Acquiring Better Load Estimates by Combining Anomaly and Change Point Detection in Power Grid Time-series Measurements

TL;DR

This paper introduces a novel method combining anomaly and change point detection to improve load estimation accuracy in power grid systems, emphasizing interpretability and robustness for critical infrastructure planning.

Contribution

The paper presents a new sequential ensemble approach for anomaly and change point detection that enhances load estimation accuracy and interpretability in power grid measurements.

Findings

Approximately 90% of load estimates are within 10% error margin.

The proposed method outperforms baseline filtering techniques.

Only one significant failure observed in test set estimates.

Abstract

In this paper we present novel methodology for automatic anomaly and switch event filtering to improve load estimation in power grid systems. By leveraging unsupervised methods with supervised optimization, our approach prioritizes interpretability while ensuring robust and generalizable performance on unseen data. Through experimentation, a combination of binary segmentation for change point detection and statistical process control for anomaly detection emerges as the most effective strategy, specifically when ensembled in a novel sequential manner. Results indicate the clear wasted potential when filtering is not applied. The automatic load estimation is also fairly accurate, with approximately 90% of estimates falling within a 10% error margin, with only a single significant failure in both the minimum and maximum load estimates across 60 measurements in the test set. Our methodology's interpretability makes it particularly suitable for critical infrastructure planning, thereby enhancing decision-making processes.