To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e.g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation. However, anomaly detection for these seasonal KPIs with various patterns and data quality has been a great challenge, especially without labels. In this paper, we proposed Donut, an unsupervised anomaly detection algorithm based on VAE. Thanks to a few of our key techniques, Donut greatly outperforms a state-of-arts supervised ensemble approach and a baseline VAE approach, and its best F-scores range from 0.75 to 0.9 for the studied KPIs from a top global Internet company. We come up with a novel KDE interpretation of reconstruction for Donut, making it the first VAE-based anomaly detection algorithm with solid theoretical explanation.
This article studies the problems of exponential stabilization and ℒ2‐gain performance for networked control systems (NCSs) with transmission delays and periodic denial‐of‐service (DoS) attacks by exploring a resilient event‐triggered communication mechanism. First, a new resilient event‐triggered mechanism is developed to eliminate the adverse effects of network congestion caused by DoS attacks and decrease redundant communication so as to ensure efficient utilization of the limited network resources. The threshold parameter in the predefined event‐triggered condition can be adjusted according to the dynamic characteristics of the system. Then, an event‐driven control protocol is proposed, and a new switched NCS model is constructed. Sufficient conditions are then presented to ensure the exponential stability and ℒ2‐gain performance of the resulting closed‐loop system. Moreover, a co‐design scheme of the parameters in the event‐triggered condition and the controller gain is provided. Finally, the effectiveness and advantages of the new design techniques are verified through a comparative study for a robot manipulator control system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.