Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866907783146766336 |
|---|---|
| author | Li, Haozhe Ma, Minghua Liu, Yudong Zhao, Pu Zheng, Lingling Li, Ze Dang, Yingnong Chintalapati, Murali Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei |
| author_facet | Li, Haozhe Ma, Minghua Liu, Yudong Zhao, Pu Zheng, Lingling Li, Ze Dang, Yingnong Chintalapati, Murali Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction Li, Haozhe Ma, Minghua Liu, Yudong Zhao, Pu Zheng, Lingling Li, Ze Dang, Yingnong Chintalapati, Murali Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei Distributed, Parallel, and Cluster Computing Artificial Intelligence K.6.3; I.2.0 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. |
| title | Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence K.6.3; I.2.0 |
| url | https://arxiv.org/abs/2402.00034 |