一句话：用 GCN-GAE 学习微服务服务图嵌入，以负载测试与真实事件嵌入的余弦相似度检测异常服务。
Prime Video 常在周四夜橄榄球直播等大型活动前进行负载测试，但压力测试可能遗漏真实事件流量中特有的服务行为。论文提出一个基于图的异常检测系统：在分钟级分辨率上，从有向加权服务图出发，用 GCN-GAE 学习无监督的节点级结构嵌入，再通过比较负载测试与真实事件嵌入之间的余弦相似度，标出「表示不足」的服务，从而发现与事故相关的服务并具备早期检测能力。为进行受控评估，作者还提出一个初步的合成异常注入框架，在保守的异常传播假设下取得 96% 的精确率与 0.08% 的误报率，但召回率仅为 58%。该系统已在 Prime Video 生产环境中体现实用价值，并给出了方法论层面的经验与推广方向。
Prime Video regularly conducts load tests to simulate the viewer traffic spikes seen during live events such as Thursday Night Football as well as video-on-demand (VOD) events such as Rings of Power. While these stress tests validate system capacity, they can sometimes miss service behaviors unique to real event traffic. We present a graph-based anomaly detection system that identifies under-represented services using unsupervised node-level graph embeddings. Built on a GCN-GAE, our approach learns structural representations from directed, weighted service graphs at minute-level resolution and flags anomalies based on cosine similarity between load test and event embeddings. The system identifies incident-related services that are documented and demonstrates early detection capability. We also introduce a preliminary synthetic anomaly injection framework for controlled evaluation that show promising precision (96%) and low false positive rate (0.08%), though recall (58%) remains limited under conservative propagation assumptions. This framework demonstrates practical utility within Prime Video while also surfacing methodological lessons and directions, providing a foundation for broader application across microservice ecosystems.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2604-06448,
title = {From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures},
author = {Srinidhi Madabhushi and Pranesh Vyas and Swathi Vaidyanathan and Mayur Kurup and Elliott Nash and Yegor Silyutin},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805232}
}