Adaptive Calibration Framework for Intelligent Meter Error Prediction Based on Machine Learning
DOI:
https://doi.org/10.4108/ew.12150Keywords:
Adaptive Calibration, Intelligent Meter, Measurement Error Prediction, Smart Metering Systems, Machine-Learning-Based Calibration, ACSO-WIForest, Anomaly Detection, Robust Principal Component Analysis, Swarm OptimizationAbstract
INTRODUCTION: Accurate measurement in intelligent metering systems is crucial for reliable energy monitoring, billing, and smart grid management. However, intelligent power meters often experience measurement inaccuracies due to environmental disturbances, hardware aging, and insufficient calibration mechanisms. These issues may lead to systematic errors and unreliable data in energy management systems. Therefore, improving the reliability and accuracy of intelligent metering devices through advanced data-driven techniques has become an important research focus.
OBJECTIVES: The main objective of this study is to develop an Adaptive Calibration Framework for Intelligent Meter Error Prediction using Machine Learning. The framework aims to detect abnormal data, predict measurement errors, and improve the accuracy and reliability of intelligent metering systems operating under diverse environmental conditions.
METHODS: The proposed framework integrates dynamic error detection, outlier filtering, and predictive modeling. Data collected from intelligent meters are first normalized using Min–Max scaling to ensure consistent training. Robust Principal Component Analysis (RPCA) with an improved distance function and adaptive thresholding based on the box plot method is used to detect and remove anomalous data. Subsequently, an Adaptive Cockroach Swarm Optimized Weighted Isolation Forest (ACSO-WIForest) model is employed to predict measurement errors by learning complex relationships between environmental stress factors and device performance.
RESULTS: The experimental evaluation of the proposed ACSO-WIForest model using datasets from intelligent meters in harsh environmental conditions shows its effectiveness. The model demonstrates strong predictive performance with a Mean Absolute Error (MAE) of 0.00156, Root Mean Square Error (RMSE) of 0.0040, and a low Mean Absolute Percentage Error (MAPE) of 0.221, indicating high prediction precision. With a coefficient of determination (R²) of 0.998, the model achieves excellent fit and reliability, significantly outperforming existing methods in intelligent meter error prediction.
CONCLUSION: The results indicate that machine learning–based adaptive calibration can significantly improve the accuracy, reliability, and self-correcting capability of intelligent metering systems. This approach provides a practical solution for enhancing trustworthy energy monitoring and management infrastructures
Downloads
References
[1] Fan Z, Shi L, Xi C, Wang H, Wang S, Wu G. Real-time power equipment meter recognition based on deep learning. IEEE Trans Instrum Meas. 2022;71:1–15.
[2] Saeedi R, Sadanandan SK, Srivastava AK, Davies KL, Gebremedhin AH. An adaptive machine learning framework for behind-the-meter load/PV disaggregation. IEEE Trans Ind Inform. 2021;17(10):7060–7069.
[3] Soluyanov YI, Fedotov AI, Akhmetshin AR, Soluyanov VI. Application of intelligent electricity metering systems for timely adjustment of standard values for electrical loads calculation. In: Proceedings of the 3rd International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE); 2021; Moscow, Russia. p.1–5.
[4] Abdulla N, Demirci M, Ozdemir S. Smart meter-based energy consumption forecasting for smart cities using adaptive federated learning. Sustain Energy Grids Netw. 2024;38:101342.
[5] Devanathan B, Kaushik K, Jayasurya G, Lakshmanan SA, Suyampulingam A. Smart metering for real-time power prediction, price forecasting and intelligent alerts in modern living spaces. In: Proceedings of the 5th International Conference on Expert Clouds and Applications (ICOECA); 2025. p.396–401.
[6] Almufareh MF, Humayun M, Ahmad Z, Khan A. An intelligent LoRaWAN-based IoT device for monitoring and control solutions in smart farming through anomaly detection integrated with unsupervised machine learning. IEEE Access. 2024;12:119072–119086.
[7] Rind YM, Raza MH, Zubair M, Mehmood MQ, Massoud Y. Smart energy meters for smart grids: An Internet of Things perspective. Energies. 2023;16(4):1974.
[8] Ramos Ruiz G, Fernandez Bandera C. Validation of calibrated energy models: Common errors. Energies. 2017;10(10):1587.
[9] Qu Z, Jiao Y, Li H, Chen Q, Zhu Y, Wei W. An online accuracy evaluation method for smart electricity meter calibration devices based on mutual correlations of calibration data. IEEE Trans Instrum Meas. 2024.
[10] Wang Q, Li H, Wang H, Zhang J, Fu J. A remote calibration device using edge intelligence. Sensors. 2022;22(1):322.
[11] Ma L, Meng Z, Teng Z, Tang Q. A measurement error prediction framework for smart meters under extreme natural environment stresses. Electr Power Syst Res. 2023;218:109192.
[12] Ma J, Teng Z, Tang Q, Guo Z, Kang L, Wang Q, Li N, Peretto L. A novel multisource feature fusion framework for measurement error prediction of smart electricity meters. IEEE Sens J. 2023;23(17):19571–19581.
[13] Zhang B, Xia X, He C, Kang W, Zhang J. Examining performance calibration in smart power system electricity metering based on environmental perception attention LSTM network. Front Energy Res. 2024;12:1405725.
[14] Ma L, Meng Z, Teng Z, Qiu W. A reliability evaluation framework for smart meters based on AGG-ARIMA and PFR. Meas Sci Technol. 2022;33(4):045006.
[15] Ma L, Teng Z, Tang Q, Wan Z, Li N, Meng Z. Measurement error prediction-based reliability assessment framework for electric metering devices under harsh natural environments. Measurement. 2024;232:114481.
[16] Tong X, Ma J, Ma L, Yan S, Tang Q, Teng Z, Cheng D. A novel prediction method for smart meter error using multi-view convolutional neural network. IEEE Sens J. 2024.
[17] Xia T, Liu C, Lei M, Xia S, Li D, Ming D. Measurement error estimation for distributed smart meters through a modified BP neural network. Front Energy Res. 2022;10:928681.
[18] Ma J, Teng Z, Tang Q, Qiu W, Yang Y, Duan J. Measurement error prediction of power metering equipment using improved local outlier factor and kernel support vector regression. IEEE Trans Ind Electron. 2022;69(9):9575–9585.
[19] Deligiannis P, Koutroubinas S, Koronias G. Predicting energy consumption through machine learning using a smart-metering architecture. IEEE Potentials. 2019;38(2):29–34.
[20] Hong Y. Nonlinear modeling of measurement errors in gateway energy meters. Meas Sensors. 2024;35:101286.
[21] Oprea SV, Bâra A. Machine learning algorithms for short-term load forecast in residential buildings using smart meters, sensors and big data solutions. IEEE Access. 2019;7:177874–177889.
[22] Ma J, Teng Z, Tang Q, Qiu W, Yang Y. Measurement error assessment for smart electricity meters under extreme natural environmental stresses. IEEE Trans Ind Inform. 2022;18(6):3905–3914.
[23] Liu F, Huang H. Smart meter error estimation in topological low-voltage energy systems. IEEE Access. 2024.
[24] He C, Xia X, Zhang B, Kang W, Zhang J, Chen H. Analyzing adjustment and verification errors in electric metering devices for smart power systems considering multiple environmental factors. AIP Adv. 2024;14(12).
[25] Thirusubramanian G. Machine learning-driven AI for financial fraud detection in IoT environments. Int J HRM Organ Behav. 2021;9(4):9–25.
[26] Jin X. Multi-source collaborative optimization scheduling technology for new energy microgrid based on improved particle swarm algorithm. EAI Endorsed Trans Energy Web. 2024;12.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Chunguang Wang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
