利用 Transformer 的可解释性实现云资源主动伸缩自动化
Leveraging Interpretability in the Transformer to Automate the Proactive Scaling of Cloud Resources
AI总结:
本文提出利用具备可解释性的时序融合 Transformer 预测微服务端到端延迟,并在预测到 SLA 不合规时,将特征重要性作为核岭回归协变量学习所需资源调整量,从而实现云资源主动伸缩。
摘要:
现代 Web 服务采用云原生原则,以利用微服务的优势。为了根据服务级别协议(SLA)持续保证高服务质量(QoS)、确保令人满意的用户体验并最小化运营成本,每个微服务都必须配置适当数量的资源。然而,准确为微服务配置充足资源十分复杂,并取决于许多因素,包括工作负载强度以及微服务之间复杂的相互连接。为应对这一挑战,我们开发了一个模型,用于刻画端到端延迟、前端请求与资源利用率之间的关系。随后,我们利用所开发的模型来预测端到端延迟。我们的解决方案采用时序融合 Transformer(Temporal Fusion Transformer,TFT),这是一种基于注意力机制并具备可解释性特性的架构。当预测结果表明 SLA 不合规时,我们将 TFT 提供的特征重要性作为核岭回归(Kernel Ridge Regression,KRR)中的协变量,以期望延迟作为响应变量,学习与特征重要性相关的参数。这些学习到的参数反映了为确保 SLA 合规而需要对特征进行的调整。我们通过一个基于微服务的应用展示了该方法的优点,并提供了部署路线图。
英文摘要:
Modern web services adopt cloud-native principles to leverage the advantages of microservices. To consistently guarantee high Quality of Service (QoS) according to Service Level Agreements (SLAs), ensure satisfactory user experiences, and minimize operational costs, each microservice must be provisioned with the right amount of resources. However, accurately provisioning microservices with adequate resources is complex and depends on many factors, including workload intensity and the complex interconnections between microservices. To address this challenge, we develop a model that captures the relationship between an end-to-end latency, requests at the front-end level, and resource utilization. We then use the developed model to predict the end-to-end latency. Our solution leverages the Temporal Fusion Transformer (TFT), an attention-based architecture equipped with interpretability features. When the prediction results indicate SLA non-compliance, we use the feature importance provided by the TFT as covariates in Kernel Ridge Regression (KRR), with the response variable being the desired latency, to learn the parameters associated with the feature importance. These learned parameters reflect the adjustments required to the features to ensure SLA compliance. We demonstrate the merit of our approach with a microservice-based application and provide a roadmap to deployment.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。