Home / Current Issue / Paper 1718717
Smart Energy Consumption Forecasting using IoT, Machine Learning and Web Application
Subject area: Science,Engineering and Technology · Area of research: IoT
DOI: 10.64388/IREV9I12-1718717
Abstract
The Smart Energy Consumption Forecasting system is an intelligent energy analytics platform designed to monitor, analyze, and predict electricity usage in residential, commercial, and institutional environments. The proposed system integrates Internet of Things (IoT) sensors, cloud connectivity, machine learning models, and a responsive web application into a unified architecture for real-time energy management. Smart meters and environmental sensors continuously collect voltage, current, power factor, occupancy, temperature, and appliance-level usage data. These data streams are processed through a backend analytics engine, where machine learning algorithms such as Linear Regression, Random Forest Regressor, and Long Short-Term Memory (LSTM) networks are applied to forecast short-term and medium-term energy demand. The web application provides live dashboards, anomaly alerts, historical trend visualization, and consumption forecasting reports for users and administrators. Experimental observations indicate that the proposed platform improves energy visibility, supports proactive load balancing, and enhances decision-making for efficient power utilization. The system contributes toward sustainable smart building management by reducing energy wastage, improving forecast accuracy, and enabling intelligent, data-driven energy optimization.
Keywords
Smart Energy, Energy Forecasting, Internet of Things, Machine Learning, Web Application, Smart Meter, Load Prediction, Sustainable Energy Management
References
[1] G. Chicco, R. Napoli, and F. Piglione, "Comparisons among clustering techniques for electricity customer classification," IEEE Transactions on Power Systems, 2006.
[2] H. Hong, P. Pinson, and S. Fan, "Global energy forecasting competition 2012," International Journal of Forecasting, 2014.
[3] A. Jain, E. Srinivas, and S. R. K. Prasad, "IoT based smart energy meter monitoring system," International Journal of Engineering Research & Technology, 2018.
[4] F. Marino, C. Alippi, S. Anastasi, and M. Roveri, "A deep learning approach to short-term load forecasting," Proceedings of IEEE International Conference, 2016.
[5] Scikit-learn Documentation. Available: https://scikit-learn.org
[6] TensorFlow Documentation. Available: https://www.tensorflow.org
[7] FastAPI Documentation. Available: https://fastapi.tiangolo.com
[8] MQTT Version 5.0 Specification. OASIS Standard, 2019.
[9] Firebase Documentation. Available: https://firebase.google.com/docs
[10] PostgreSQL Documentation. Available: https://www.postgresql.org/docs
[11] MDN Web Docs. HTML, CSS, and JavaScript references. Available: https://developer.mozilla.org
[12] UCI Machine Learning Repository. Individual household electric power consumption dataset. Available: https://archive.ics.uci.edu
[13] Dr. J. Narendra Babu, "Upcoming Strengths on Internet of Things," JARDCS, 2019.
[14] Dr. J. Narendra Babu, "Enhancement of RVM Using FPGA," JARDCS, 2019.
[15] Dr. J. Narendra Babu, "Brain Signal Processing," JARDCS, 2019.
[16] IEEE Xplore Digital Library. Smart grid and load forecasting research articles. Available: https://ieeexplore.ieee.org
[17] GeeksforGeeks. Machine Learning and Web Development Resources. Available: https://www.geeksforgeeks.org
How to cite this paper
@article{1718717,
author = {Dr. J. Narendra Babu, Dr. Deepak S Sakkari, Vilas Gowda R, Sumanth Kumar V C; Trijal G S, Yogeesh G; Vijay Bhadra M},
title = {Smart Energy Consumption Forecasting using IoT, Machine Learning and Web Application},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {12},
pages = {1510-1513},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718717.pdf},
abstract = {The Smart Energy Consumption Forecasting system is an intelligent energy analytics platform designed to monitor, analyze, and predict electricity usage in residential, commercial, and institutional environments. The proposed system integrates Internet of Things (IoT) sensors, cloud connectivity, machine learning models, and a responsive web application into a unified architecture for real-time energy management. Smart meters and environmental sensors continuously collect voltage, current, power factor, occupancy, temperature, and appliance-level usage data. These data streams are processed through a backend analytics engine, where machine learning algorithms such as Linear Regression, Random Forest Regressor, and Long Short-Term Memory (LSTM) networks are applied to forecast short-term and medium-term energy demand. The web application provides live dashboards, anomaly alerts, historical trend visualization, and consumption forecasting reports for users and administrators. Experimental observations indicate that the proposed platform improves energy visibility, supports proactive load balancing, and enhances decision-making for efficient power utilization. The system contributes toward sustainable smart building management by reducing energy wastage, improving forecast accuracy, and enabling intelligent, data-driven energy optimization.},
keywords = {Smart Energy, Energy Forecasting, Internet of Things, Machine Learning, Web Application, Smart Meter, Load Prediction, Sustainable Energy Management},
month = {June},
doi = {https://doi.org/10.64388/IREV9I12-1718717}
}