Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder

论文：《Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder》
Thus， in this paper we propose Bagel, a robust and unsupervised anomaly detection algorithm for KPI that can handle time information related anomalies.

主要细节去看Donut的论文比看这篇论文更好，两篇结合查看更有助于理解。

KPI: key performance indicator

---

1. CVAE(conditional variational auto-encoder, 条件变分自编码器）:http://arxiv.org/abs/1511.06988

用于处理时序信息

2. dropout layer：to avoid overfitting.

---

• KPI v = (v1, v2, …, vn)
• the i-th window of the KPI is x(i) = (vi, vi+1, …, vi+W−1)
• z prior：p(z|y)=p(z)=N(0, i)
• z posterior: $q_{\varphi }(z|x,y)=N({\mu }_z,diag({\sigma }_z^2))$
• x posterior: $p_{\theta }(x|z,y)=N({\mu }_x,diag({\sigma }_x^2))$
• ${\mu }_z=W_{{\mu }_z}^T{f}_{\varphi }(x)+b_{{\mu }_z}$
• ${\mu }_x=W_{{\mu }_x}^T{f}_{\theta }(z)+b_{{\mu }_x}$
• ${\sigma }_z=ln(1+exp(f_{\varphi }(x)))+\Delta$
• ${\sigma }_x=ln(1+exp(f_{\theta }(z)))+\Delta$