Service-oriented 5G mobile systems are commonly believed to reshape the landscape of the Internet with ubiquitous services and infrastructures. The micro-services architecture has attracted significant interests from both academia and industry, offering the capabilities of agile development and scale capacity. The emerging mobile edge computing is able to firmly maintain efficient resource utility of 5G systems, which can be empowered by micro-services. However, such capabilities impose significant challenges on micro-services system management. Although substantial data are produced for system maintenance, the interleaved temporal-spatial information has not been fully exploited. Additionally, the flooding data impose heavy pressures on automatic analysis tools. Automated digestion of data is in an urgent need for system maintenance. In this paper, we propose a new learning-based anomaly detection framework for service-provision systems with micro-services architectures using service execution logs (temporally) and query traces (spatially). It includes two major parts: logging and tracing representation, and two-stage identification via a sequential model and temporal-spatial analysis. The experimental results show that the temporal-spatial features can accurately capture the nature of operational data. The proposed framework performs well on anomaly detection, and helps gain in-depth insights of large-scale systems.

中文翻译：

---

具有时空数据分析的微服务架构智能异常检测方案

人们普遍认为，面向服务的 5G 移动系统将通过无处不在的服务和基础设施重塑互联网格局。微服务架构吸引了学术界和工业界的极大兴趣，提供了敏捷开发和扩展能力。新兴的移动边缘计算能够牢牢保持5G系统的高效资源利用，可以通过微服务赋能。然而，这样的能力对微服务系统管理提出了重大挑战。尽管为系统维护产生了大量数据，但交错的时空信息尚未得到充分利用。此外，洪水数据给自动分析工具带来了沉重的压力。系统维护迫切需要自动消化数据。在本文中，我们提出了一种新的基于学习的异常检测框架，用于具有微服务架构的服务提供系统，使用服务执行日志（时间）和查询跟踪（空间）。它包括两个主要部分：记录和跟踪表示，以及通过序列模型和时空分析进行的两阶段识别。实验结果表明，时空特征可以准确捕捉操作数据的性质。所提出的框架在异常检测方面表现良好，并有助于深入了解大规模系统。通过序列模型和时空分析进行两阶段识别。实验结果表明，时空特征可以准确捕捉操作数据的性质。所提出的框架在异常检测方面表现良好，有助于深入了解大规模系统。通过序列模型和时空分析进行两阶段识别。实验结果表明，时空特征可以准确捕捉操作数据的性质。所提出的框架在异常检测方面表现良好，有助于深入了解大规模系统。