Opposition-Based NSGA-III Framework for Multi-Objective Optimization of Retrofitting Projects: Balancing Time, Cost, Quality, Energy, Safety, and Environmental Impact

Abstract

The study highlights significant theoretical and practical contributions, including the incorporation of safety and environmental impact—often neglected in previous models—and the demonstration of adaptability across varied urban contexts. Limitations such as computational intensity and generalizability are acknowledged, with future research directions suggested in areas like dynamic modeling, stakeholder integration, and AI-enhanced decision-making.

Introduction

This research proposes hybrid optimization models that improve the search and initialization mechanisms of traditional evolutionary algorithms. A key contribution is the integration of Opposition-Based Learning (OBL) with the Non?Dominated Sorting Genetic Algorithm III (NSGA-III) to form the OBNSGA-III framework. Opposition-Based Learning, introduced by Hamid R. Tizhoosh in 2005, enhances population diversity by evaluating both candidate solutions and their opposite solutions simultaneously, leading to improved exploration and faster convergence.

The main objective of the study is to develop a mathematical framework for optimizing six critical retrofitting objectives: minimizing completion time and cost, maximizing quality, and minimizing energy consumption, safety risk, and environmental impact. The research also aims to improve the performance of NSGA-III using OBL, apply the model to a real-world commercial retrofitting project in Delhi-NCR, and generate a Pareto-optimal solution set that helps decision-makers evaluate trade-offs among multiple project objectives.

The literature review highlights the growing importance of multi-objective optimization in construction management, particularly for sustainable and resilient infrastructure. Advanced evolutionary algorithms such as NSGA-III and its hybrid variants enable efficient optimization across multiple performance factors in complex retrofitting projects.

The research methodology introduces the TCQESET model, which evaluates retrofitting projects based on time, cost, quality, energy consumption, safety, and environmental impact. A project is divided into several retrofitting aspects, each having multiple execution options with specific resource requirements. The model optimizes these aspects while considering constraints such as precedence relationships, limited resources, integer decision variables, and the requirement that each activity must use one continuous retrofitting option.

Overall, the proposed OBNSGA-III optimization framework generates diverse Pareto-optimal solutions and identifies balanced retrofitting strategies, supporting sustainable infrastructure planning and improved decision-making in construction project management.

Conclusion

This thesis proposed and validated a novel hybrid multi-objective optimization framework for enhancing the performance of urban infrastructure retrofitting projects. This study reaffirms that urban infrastructure retrofitting is inherently a complex, multi-dimensional challenge that cannot be adequately addressed using traditional single- or bi-objective models. By integrating a hybrid NSGA-III–OBL optimization algorithm, this research advances the methodological toolkit for urban planners, offering a solution that is both technically robust and practically viable.

References

[1] Ahmad, E., Khatua, L., Chandra, K., Miguel, S., & Upadhyay, V. A. (2025). Comparative seismic analysis of symmetrical and asymmetrical G + 7 structures using STAAD . Pro?: insights into performance and material efficiency. Asian Journal of Civil Engineering. [2] Bocaneala, N., Mayouf, M., Vakaj, E., & Shelbourn, M. (2024). Artificial Intelligence Based Methods for Retrofit Projects: A Review of Applications and Impacts. Archives of Computational Methods in Engineering, 0123456789. https://doi.org/10.1007/s11831-024-10159-7 [3] Dumaru, R., Rodrigues, H., & Varum, H. (2018). Comparative study on the seismic performance assessment of existing buildings with and without retrofit strategies. International Journal of Advanced Structural Engineering, 10(4), 439–464. https://doi.org/10.1007/s40091-018-0207-z [4] Kaveh, A., Dadras Eslamlou, A., Javadi, S. M., & Geran Malek, N. (2021). Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders. Acta Mechanica, 232(3), 921–931. https://doi.org/10.1007/s00707-020-02878-2 [5] Nagayo, A. M., Singh, R., Dhawan, A., Manjunath, T. C., Qasem, A., Sethi, K. C., & Sharma, K. (2025). Integrating environmental sustainability in construction Time ? Cost trade ? off for decision ? making using hybrid NSGA ? III and MOPSO approach. Asian Journal of Civil Engineering, 0123456789. https://doi.org/10.1007/s42107-025-01265-3 [6] Panwar, A., Tripathi, K. K., & Jha, K. N. (2019). A qualitative framework for selection of optimization algorithm for multi-objective trade-off problem in construction projects. Engineering, Construction and Architectural Management. https://doi.org/10.1108/ECAM-06-2018-0246 [7] Sethi, K. C., Prajapati, U., Parihar, A., Gupta, C., Shrivastava, G., & Sharma, K. (2024). Development of optimization model for balancing time, cost, and environmental impact in retrofitting projects with NSGA-III. Asian Journal of Civil Engineering. https://doi.org/10.1007/s42107-024-01102-z

Copyright

Copyright © 2026 Shreyansh Upraiti, Mukesh Pandey, Rakesh Gupta. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.