Volume no :
10 |
Issue no :
01
Article Type :
Google Scholar
Author :
P.N.Periyasamy, Abhiniti S, Divya Bharathi S , Mohamed Sulthan Ashar, mohamed kaiyum
Published Date :
08 - April - 2026
Publisher :
Journal of Artificial Intelligence and Cyber Security (JAICS)
Page No: 1 - 6
Abstract : The rapid expansion of smart grid infrastructure, renewable energy sources, and IoT-enabled devices has created an urgent demand for intelligent and adaptive energy management. The AI-Powered Energy Management Intelligence System (EMS-AI) is proposed to address this challenge by leveraging artificial intelligence, deep learning, and real-time data analytics to optimize energy consumption across residential, commercial, and industrial environments. The system integrates user behavioral data, device usage patterns, environmental parameters, and grid signals to generate dynamic, personalized energy schedules and recommendations. A deep learning model based on Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) is used for short-term and long-term energy load forecasting. Large Language Models (LLMs) are utilized through APIs to generate natural-language energy-saving recommendations and adaptive scheduling plans. Additionally, the platform supports real-time anomaly detection, demand response optimization, renewable energy integration, and carbon footprint monitoring via an interactive analytics dashboard. By combining AI-based prediction, intelligent recommendation, and continuous monitoring, EMS-AI aims to reduce energy waste, lower electricity costs, and support sustainable energy goals.
Keyword Artificial Intelligence (AI), Energy Management System, Deep Learning, LSTM, Load Forecasting, Smart Grid, Demand Response, Anomaly Detection, Renewable Energy Integration, IoT Devices, Carbon Footprint, Real-Time Analytics, Personalized Recommendations.
Reference:

1.
Batra, N., Kelly, J., Parson, O., Dutta, H., Knottenbelt, W., Rogers, A., Singh, A. and Srivastava, M. (2014) ‘NILMTK: An Open Source Toolkit for Non-Intrusive Load Monitoring’, Proceedings of the 5th International Conference on Future Energy Systems (ACM e-Energy).
2.
Kong, W., Dong, Z.Y., Jia, Y., Hill, D.J., Xu, Y. and Zhang, Y. (2019) ‘Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network’, IEEE Transactions on Smart Grid.
3.
Cano, A., Garnica-Caparrós, M. and Menchón-Lara, R.M. (2021) ‘Comparative Analysis of Python Web Frameworks for Data Visualisation Applications’, Proceedings of the International Conference on Data Science and Analytics.

4.
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H. and Zhang, W. (2021) ‘Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting’, Proceedings of the AAAI Conference on Artificial Intelligence.
5.
Kelly, J. and Knottenbelt, W. (2015) ‘Neural NILM: Deep Neural Networks Applied to Energy Disaggregation’, Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys).
6.
Batra, N., et al. (2019) ‘NILMTK v0.4: A Novel Dataset and Reproducible Benchmarking of Energy Disaggregation Systems’, Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities and Transportation.
7.
Lahouar, A. and Ben Hadj Slama, J. (2015) ‘Day-Ahead Load Forecast Using Random Forest and Expert Input Selection’, Energy Conversion and Management.
8.
Malhotra, P., Vig, L., Shroff, G. and Agarwal, P. (2016) ‘LSTM-Based Encoder-Decoder for Multi-Sensor Anomaly Detection’, Proceedings of the Anomaly Detection Workshop at the 33rd International Conference on Machine Learning.
9.
Negi, G. and Bhatt, U. (2020) ‘Anomaly Detection in Smart Meter Data: A Survey’, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering.
10.
Schimansky, T. (2022) CustomTkinter: A Modern and Customisable Python UI Library