FDNN: Feature-based Deep Neural Network Model for Anomaly Detection of KPIs
FDNN: Feature-based Deep Neural Network Model for Anomaly Detection of KPIs
复制标题
FDNN：用于 KPI 异常检测的基于特征的深度神经网络模型
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Wei Fang
中科院分区：
文献类型：
--
作者：
Zhibo Lan;Liutong Xu;Wei Fang
KPI（关键绩效指标）的异常检测已广泛应用于确保现实世界中的系统稳定性。 KPI包括网页的响应时间，CPU利用率，内存利用率，磁盘IO等。但是，不同KPI的时间序列具有不同的形状，因此通过简单的统计或机器学习模型来检测KPI的异常是一个巨大的挑战。在本文中，我们设计和实施FDNN（基于功能的深神网络）模型，以用于KPI的异常检测。我们提出了一种名为MSWFeature（多个滑动窗口功能）的新型功能工程方法，该方法更适合于为KPI的时间序列提取时间功能。与其他监督模型相比，具有MSWFeature的FDNN模型在F1得分中取得了良好的性能，以在全球顶级互联网公司收集的研究KPI数据集上进行异常检测。 （抽象的）
Anomaly detection of KPIs (key performance indicators) has been widely applied to guarantee systems stability in real world. KPIs include response time of Web pages, CPU utilization, memory utilization, disk IO and so on. However, time series of different KPIs have different shapes, so that it is a great challenge to detect anomaly of KPIs by a simple statistical or machine learning model. In this paper, we design and implement FDNN (Feature-based Deep Neural Network) model for anomaly detection of KPIs. We present a novel feature engineering approach called MSWFeature (multiple sliding windows feature) which is more suitable to extract temporal feature for time series of KPIs. FDNN model with MSWFeature achieves good performance in F1-Score over other supervised models for anomaly detection on the studied KPIs dataset collected by the top global internet companies. (Abstract)