AI Enabled Smart Web Based System for Monitoring Sustainable Energy Usage in Construction Supply Management

The construction industry significantly contributes to global energy consumption and carbon emissions, necessitating innovative solutions for sustainable supply chain management. This study presents an AI-Enabled Smart Web-Based System for Monitoring Sustainable Energy Usage in Construction Supply Management, which innovatively integrates AI-driven energy prediction directly into procurement workflows. The system, developed using the Waterfall model and built upon a Laravel-MySQL-Python (Scikit-Learn) architecture, provides a robust platform for real-time procurement tracking and AI-driven energy usage prediction. Functional testing verified the system's operational reliability, achieving a 100% pass rate. The integrated AI prediction module demonstrated high accuracy with a Mean Absolute Error (MAE) of 0.62 kWh, effectively forecasting energy consumption associated with procurement transactions. User evaluations indicated a 92% overall satisfaction rate, highlighting significant improvements in data transparency, report generation speed, and enhanced understanding of energy-related impacts. This system offers a novel approach to bridge the critical gap between operational efficiency and environmental sustainability in construction supply chains, providing a scalable model for intelligent, energy-aware process transformation. This research contributes a scalable model for fostering sustainable digital transformation within the construction sector, aligning with global sustainability goals and promoting eco-efficient practices.