一句话：提出首个云服务性能指标异常预判方法，用条件扩散预测指标并结合孤立森林提前发现异常。
云服务异常检测通常仅在异常发生后实时告警，但异常会传播并升级为故障，因此更早预判异常对下游诊断与干预至关重要。本文提出 Maat，首个面向云服务性能指标的异常预判方法。Maat 采用两阶段范式：先以条件去噪扩散模型自回归地进行多步指标预测，再基于领域知识提取异常指示特征，并用带增量学习的孤立森林在预测序列上检测未来异常。在三个公开数据集上的评估表明，Maat 能比实时检测更早预判异常，或在效果上优于最先进的实时异常检测器；案例研究进一步展示了其预测异常指标并发现异常的能力。
Ensuring the reliability and user satisfaction of cloud services necessitates prompt anomaly detection followed by diagnosis. Existing techniques for anomaly detection focus solely on real-time detection, meaning that anomaly alerts are issued as soon as anomalies occur. However, anomalies can propagate and escalate into failures, making faster-than-real-time anomaly detection highly desirable for expediting downstream analysis and intervention. This paper proposes Maat, the first work to address anomaly anticipation of performance metrics in cloud services. Maat adopts a novel two-stage paradigm for anomaly anticipation, consisting of metric forecasting and anomaly detection on forecasts. The metric forecasting stage employs a conditional denoising diffusion model to enable multi-step forecasting in an auto-regressive manner. The detection stage extracts anomaly-indicating features based on domain knowledge and applies isolation forest with incremental learning to detect upcoming anomalies. Thus, our method can uncover anomalies that better conform to human expertise. Evaluation on three publicly available datasets demonstrates that Maat can anticipate anomalies faster than real-time comparatively or more effectively compared with state-of-the-art real-time anomaly detectors. We also present cases highlighting Maat's success in forecasting abnormal metrics and discovering anomalies.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{LeeYCSL23,
title = {Maat: Performance Metric Anomaly Anticipation for Cloud Services with Conditional Diffusion},
author = {Cheryl Lee and Tianyi Yang and Zhuangbin Chen and Yuxin Su and Michael R. Lyu},
booktitle = {ASE},
year = {2023},
doi = {10.1109/ase56229.2023.00082}
}