Intelligent anomaly detection for key performance indicators (KPIs) is important for keeping services reliable in industrial-based cyber–physical systems (CPS). However, it is common in practice for various KPI sampling strategies to be utilized. We experimentally verify that anomaly detection is highly sensitive to irregular sampling, and accordingly go on to investigate low-cost anomaly detection for large-scale irregular KPIs. Irregular KPIs can be classified into four types: equal interval and unequal quantity (EIUQ) KPIs, unequal interval (UI) KPIs, unequal interval with equal duration (UIED) KPIs, and segmented irregular KPIs. In this article, we propose an anomaly detection framework based on these irregular types. Moreover, to handle the various lengths and phase shifts among EIUQ KPIs, we propose a normalized version of unequal cross-correlation, which slides the KPIs to enable finding the most similar position. To avoid high computational costs, we analyze the low-rank feature of KPIs data and propose a matrix factorization-based alignment algorithm for UIED KPIs; this algorithm treats UIED KPIs as an incomplete matrix and recovers the KPIs to align them before performing anomaly detection. Extensive simulations using three public datasets and two real-world datasets demonstrate that our algorithm can achieve a larger F1-score than Minkowski distance and less time than dynamic time warping distance.

中文翻译：

---

基于工业的网络物理系统中关键性能指标的智能检测

关键性能指标（KPI）的智能异常检测对于在基于工业的网络物理系统（CPS）中保持服务可靠至关重要。但是，实践中通常会使用各种KPI采样策略。我们通过实验验证了异常检测对不规则采样高度敏感，因此继续研究了针对大规模不规则KPI的低成本异常检测。不规则KPI可以分为四种类型：等间隔和不等量（EIUQ）KPI，不等间隔（UI）KPI，不等距等长（UIED）KPI和分段不规则KPI。在本文中，我们提出了一种基于这些不规则类型的异常检测框架。此外，为了处理EIUQ KPI之间的各种长度和相移，我们提出了不等互相关的归一化版本，该版本可以滑动KPI以便找到最相似的位置。为了避免高昂的计算成本，我们分析了KPI数据的低阶特征，并提出了一种基于矩阵分解的UIED KPI对齐算法。该算法将UIED KPI视为不完整的矩阵，并在执行异常检测之前恢复KPI以对齐它们。使用三个公共数据集和两个实际数据集的广泛仿真表明，我们的算法可以实现比Minkowski距离更大的F1得分，并且比动态时间扭曲距离更短的时间。该算法将UIED KPI视为不完整的矩阵，并在执行异常检测之前恢复KPI以对齐它们。使用三个公共数据集和两个现实世界数据集的大量仿真表明，我们的算法可以实现比Minkowski距离更大的F1得分，并且比动态时间扭曲距离更短的时间。该算法将UIED KPI视为不完整的矩阵，并在执行异常检测之前恢复KPI以对齐它们。使用三个公共数据集和两个实际数据集的广泛仿真表明，我们的算法可以实现比Minkowski距离更大的F1得分，并且比动态时间扭曲距离更短的时间。