A HYBRID EVOLUTIONARY OPTIMISATION FRAMEWORK FOR DYNAMIC RESOURCE ALLOCATION AND MULTIDIMENSIONAL CONSTRUCTION PROJECT PERFORMANCE ENHANCEMENT USING GENETIC ALGORITHM, PARTICLE SWARM OPTIMISATION, AND ANT COLONY OPTIMISATION

Complexity involved in the construction projects is posing many problems in terms of resource planning, labour productivity, machinery utilization, cost control, and scheduling of the project. Traditional methods of managing construction projects are generally based on manual planning and monitoring and are ineffective to adapt to changing dynamics on site. The current research work aims to introduce an AI and IoT-based intelligent multidimensional construction project management framework that is based on GA, PSO, and ACO for improved real-time planning and monitoring as well as effective resource optimization. Construction Project Database which included data related to construction project, IoT sensor observation, labour force, machinery database, material allocation, construction activities, and optimization parameters was developed. IoT sensing devices including RFID, GPS, wearables, environment sensors, and machinery monitoring system provided real-time data for the project, while optimization algorithms offered optimal resource allocation plan. The proposed framework was analyzed in terms of many different performance measures including project cost, project time, labour productivity, machinery utilization, material wastage, planning accuracy, monitoring accuracy, resource allocation efficiency, prediction accuracy, and overall project performance. The optimisation outcomes showed that there was a cost saving of 8.0%, project time savings of 8.7%, productivity improvement of labour from 82.6 to 91.8, equipment utilisation improvement from 74.2% to 88.5%, and savings in material wastage by 40.6%. In addition, there was a significant improvement in planning accuracy (96.1%), monitoring accuracy (97.5%), resource allocation efficiency (95.2%), and Overall Project Performance Index improved from 81.6 to 95.9. PSO performed better than GA and ACO with respect to the maximum fitness score of 0.928 and a higher convergence rate of 95.8%. The developed AI–IoT optimisation framework is an intelligent decision support tool that improves construction productivity and efficiency, operational efficiency, sustainability and real-time project management and helps in the evolution of digital and smart construction under Construction 4.0.