IoT‐Enabled Smart Metering With Transfer Learning for Optimized Energy Load Forecasting.
Saved in:
| Title: | IoT‐Enabled Smart Metering With Transfer Learning for Optimized Energy Load Forecasting. |
|---|---|
| Authors: | Ahmed, Muhammad Maroof1 (AUTHOR), Ditta, Allah2 (AUTHOR), Siddiqa, Ayesha3 (AUTHOR), Wazir, Perwasha4 (AUTHOR), Shah, Asghar Ali5 (AUTHOR) asghar.ali.shah@kateb.edu.af, Adnan, Khan Muhammad6 (AUTHOR) adnan@gachon.ac.kr, Du, Cheng (AUTHOR) cdu@wiley.com |
| Source: | International Journal of Energy Research. 7/8/2026, Vol. 2026, p1-13. 13p. |
| Subjects: | Smart meters, Energy consumption forecasting, Real-time computing, Energy consumption, Energy management, Machine learning, Internet of things |
| Abstract: | Rapid urbanization and increasing electricity demand require an enhanced energy management system (EMS) to ensure better use of limited energy resources. Smart energy metering systems play a vital role in monitoring power consumption and forecasting future energy demand. Weather conditions, including temperature, humidity, and wind speed, significantly influence energy consumption patterns by affecting heating, cooling, ventilation, and appliance usage. This study aims to develop an IoT‐enabled smart energy meter integrated with a transfer learning (TL)‐based forecasting model using real‐time electrical and weather parameters, including voltage, current, power, frequency, power factor, energy consumption, temperature, humidity, wind speed, and atmospheric pressure. A real‐time dataset was collected over 3 months and analyzed using random forest (RF), support vector machine (SVM), artificial neural network (ANN), long short‐term memory (LSTM), and recurrent neural network (RNN) models, where the RNN achieved the best forecasting performance with minimum prediction errors. System performance was evaluated, including mean absolute error (MAE), mean square error (MSE), root MSE (RMSE), and mean absolute percentage error (MAPE). Experimental results demonstrate the effectiveness of the proposed method, achieving 2.18%, 5.45%, 2.34%, 14.43%, and an accuracy performance (AP) of 85%. These findings highlight the system's accuracy and its potential to significantly enhance energy management, reduce unnecessary consumption, and provide real‐time insights to consumers. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Energy Research is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| Abstract: | Rapid urbanization and increasing electricity demand require an enhanced energy management system (EMS) to ensure better use of limited energy resources. Smart energy metering systems play a vital role in monitoring power consumption and forecasting future energy demand. Weather conditions, including temperature, humidity, and wind speed, significantly influence energy consumption patterns by affecting heating, cooling, ventilation, and appliance usage. This study aims to develop an IoT‐enabled smart energy meter integrated with a transfer learning (TL)‐based forecasting model using real‐time electrical and weather parameters, including voltage, current, power, frequency, power factor, energy consumption, temperature, humidity, wind speed, and atmospheric pressure. A real‐time dataset was collected over 3 months and analyzed using random forest (RF), support vector machine (SVM), artificial neural network (ANN), long short‐term memory (LSTM), and recurrent neural network (RNN) models, where the RNN achieved the best forecasting performance with minimum prediction errors. System performance was evaluated, including mean absolute error (MAE), mean square error (MSE), root MSE (RMSE), and mean absolute percentage error (MAPE). Experimental results demonstrate the effectiveness of the proposed method, achieving 2.18%, 5.45%, 2.34%, 14.43%, and an accuracy performance (AP) of 85%. These findings highlight the system's accuracy and its potential to significantly enhance energy management, reduce unnecessary consumption, and provide real‐time insights to consumers. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 0363907X |
| DOI: | 10.1155/er/1719445 |
