arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00034cs.DCcs.AI
收藏

为何预测准确率会随时间下降?面向云故障预测的不确定正样本学习

Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction

Microsoft(微软)

Haozhe Li, Minghua Ma, Yudong Liu, Pu Zhao, Lingling Zheng, Ze Li, Yingnong Dang, Murali Chintalapati, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

AI总结:

针对云故障预测中模型重训后准确率下降的不确定正样本学习问题,提出Uptake风险估计方法,在Azure真实场景中平均提升预测准确率5%。

摘要:

随着云计算的快速发展,各类软件服务已部署在云端。为保障云服务的可靠性,既往研究聚焦于故障实例(磁盘、节点、交换机等)预测,一旦预测结果为正,就会采取缓解措施以快速排查潜在故障。根据我们在Microsoft Azure中的实际运维经验,模型重新训练后预测准确率可能下降约9%。我们分析认为,缓解措施实施后无法验证故障是否真实存在,会产生不确定的正样本,进而在预测模型更新时引入更多噪声。据我们所知,我们是首个在真实云故障预测场景中发现这一“不确定正样本学习(Uncertain Positive Learning,简称UPLearning)”问题的团队。为解决该问题,我们设计了不确定正样本学习风险估计器(Uncertain Positive Learning Risk Estimator,简称Uptake)方法。我们在服务数百万用户的顶级云服务商Microsoft Azure中,使用两个真实磁盘故障预测数据集并开展节点故障预测实验,结果表明Uptake可将故障预测准确率平均显著提升5%。

英文摘要:

With the rapid growth of cloud computing, a variety of software services have been deployed in the cloud. To ensure the reliability of cloud services, prior studies focus on failure instance (disk, node, and switch, etc.) prediction. Once the output of prediction is positive, mitigation actions are taken to rapidly resolve the underlying failure. According to our real-world practice in Microsoft Azure, we find that the prediction accuracy may decrease by about 9% after retraining the models. Considering that the mitigation actions may result in uncertain positive instances since they cannot be verified after mitigation, which may introduce more noise while updating the prediction model. To the best of our knowledge, we are the first to identify this Uncertain Positive Learning (UPLearning) issue in the real-world cloud failure prediction scenario. To tackle this problem, we design an Uncertain Positive Learning Risk Estimator (Uptake) approach. Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.

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。

↑