Time and Frequency Domain-based Anomaly Detection in Smart Meter Data for Distribution Network Studies
Petar Labura, Tomislav Antic, Tomislav Capuder
TL;DR
The paper tackles data quality in smart-meter–driven distribution studies by distinguishing point and contextual anomalies that affect LV network analyses. It introduces a dual approach: Isolation Forest for time-domain point anomalies and an FFT-based low-pass filter for frequency-domain contextual anomalies, validated on real-world Croatian LV data. The results show robust improvements in downstream voltage predictions and demonstrate that the framework outperforms conventional anomaly detectors, especially for contextual anomalies. This work offers a practical, time- and frequency-domain anomaly-detection framework that DSOs can deploy to improve the reliability of data-driven network studies.
Abstract
The widespread integration of new technologies in low-voltage distribution networks on the consumer side creates the need for distribution system operators to perform advanced real-time calculations to estimate network conditions. In recent years, data-driven models based on machine learning and big data analysis have emerged for calculation purposes, leveraging the information available in large datasets obtained from smart meters and other advanced measurement infrastructure. However, existing data-driven algorithms do not take into account the quality of data collected from smart meters. They lack built-in anomaly detection mechanisms and fail to differentiate anomalies based on whether the value or context of anomalous data instances deviates from the norm. This paper focuses on methods for detecting and mitigating the impact of anomalies on the consumption of active and reactive power datasets. It proposes an anomaly detection framework based on the Isolation Forest machine learning algorithm and Fast Fourier Transform filtering that works in both the time and frequency domain and is unaffected by point anomalies or contextual anomalies of the power consumption data. The importance of integrating anomaly detection methods is demonstrated in the analysis important for distribution networks with a high share of smart meters.