Generative Adversarial Network with Soft-Dynamic Time Warping and Parallel Reconstruction for Energy Time Series Anomaly Detection (2402.14384v1)
Abstract: In this paper, we employ a 1D deep convolutional generative adversarial network (DCGAN) for sequential anomaly detection in energy time series data. Anomaly detection involves gradient descent to reconstruct energy sub-sequences, identifying the noise vector that closely generates them through the generator network. Soft-DTW is used as a differentiable alternative for the reconstruction loss and is found to be superior to Euclidean distance. Combining reconstruction loss and the latent space's prior probability distribution serves as the anomaly score. Our novel method accelerates detection by parallel computation of reconstruction of multiple points and shows promise in identifying anomalous energy consumption in buildings, as evidenced by performing experiments on hourly energy time series from 15 buildings.
- Wasserstein generative adversarial networks. In International conference on machine learning, 214–223. PMLR.
- TAnoGAN: Time series anomaly detection with generative adversarial networks. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 1778–1785. IEEE.
- Using dynamic time warping to find patterns in time series. In Proceedings of the 3rd international conference on knowledge discovery and data mining, 359–370.
- Generative adversarial networks in time series: A survey and taxonomy. arXiv preprint arXiv:2107.11098.
- Distribution-based anomaly detection via generalized likelihood ratio test: A general maximum entropy approach. Computer Networks, 57(17): 3446–3462.
- Soft-dtw: a differentiable loss function for time-series. In International conference on machine learning, 894–903. PMLR.
- A survey on gans for anomaly detection. arXiv preprint arXiv:1906.11632.
- Tadgan: Time series anomaly detection using generative adversarial networks. In 2020 IEEE International Conference on Big Data (Big Data), 33–43. IEEE.
- Generative adversarial nets. Advances in neural information processing systems, 27.
- DEGAN: Time Series Anomaly Detection using Generative Adversarial Network Discriminators and Density Estimation. arXiv preprint arXiv:2210.02449.
- LEAD1. 0: a large-scale annotated dataset for energy anomaly detection in commercial buildings. In Proceedings of the Thirteenth ACM International Conference on Future Energy Systems, 485–488.
- Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives. Applied Energy, 287: 116601.
- Methods for fault detection, diagnostics, and prognostics for building systems—a review, part I. Hvac&R Research, 11(1): 3–25.
- MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks. In International conference on artificial neural networks, 703–716. Springer.
- Parzen, E. 1962. On estimation of a probability density function and mode. The annals of mathematical statistics, 33(3): 1065–1076.
- Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434.
- Energy impact of commercial building controls and performance diagnostics: market characterization, energy impact of building faults and energy savings potential. Prepared by TAIX LLC for the US Department of Energy. November. 412pp (Table 2–1).
- A rule-based fault detection method for air handling units. Energy and buildings, 38(12): 1485–1492.
- Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International conference on information processing in medical imaging, 146–157. Springer.
- A novel LSTM-GAN algorithm for time series anomaly detection. In 2019 prognostics and system health management conference (PHM-Qingdao), 1–6. IEEE.