arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.02564cs.DCcs.AIcs.LG
收藏

基于扩散的 Microsoft 365 时间序列数据插补

Diffusion-based Time Series Data Imputation for Microsoft 365

Microsoft Research(微软研究院);Microsoft 365(微软365);KTH Royal Institute of Technology(瑞典皇家理工学院)

Fangkai Yang, Wenjie Yin, Lu Wang, Tianci Li, Pu Zhao, Bo Liu, Paul Wang, Bo Qiao, Yudong Liu, Mårten Björkman, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

AI总结:

针对 Microsoft 365 云系统故障预测中数据缺失影响性能的问题,提出样本高效的扩散模型 Diffusion+ 进行时间序列数据插补,有效提升了下游故障预测任务的性能。

摘要:

可靠性对于像 Microsoft 365 这样的大规模云系统极为重要。磁盘故障、节点故障等云故障威胁着服务可靠性,导致在线服务中断和经济损失。现有工作侧重于预测云故障并在故障发生前主动采取行动。然而,它们在模型训练和预测中受困于数据缺失等数据质量差的问题,这限制了性能。在本文中,我们专注于通过所提出的 Diffusion+(一种样本高效的扩散模型)进行数据插补来提升数据质量,基于观测数据高效地插补缺失数据。我们的实验和应用实践表明,我们的模型有助于提升下游故障预测任务的性能。

英文摘要:

Reliability is extremely important for large-scale cloud systems like Microsoft 365. Cloud failures such as disk failure, node failure, etc. threaten service reliability, resulting in online service interruptions and economic loss. Existing works focus on predicting cloud failures and proactively taking action before failures happen. However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance. In this paper, we focus on enhancing data quality through data imputation by the proposed Diffusion+, a sample-efficient diffusion model, to impute the missing data efficiently based on the observed data. Our experiments and application practice show that our model contributes to improving the performance of the downstream failure prediction task.

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。

↑