Advanced AI based Energy Monitoring and Demand Prediction with Theft Detection

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 17 | 01 | Page :
    By

    Manikandan S,

  • Manojkumar T,

  • Adhithya Varman R,

  • Sreedharan P,

  • Karthick S,

  1. Assistant Professor, Department of ETE Karpagam College of Engineering Coimbatore, Tamil Nadu, India
  2. Associate Professor, Department of ETE Karpagam College of Engineering Coimbatore, Tamil Nadu, India
  3. Student, Department of ETE Karpagam College of Engineering Coimbatore, Tamil Nadu, India
  4. Student, Department of ETE Karpagam College of Engineering Coimbatore, Tamil Nadu, India
  5. Student, Department of ETE Karpagam College of Engineering Coimbatore, Tamil Nadu, India

Abstract

This paper presents a study on an AI-based energy management system, which is designed for real-time monitoring of energy consumption for theft detection and energy demand prediction. Our energy management system has voltage and current sensors for energy consumption measurement and provides real- time data on voltage (V), current (mA), and energy units. We have implemented Machine Learning algorithm SVM to improve the process of theft detection by identifying anomalies and classifying the status of each anomaly into either “Normal” or “Theft” on the monitoring interface. A machine learning approach based on Support Vector Machines (SVM) is used to improve the identification of electricity theft and anomalous usage trends. Each detected event is classified as either “Normal” or “Theft” by the algorithm, which examines real-time consumption data to find anomalies. The results are shown on a special monitoring interface. Authorized staff are given the capacity to remotely manage the power supply using a NodeMCU microcontroller in response to suspicious activity, enabling the system to turn the power ON or OFF as a preventive and remedial action. Additionally, the NodeMCU ensures dependable data storage, retrieval, and system scalability by facilitating smooth connectivity with the cloud infrastructure. The authorized person can remotely switch ON/OFF the power supply using a NodeMCU, which further sends data to the Cloud for real-time monitoring and retrieval. The LSTM algorithm is incorporated in the system to examine consumption trends in the future for predicting energy usages. The cloud infrastructure provides persistent data availability and access, thereby enabling real-time decision-making and productivity enhancement. Experimental results verify the system for energy consumption monitoring, theft prevention, and demand forecast, while further prospects are opened for energy efficiency and energy loss reduction.

Keywords: Energy Management, theft detection, demand prediction, SVM (Support Vector Machine), LSTM (Long-Short term memory).

How to cite this article:
Manikandan S, Manojkumar T, Adhithya Varman R, Sreedharan P, Karthick S. Advanced AI based Energy Monitoring and Demand Prediction with Theft Detection. Journal of Alternate Energy Sources & Technologies. 2026; 17(01):-.
How to cite this URL:
Manikandan S, Manojkumar T, Adhithya Varman R, Sreedharan P, Karthick S. Advanced AI based Energy Monitoring and Demand Prediction with Theft Detection. Journal of Alternate Energy Sources & Technologies. 2026; 17(01):-. Available from: https://journals.stmjournals.com/joaest/article=2026/view=238806


References

  1. Wang X, Wang H, Bhandari B, Cheng L. AI-empowered methods for smart energy consumption: A review of load forecasting, anomaly detection and demand response. International Journal of Precision Engineering and Manufacturing-Green Technology. 2024 May;11(3):963-93.
  2. Abilesh KS, Naresh B, Maithili P. Revolutionizing Energy Management System with Machine Learning Based Energy Demand Prediction and Theft Detection. In2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS) 2024 Mar 14 (Vol. 1, pp. 765-770). IEEE.
  3. Žarković M, Dobrić G. Artificial intelligence for energy theft detection in distribution networks. Energies. 2024 Mar 26;17(7):1580.
  4. Shahzadi N, Javaid N, Akbar M, Aldegheishem A, Alrajeh N, Bouk SH. A novel data driven approach for combating energy theft in urbanized smart grids using artificial intelligence. Expert Systems with Applications. 2024 Nov 1;253:124182.
  5. Liu K, Liu A, Ma X, Jia X. Artificial Intelligence-based Real-Time Electricity Metering Data Analysis and its Application to Anti-Theft Actions. International Journal of Advanced Computer Science & Applications. 2024 Jun 1;15(6).
  6. Anbarasu L, Abishake S, Sakthivel A, Saravanan A, Vignesh R. AI Based System for Real-Time Electric Theft Identification. InIntelligent and Sustainable Power and Energy Systems 2025 Jul 23 (pp. 286-293). CRC Press.
  7. Dash SK, Roccotelli M, Khansama RR, Fanti MP, Mangini AM. Long term household electricity demand forecasting based on RNN-GBRT model and a novel energy theft detection method. Applied Sciences. 2021 Sep 16;11(18):8612.
  8. Kim S, Sun Y, Lee S, Seon J, Hwang B, Kim J, Kim J, Kim K, Kim J. Data-driven approaches for energy theft detection: A comprehensive review. Energies. 2024 Jun 20;17(12):3057.
  9. Khan MA, Saleh AM, Waseem M, Sajjad IA. Artificial intelligence enabled demand response: Prospects and challenges in smart grid environment. Ieee Access. 2022 Dec 21;11:1477-505.
  10. Aldegheishem A, Anwar M, Javaid N, Alrajeh N, Shafiq M, Ahmed H. Towards sustainable energy efficiency with intelligent electricity theft detection in smart grids emphasising enhanced neural networks. IEEE Access. 2021 Feb 2;9:25036- 61. .
  11. Tanwar S, Kumari A, Vekaria D, Raboaca MS, Alqahtani F, Tolba A, Neagu BC, Sharma R. GrAb: a deep learning-based data-driven analytics scheme for energy theft detection. Sensors. 2022 May 26;22(11):4048.
  12. Zheng K, Chen Q, Wang Y, Kang C, Xia Q. A novel combined data-driven approach for electricity theft detection. IEEE Transactions on Industrial Informatics. 2018 Oct 4;15(3):1809-19.
  13. Saad M, Tariq MF, Nawaz A, Jamal MY. Theft detection based GSM prepaid electricity system. In2017 3rd IEEE International Conference on Control Science and Systems Engineering (ICCSSE) 2017 Aug 17 (pp. 435-438). IEEE.
  14. Mutupe RM, Osuri SO, Lencwe MJ, Chowdhury SD. 1 Electricity theft detection system with RF communication between distribution and customer usage. In2017 IEEE PES PowerAfrica 2017 Jun 27 (pp. 566-572). IEEE.
  15. Jiang R, Lu R, Wang Y, Luo J, Shen C, Shen X. Energy-theft detection issues for advanced metering infrastructure in smart grid. Tsinghua Science and Technology. 2014 Apr 15;19(2):105- 20.
  16. Sharma, R. and Patel, K. (2021) ‘Energy Demand Prediction Using Long Short-Term Memory Networks’, Journal of Renewable Energy Systems, Vol. 39, No. 2, pp. 215-222.
  17. Yip SC, Wong K, Hew WP, Gan MT, Phan RC, Tan SW. Detection of energy theft and defective smart meters in smart grids using linear regression. International Journal of Electrical Power & Energy Systems. 2017 Oct 1;91:230-40.
Ahead of Print Subscription Original Research
Volume 17
01
Received 22/11/2025
Accepted 11/12/2025
Published 12/03/2026
Publication Time 110 Days
53

Login


My IP

PlumX Metrics