this discovery.