# Generative Adversarial Network with Soft-Dynamic Time Warping and Parallel Reconstruction for Energy Time Series Anomaly Detection

arXiv: https://arxiv.org/abs/2402.14384 · HTML: https://mlsanity.com/paper/2402.14384/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks](https://mlsanity.com/paper/1901.04997/) (2019)
- [TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.07769/) (2020)
- [A Survey on GANs for Anomaly Detection](https://mlsanity.com/paper/1906.11632/) (2019)
- [LEAD1.0: A Large-scale Annotated Dataset for Energy Anomaly Detection in Commercial Buildings](https://mlsanity.com/paper/2203.17256/) (2022)

## Built on by (most cited first, 1 of 1)

- [Financial time series augmentation using transformer based GAN architecture](https://mlsanity.com/paper/2602.17865/) (2026)

## Abstract (arXiv)

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.