Remote in-service detection of energy metering anomalies and identification of faulty meters remains an active challenge due to the limitations of existing methods. Traditional energy conservation-based techniques require readings from all consumers’ meters and are not applicable in the case of partial deployment of smart meters in the distribution grid. This paper presents two novel methods for remote estimation of active power measurement error of individual smart energy meter that utilizes consumer-side power events. The first approach, Inverse Problem Solution (IPS), utilizes feedforward neural network model trained under reference conditions for the prediction of the expected power change at the location of the sum meter. The power measurement gain error of the consumer meter is estimated by minimizing the difference between the predicted power change and the power change measured by the sum meter. The second approach, Electrical Data Augmentation (EDA), utilizes feature engineering with injection of different levels of gain error of meter power measurement to create dataset for the training of a random forest regression model dedicated to predict the gain error directly. Both techniques were examined using synthetic datasets generated from power flow simulation of low-voltage distribution grid. It is shown that both methods achieve sub-1% root mean square error (RMSE) of estimation of power measurement gain error, with EDA demonstrating slightly superior performance in terms of meter error prediction RMSE and robustness to grid technical losses variations.
This research targets prediction of power consumption change (PCC) in the branch of electrical distribution grid between a sum meter and consumer meter in response to consumer load change. The problem is relevant for power preservation law-based event-driven methods aiming for detection of anomalies like meter errors, electricity thefts, etc. The PCC in the branch is due to the change of technical (wiring) losses as well as change of power consumption of loads connected to the same distribution branch. Using synthesized dataset set a data-driven model is built to predict PCC in the branch. Model performance is assessed using root mean squared error (RMSE), mean absolute, and mean relative error, together with their standard deviations. The preliminary experimental verification using a test bed confirmed the potential of the method. The accuracy of the PCC in the branch prediction is influenced by the systematic error of the meters. Therefore, the error of the consumer meter and the PCC in the branch cannot be evaluated separately. It was observed that the absolute error of the estimate of power measurement gain error was observed to be within ±0.3% and the relative error of PCC in the branch prediction was within ±10%.
Smart energy meters are widely deployed in modern distribution networks, extending their role beyond revenue billing to real-time monitoring and data-driven smart city applications. However, conventional legal metrology frameworks rely on periodic recalibration and are not intended for the detection of accuracy drift or unexpected malfunctions between scheduled inspections. In scientific publications, various techniques for remote smart meters’ error surveillance are presented, but experimental verification on real distribution network data remains limited. The objective of this study is to experimentally verify two previously proposed power event-driven methods for remote estimation of active power measurement error in individual consumer meters, using a feeder-level sum meter as a reference instrument. One-second resolution electrical readings were collected from a real low-voltage distribution branch using ESP32-based local adapters communicating via MQTT over Wi-Fi, with SNTP-based clock synchronization for power event correlation. Under optimized detection parameters, the linear regression method achieved 0.20% RMSE and 0.75% maximum absolute error, and the neural network method 0.09% RMSE and 0.31%, confirming suitability for Class 1 m accuracy surveillance. Feasibility analysis of three MQTT-based deployment scenarios demonstrates that binary encoding limits local adapter buffers to 2.8 kB and worst-case daily channel demand to 2000 kB, confirming the practical viability of the proposed architecture.