Abstract
As electric energy demand continues to rise, understanding electricity consumption habits and promptly detecting abnormal usage patterns are crucial steps in reducing energy waste. This study introduces a novel anomaly detection approach that identifies out-of-the-ordinary patterns in energy consumption, leveraging state-of-the-art deep learning techniques on relevant data and more specifically, a transformer-based architecture. By utilizing the proposed methodology, the energy demand is classified either as expected or unexpected, based on the discovered energy patterns. The latter cases can then be further examined in order to find the potential causes for such anomalies. In this respect, the proposed architecture can be used to gain insight into electricity consumption patterns and actively work towards reducing energy waste.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bontemps, Loïc., Cao, Van Loi, McDermott, James, Le-Khac, Nhien-An.: Collective anomaly detection based on long short-term memory recurrent neural networks. In: Dang, Tran Khanh, Wagner, Roland, Küng, Josef, Thoai, Nam, Takizawa, Makoto, Neuhold, Erich (eds.) FDSE 2016. LNCS, vol. 10018, pp. 141–152. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48057-2_9
Lee, T.J., Gottschlich, J., Tatbul, N., Metcalf, E., Zdonik, S.: Greenhouse: a zero-positive machine learning system for time-series anomaly detection (2018)
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., Shroff, G.: LSTM-based encoder-decoder for multi-sensor anomaly detection (2016)
Malhotra, P., Vig, L., Shroff, G., Agarwal, P., et al.: Long short term memory networks for anomaly detection in time series. In: ESANN, vol. 2015, p. 89 (2015)
Wu, H., Xu, J., Wang, J., Long, M.: Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. CoRR abs/2106.13008 (2021). https://arxiv.org/abs/2106.13008
Wu, J., Zeng, W., Yan, F.: Hierarchical temporal memory method for time-series-based anomaly detection. Neurocomputing 273, 535–546 (2018). https://doi.org/10.1016/j.neucom.2017.08.026
Xie, X., Wu, D., Liu, S., Li, R.: IoT data analytics using deep learning (2021)
Zhu, L., Laptev, N.: Deep and confident prediction for time series at Uber. In: 2017 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 103–110 (2017). https://doi.org/10.1109/ICDMW.2017.19
Keogh, E., Lin, J., Fu, A.: Hot sax: efficiently finding the most unusual time series subsequence. In: Fifth IEEE International Conference on Data Mining (ICDM’05), pp. 8–pp (2005). https://doi.org/10.1109/ICDM.2005.79
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 IFIP International Federation for Information Processing
About this paper
Cite this paper
Karpontinis, D., Alexandridis, G. (2024). Transformer-Based Anomaly Detection in Energy Consumption Data. In: Maglogiannis, I., Iliadis, L., Karydis, I., Papaleonidas, A., Chochliouros, I. (eds) Artificial Intelligence Applications and Innovations. AIAI 2024 IFIP WG 12.5 International Workshops. AIAI 2024. IFIP Advances in Information and Communication Technology, vol 715. Springer, Cham. https://doi.org/10.1007/978-3-031-63227-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-63227-3_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-63226-6
Online ISBN: 978-3-031-63227-3
eBook Packages: Computer ScienceComputer Science (R0)
