Analysis of Electrical Load Anomalies in Educational Buildings Using Isolation Forest and PCA for Dimensionality Reduction
Article Sidebar
Main Article Content
Abstract
This study utilizes Principal Component Analysis (PCA) and Isolation Forest to analyze energy data from the Industrial Technician School Building at the College of Industrial Technology and Management, Rajamangala University of Technology Srivijaya (Phase A, Phase B, Phase C). The analysis begins with data standardization and PCA to reduce the dimensionality of the data to two components, which helps in better understanding the structure and variance of the data. The results show that Principal Component 1 (PC1) and Principal Component 2 (PC2) explain a significant portion of the data variance, with PC1 being the most influential component in explaining the power data. Furthermore, Isolation Forest is used to detect outliers by calculating the Anomaly Score. The distribution of anomaly scores reveals periods in the energy data that may indicate abnormalities in the electrical system. This outlier detection helps in identifying potential issues in the system more quickly. The study demonstrates that Isolation Forest can effectively detect outliers, making it an important tool for identifying anomalies and reducing the risk of system failures. The combination of PCA and Isolation Forest enhances the ability to analyze and manage energy in the electrical system, enabling the detection and resolution of issues during specific time periods efficiently. This is crucial for maintaining and improving the stability of the electrical system.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content within the published articles, including images and tables, is copyrighted by Rajamangala University of Technology Rattanakosin. Any use of the article's content, text, ideas, images, or tables for commercial purposes in various formats requires permission from the journal's editorial board.
Rajamangala University of Technology Rattanakosin permits the use and dissemination of article files under the condition that proper attribution to the journal is provided and the content is not used for commercial purposes.
The opinions and views expressed in the articles are solely those of the respective authors and are not associated with Rajamangala University of Technology Rattanakosin or other faculty members in the university. The authors bear full responsibility for the content of their articles, including any errors, and are responsible for the content and editorial review. The editorial board is not responsible for the content or views expressed in the articles.
References
Lam, J. C., Wan, K. K. W., Cheung, K. L., & Yang, L. (2008). Principal component analysis of electricity use in office buildings. Energy and Buildings, 40(5), 828–836. https://doi.org/10.1016/j.enbuild.2007.06.001
Pang, G., Shen, C., Cao, L., & van den Hengel, A. (2021). Deep learning for anomaly detection: A review. ACM Computing Surveys, 54(2), 1–38. https://doi.org/10.1145/3439950
Fan, S., & Hyndman, R. J. (2012). Short-term load forecasting based on a semi-parametric additive model. IEEE Transactions on Power Systems. 27(1), 134–141. https://doi.org/10.1109/TPWRS.2011.2162082
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (ICDM), 413–422. https://doi.org/10.1109/ICDM.2008.17
Koch, C., & Hirth, L. (2019). Short-term electricity trading for system balancing: An empirical analysis of the role of intraday trading in balancing Germany's electricity system, Renewable and Sustainable Energy Reviews, 113, 109275. https://doi.org/10.1016/j.rser.2019.109275
Cook, A. A., Mısırlı, G., & Fan, Z. (2020). Anomaly detection for IoT time-series data: A survey. IEEE Internet of Things Journal, 7(7), https://doi.org/10.1109/JIOT.2019.2958185.
Amigo, P., Cea-Echenique, S., & Feijoo, F. (2021). A two stage cap-and-trade model with allowance re-trading and capacity investment: The case of the Chilean NDC targets. Energy, 224,120129. https://doi.org/10.1016/j.energy.2021.120129
Zhu, L., & Chen, J. (2019). Development of energy efficiency principal component analysis model for factor extraction and efficiency evaluation in large-scale chemical processes. International Journal of Energy Research, 43(2), 814–828. https://doi.org/10.1002/er.4312
Zhang, L., Ge, R., & Chai, J. (2019). Prediction of China’s energy consumption based on robust principal component analysis and PSO-LSSVM optimized by the Tabu search algorithm. Energies, 12(1), 196. https://doi.org/10.3390/en12010196
Beretta, D., Grillo, S., Pigoli, D., Bionda, E., Bossi, C., & Tornelli, C. (2019). Functional principal component analysis as a versatile technique to understand and predict the electric consumption patterns. arXiv preprint arXiv:1909.05237, 1-8. https://arxiv.org/abs/1909.05237
