Scholarlink

<p>The growing need for sustainable civil infrastructure demands data-driven strategies capable of balancing conflicting project objectives such as time, cost, energy consumption, and structural durability. This study presents an integrated Big Data– and cloud-enabled multi-objective optimization framework that leverages heterogeneous construction data from Building Information Modeling (BIM), Internet of Things (IoT), Geographic Information Systems (GIS), and environmental APIs. The proposed system employs the Non-dominated Sorting Genetic Algorithm III (NSGA-III) to generate Pareto-optimal solutions, implemented within an Amazon Web Services (AWS) and Apache Spark architecture for scalable, real-time computation. A case study on a mid-rise reinforced concrete building involving ten decision variables—such as zeolite percentage, bacterial concentration, and curing duration—was conducted to validate the framework. The optimized solution achieved a project duration of 395 days, a life-cycle cost of ₹54.1&#xa0;million, energy consumption of 920 GJ, and structural durability of 84.3%, demonstrating significant performance improvement over conventional methods (MOPSO, MOACO, and NSGA-II) in terms of solution diversity, convergence speed, and computational efficiency. Trade-off and sensitivity analyses further reveal the nonlinear interdependence between material composition, curing conditions, and sustainability metrics. The findings confirm that the integration of Big Data and cloud-based optimization enhances real-time decision-making and operational sustainability. The proposed framework provides a scalable digital foundation for achieving resilient, cost-efficient, and environmentally responsible infrastructure design, aligning with the UN Sustainable Development Goals.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating big data and cloud computing for multi-objective optimization in sustainable civil engineering projects

  • 期刊论文

  • 发表日期：

    2025年11月17日

查看全文
  • Debendra Maharana,
  • Srinivas Sethi

摘要

The growing need for sustainable civil infrastructure demands data-driven strategies capable of balancing conflicting project objectives such as time, cost, energy consumption, and structural durability. This study presents an integrated Big Data– and cloud-enabled multi-objective optimization framework that leverages heterogeneous construction data from Building Information Modeling (BIM), Internet of Things (IoT), Geographic Information Systems (GIS), and environmental APIs. The proposed system employs the Non-dominated Sorting Genetic Algorithm III (NSGA-III) to generate Pareto-optimal solutions, implemented within an Amazon Web Services (AWS) and Apache Spark architecture for scalable, real-time computation. A case study on a mid-rise reinforced concrete building involving ten decision variables—such as zeolite percentage, bacterial concentration, and curing duration—was conducted to validate the framework. The optimized solution achieved a project duration of 395 days, a life-cycle cost of ₹54.1 million, energy consumption of 920 GJ, and structural durability of 84.3%, demonstrating significant performance improvement over conventional methods (MOPSO, MOACO, and NSGA-II) in terms of solution diversity, convergence speed, and computational efficiency. Trade-off and sensitivity analyses further reveal the nonlinear interdependence between material composition, curing conditions, and sustainability metrics. The findings confirm that the integration of Big Data and cloud-based optimization enhances real-time decision-making and operational sustainability. The proposed framework provides a scalable digital foundation for achieving resilient, cost-efficient, and environmentally responsible infrastructure design, aligning with the UN Sustainable Development Goals.