两篇新研究论文提出了预测微服务系统尾部延迟的先进方法。第一篇STLGT使用图变换器对服务依赖关系进行建模，并使用时间模块处理工作负载动态，显示出比现有方法更高的准确性和速度。第二篇USRFNet采用双流学习方法分离流量和资源指标，并结合梯度调制策略来解决训练不平衡问题，显著降低了预测误差。 AI
影响 这些新模型提供了更准确、更高效的微服务尾部延迟预测，有助于主动的SLO管理和系统可靠性。
排序理由 两篇在arXiv上发表的学术论文提出了微服务尾部延迟预测的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.26422v1 Announce Type: cross Abstract: Accurate end-to-end tail-latency forecasting is critical for proactive SLO management in microservice systems. However, modeling long-range dependency propagation and non-stationary, bursty workloads while maintaining inference ef…
Accurate end-to-end tail-latency forecasting is critical for proactive SLO management in microservice systems. However, modeling long-range dependency propagation and non-stationary, bursty workloads while maintaining inference efficiency at scale remains challenging. We present …
arXiv:2508.01635v2 Announce Type: replace Abstract: Microservice architectures enable scalable cloud-native applications; however, the distributed nature of these systems complicates the maintenance of strict Service Level Objectives. Accurately predicting window-level P95 tail l…