E-MOIS: An Intelligent Mobile Platform for Institutional Energy Monitoring and Optimization

Abstract

Energy consumption in academic institutions is a growing concern due to increasing electricity costs, inefficient monitoring, and environmental impact. At institution, manual and delayed data collection limits timely energy optimization. This study developed E-MOIS (Energy Monitoring and Optimization Intelligent System), a mobile-based intelligent system for real-time energy monitoring and optimization. Using the Agile methodology, the system was built with Flutter (Dart) for the mobile interface, Python for back-end analytics, and Firebase as the cloud database. A Random Forest Regression model analyzed daily energy data, enhanced through preprocessing and feature engineering, and evaluated using Mean Squared Error (MSE). The system provided dashboards, trend reports, and abnormal usage alerts for various users. Results showed accurate consumption forecasting and early detection of irregularities. User testing confirmed its reliability and usability. E-MOIS demonstrates a scalable decision-support tool that enhances energy management and promotes sustainability in academic institutions.