Performance issues permeate large-scale cloud service systems, which can lead to huge revenue losses. To ensure reliable performance, it's essential to accurately identify and localize these issues using service monitoring metrics. Given the complexity and scale of modern cloud systems, this task can be challenging and may require extensive expertise and resources beyond the capacity of individual humans. Some existing methods tackle this problem by analyzing each metric independently to detect anomalies. However, this could incur overwhelming alert storms that are difficult for engineers to diagnose manually. To pursue better performance, not only the temporal patterns of metrics but also the correlation between metrics (i.e., relational patterns) should be considered, which can be formulated as a multivariate metrics anomaly detection problem. However, most of the studies fall short of extracting these two types of features explicitly. Moreover, there exist some unlabeled anomalies mixed in the training data, which may hinder the detection performance. To address these limitations, we propose the Relational- Temporal Anomaly Detection Model (RTAnomaly) that combines the relational and temporal information of metrics. RTAnomaly employs a graph attention layer to learn the dependencies among metrics, which will further help pinpoint the anomalous metrics that may cause the anomaly effectively. In addition, we exploit the concept of positive unlabeled learning to address the issue of potential anomalies in the training data. To evaluate our method, we conduct experiments on a public dataset and two industrial datasets. RTAnomaly outperforms all the baseline models by achieving an average F1 score of 0.929 and Hit@3 of 0.920, demonstrating its superiority.

翻译：性能问题在大型云服务系统中普遍存在，可能导致巨额收益损失。为确保可靠性能，必须利用服务监控指标准确识别并定位这些问题。鉴于现代云系统的复杂性和规模，这一任务面临挑战，可能需要超出单个人力范围的广泛专业知识和资源。现有方法通过独立分析每个指标来检测异常，但这可能引发工程师难以人工诊断的告警风暴。为追求更优性能，不仅需要考虑指标的时间模式，还需考虑指标间的关联性（即关系模式），这可以形式化为多变量指标异常检测问题。然而，多数研究未能明确提取这两类特征。此外，训练数据中混杂的未标注异常会阻碍检测性能。为解决这些局限，我们提出结合指标关系与时间信息的RTAnomaly（关系-时序异常检测模型）。该模型采用图注意力层学习指标间的依赖关系，从而有效定位可能导致异常的异常指标。同时，我们利用正样本-未标注学习概念处理训练数据中的潜在异常。为评估方法，我们在公开数据集和两个工业数据集上开展实验。RTAnomaly在所有基线模型中表现最优，平均F1分数达0.929，Hit@3达0.920，彰显其优越性。