Open Access Open Access  Restricted Access Subscription Access

AI-Driven Smart Energy Management Platform for Renewable Energy Optimisation

Saiyam N Bothra, Dr. Manish Kumar

Abstract


The variability of solar and wind generation poses challenges for grid stability and efficiency. This paper presents a smart energy management system (SEMS) with an AI-driven software architecture to optimize renewable energy use in buildings and microgrids. The platform integrates IoT sensor data, machine learning forecasts (e.g. Support Vector Regression) for generation/load prediction, and a predictive scheduling algorithm for battery storage and load control. A microservices architecture with cloud/edge deployment is used for scalability and fault tolerance. In simulation with realistic profiles, the SEMS improves renewable self-consumption and reduces grid dependency, consistent with results in similar studies.


Full Text:

PDF

References


Z. Lyu et al., “Microservice-Based Architecture for an Energy Management System,” IEEE Systems J., 2020. (Containerized microservices improved EMS scalability and reliability.)

I. Núñez et al., “Design of a Microservices-Based Architecture for Residential Energy Efficiency Monitoring,” Int. J. Electr. Telecommun., vol. 70, no. 4, 2024. (Proposes a cloud-IoT microservices EMS that significantly improves demand response and energy savings.)

C. K. Rao et al., “IoT Enabled Intelligent Energy Management System with Advanced Forecasting and Load Optimization,” Unconv. Res., vol. 4, 2024. (An IoT-based SEMS using SVM+PSO forecasting for planning; shows IoT-enabled forecasting improves day-ahead scheduling accuracy.)

A. H. Bagdadee et al., “IoT-driven Hybrid Renewable Energy Integration for Enhanced Smart Home Efficiency,” Sci. Rep., 15:41491 (2025). (IoT sensors and control in hybrid solar-wind-storage homes increased efficiency by ~72%, reduced costs and CO₂.)

A. R. Singh et al., “ML-Based Energy Management and Power Forecasting in Grid-Connected Microgrids,” Sci. Rep., 2025. (Employs SVR to forecast distributed generation; highlights that accurate forecasts are crucial for microgrid efficiency.)

J. A. A. Silva et al., “IoT-Based EMS for AC Microgrids with Grid and Security Constraints,” Appl. Energy, vol. 337, May 2023. (Presents a microservices IoT-EMS with a GUI, database, API, and MILP optimizer, validated on real microgrid data.)

N. Reiners and L. Millet, “Application of the Open-Source Energy Management System OpenEMS in Hybrid Power Systems,” 4th Hybrid Power Systems Workshop, 2019. (Uses OpenEMS platform to simulate PV-battery-diesel microgrid; shows open EMS can coordinate diverse sources and optimize generator dispatch for fuel savings.)

L. L. Motta et al., “A Cloud Architecture for Home Energy Management Systems: A Conceptual Model,” Energy Informatics, vol. 8:142 (2025). (Proposes a layered cloud–edge architecture for HEMS, highlighting scalable IoT data ingestion and analytics to support real-time monitoring and stakeholder needs.)

C. K. Rao et al., “Review of IoT-Enabled Smart EMS for Photovoltaic Forecasting,” Unconv. Res., vol. 9, 2026. (Reviews IoT-based PV energy management; emphasizes that reliable forecasting and cloud-based frameworks are required for effective smart grid operation.)

F. Z. Elargoubi et al., “Advancements in Home Energy Management Systems: Review of Optimization Strategies,” IFAC-PapersOnLine, vol. 58, no. 13, 2024. (Surveys HEMS techniques; finds that real-time control and renewable integration greatly reduce costs and emissions, and stresses IoT for user empowerment.)


Refbacks

  • There are currently no refbacks.