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

arXiv: https://arxiv.org/abs/2405.16164 · HTML: https://mlsanity.com/paper/2405.16164/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 47 references that are in the map.
- First posted on arXiv 25 May 2024.

## Builds on (most cited first, 8 of 8)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [An Evaluation of Change Point Detection Algorithms](https://mlsanity.com/paper/2003.06222/) (2020)
- [A Survey on Anomaly Detection for Technical Systems using LSTM Networks](https://mlsanity.com/paper/2105.13810/) (2021)
- [ClaSP -- Parameter-free Time Series Segmentation](https://mlsanity.com/paper/2207.13987/) (2022)
- [Unsupervised anomaly detection algorithms on real-world data: how many do we need?](https://mlsanity.com/paper/2305.00735/) (2023)
- [Time Series Anomaly Detection for Smart Grids: A Survey](https://mlsanity.com/paper/2107.08835/) (2021)
- [Efficient Assessment of Electricity Distribution Network Adequacy with the Cross-Entropy Method](https://mlsanity.com/paper/2011.14937/) (2020)

## Abstract (arXiv)

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.