Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Acquiring Better Load Estimates by Combining Anomaly and Change Point Detection in Power Grid Time-series Measurements (2405.16164v3)

Published 25 May 2024 in cs.LG, cs.AI, stat.AP, and stat.ML

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. A comparison of energy transition governance in Germany, the Netherlands and the United Kingdom, Sustainability 6 (2014) 1129–1152.
  2. Integration of HTS cables in the future grid of the Netherlands, Physics Procedia 36 (2012) 890–893.
  3. Fulfilling the electricity demand of electric vehicles in the long term future: An evaluation of centralized and decentralized power supply systems, Applied energy 107 (2013) 33–51.
  4. G. A. Pagani, M. Aiello, Towards decentralization: A topological investigation of the medium and low voltage grids, IEEE Transactions on Smart Grid 2 (2011) 538–547.
  5. Heat pumps in the existing Dutch housing stock: An assessment of its technological innovation system, Sustainable Energy Technologies and Assessments 44 (2021) 101064.
  6. Indications for a changing electricity demand pattern: The temperature dependence of electricity demand in the Netherlands, Energy Policy 37 (2009) 1542–1551.
  7. Grid impact of electric vehicle fast charging stations: Trends, standards, issues and mitigation measures-an overview, IEEE Open Journal of Power Electronics 2 (2021) 56–74.
  8. How much charging infrastructure do electric vehicles need? a review of the evidence and international comparison, Transportation research part D: transport and environment 77 (2019) 224–242.
  9. Sizing and applications of battery energy storage technologies in smart grid system: A review, Journal of Renewable and Sustainable Energy 11 (2019).
  10. Efficient assessment of electricity distribution network adequacy with the cross-entropy method, in: 2021 IEEE Madrid PowerTech, IEEE, 2021, pp. 1–6.
  11. Time series anomaly detection for smart grids: A survey, in: 2021 IEEE Electrical Power and Energy Conference (EPEC), IEEE, 2021, pp. 125–130.
  12. A passive islanding detection method based on k-means clustering and emd of reactive power signal, Sustainable Energy, Grids and Networks 23 (2020) 100377.
  13. Change point detection in recent hydropower generation in Romania, in: IOP Conference Series: Materials Science and Engineering, volume 1032, IOP Publishing, 2021, p. 012045.
  14. X. Wang, S.-H. Ahn, Real-time prediction and anomaly detection of electrical load in a residential community, Applied Energy 259 (2020) 114145.
  15. A real-time electrical load forecasting and unsupervised anomaly detection framework, Applied Energy 330 (2023) 120279.
  16. A comparative study of clustering techniques for electrical load pattern segmentation, Renewable and Sustainable Energy Reviews 120 (2020) 109628.
  17. Maximum PV generation estimation method for residential low voltage feeders, Sustainable Energy, Grids and Networks 7 (2016) 58–69.
  18. Signal processing on graphs for estimating load current variability in feeders with high integration of distributed generation, Sustainable Energy, Grids and Networks 34 (2023) 101032.
  19. Efficient deep generative model for short-term household load forecasting using non-intrusive load monitoring, Sustainable Energy, Grids and Networks 34 (2023) 101006.
  20. Disaggregating solar generation from feeder-level measurements, Sustainable Energy, Grids and Networks 13 (2018) 112–121.
  21. Anomaly detection and classification in power system state estimation: Combining model-based and data-driven methods, Sustainable Energy, Grids and Networks 35 (2023) 101116.
  22. Creating bottom up load profiles using disaggregation, clustering and supervised machine learning on large smart meter dataset, in: 27th International Conference on Electricity Distribution (CIRED 2023), volume 2023, IET, 2023, pp. 3503–3507.
  23. D. Chen, D. Irwin, Sundance: Black-box behind-the-meter solar disaggregation, in: Proceedings of the eighth international conference on future energy systems, 2017, pp. 45–55.
  24. J. MacQueen, et al., Some methods for classification and analysis of multivariate observations, in: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, Oakland, CA, USA, 1967, pp. 281–297.
  25. S. Lloyd, Least squares quantization in PCM, IEEE transactions on information theory 28 (1982) 129–137.
  26. T. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, in: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794.
  27. Isolation forest, in: Eighth IEEE International Conference on Data Mining, IEEE, 2008, pp. 413–422.
  28. A. J. Scott, M. Knott, A cluster analysis method for grouping means in the analysis of variance, Biometrics (1974) 507–512.
  29. J. Bai, Estimating multiple breaks one at a time, Econometric Theory 13 (1997) 315–352.
  30. G. J. Van den Burg, C. K. Williams, An evaluation of change point detection algorithms, arXiv preprint arXiv:2003.06222 (2020).
  31. ClaSP - time series segmentation, in: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, CIKM ’21, Association for Computing Machinery, New York, NY, USA, 2021, p. 1578–1587. URL: https://doi.org/10.1145/3459637.3482240. doi:doi:10.1145/3459637.3482240.
  32. ClaSP: Parameter-free time series segmentation, Data Mining and Knowledge Discovery (2023).
  33. Array programming with NumPy, Nature 585 (2020) 357–362. URL: https://doi.org/10.1038/s41586-020-2649-2. doi:doi:10.1038/s41586-020-2649-2.
  34. Ruptures: Change point detection in Python, arXiv preprint arXiv:1801.00826 (2018).
  35. Scikit-learn: Machine learning in Python, Journal of Machine Learning Research 12 (2011) 2825–2830.
  36. M. L. Waskom, Seaborn: Statistical data visualization, Journal of Open Source Software 6 (2021) 3021. URL: https://doi.org/10.21105/joss.03021. doi:doi:10.21105/joss.03021.
  37. J. D. Hunter, Matplotlib: A 2d graphics environment, Computing in Science & Engineering 9 (2007) 90–95. doi:doi:10.1109/MCSE.2007.55.
  38. A survey on anomaly detection for technical systems using LSTM networks, Computers in Industry 131 (2021) 103498.
  39. S. J. Taylor, B. Letham, Forecasting at scale, The American Statistician 72 (2018) 37–45.
  40. R. Wu, E. J. Keogh, Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress, IEEE transactions on knowledge and data engineering 35 (2021) 2421–2429.

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets