With the rapid deployment of cloud platforms, high service reliability is of critical importance. An industrial cloud platform contains a huge number of disks, and disk failure is a common cause of service unreliability. In recent years, many machine learning based disk failure prediction approaches have been proposed, and they can predict disk failures based on disk status data before the failures actually happen. In this way, proactive actions can be taken in advance to improve service reliability. However, existing approaches treat each disk individually and do not explore the influence of the neighboring disks. In this paper, we propose Neighborhood-Temporal Attention Model (NTAM), a novel deep learning based approach to disk failure prediction. When predicting whether or not a disk will fail in near future, NTAM is a novel approach that not only utilizes a disk’s own status data, but also considers its neighbors’ status data. Moreover, NTAM includes a novel attention-based temporal component to capture the temporal nature of the disk status data. Besides, we propose a data enhancement method, called Temporal Progressive Sampling (TPS), to handle the extreme data imbalance issue. We evaluate NTAM on a public dataset as well as two industrial datasets collected from millions of disks in Microsoft Azure. Our experimental results show that NTAM significantly outperforms state-of-the-art competitors. Also, our empirical evaluations indicate the effectiveness of the neighborhood-ware component and the temporal component underlying NTAM as well as the effectiveness of TPS. More encouragingly, we have successfully applied NTAM and TPS to Microsoft Azure and obtained practical benefits in industrial practice.<\/p>\n","protected":false},"excerpt":{"rendered":"
With the rapid deployment of cloud platforms, high service reliability is of critical importance. An industrial cloud platform contains a huge number of disks, and disk failure is a common cause of service unreliability. In recent years, many machine learning based disk failure prediction approaches have been proposed, and they can predict disk failures based […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"WWW (TheWebConf) 2021","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2021-2-1","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13561,13556,13563],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-723331","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-data-platform-analytics","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-2-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/02\/NTAM_WWW_2021_camera_ready.pdf","id":"732697","title":"ntam_www_2021_camera_ready","label_id":"243109","label":0}],"msr_related_uploader":[{"type":"file","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/02\/NTAM_WWW_2021_camera_ready.pdf","id":"732697","title":"ntam_www_2021_camera_ready","label_id":"243118","label":0}],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":732697,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/03\/NTAM_WWW_2021_camera_ready.pdf"},{"id":723334,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/02\/NTAM.docx"}],"msr-author-ordering":[{"type":"text","value":"Chuan Luo","user_id":0,"rest_url":false},{"type":"text","value":"Pu Zhao","user_id":0,"rest_url":false},{"type":"text","value":"...","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Qingwei Lin","user_id":33318,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Qingwei Lin"},{"type":"text","value":"...","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[793670,811276],"msr_project":[853323,855579,807190],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":853323,"post_title":"Cloud System and Software Analytics","post_name":"cloud-system-and-software-analytics","post_type":"msr-project","post_date":"2022-06-24 00:55:15","post_modified":"2022-10-24 01:21:01","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/cloud-system-and-software-analytics\/","post_excerpt":"In Microsoft, we build and operate several world leading complex and large-scale productivity clouds (Azure, Microsoft 365). The quality of cloud platforms, including reliability, performance, efficiency, security, sustainability, etc., has become immensely important. The distributed nature, massive scale, and high complexity of cloud platforms present huge challenges to build and operate such systems effectively and efficiently. Each independent service in cloud computing, such as computing virtualization, cloud storage service, distributed database, etc., is a complex…","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/853323"}]}},{"ID":855579,"post_title":"AIOps","post_name":"aiops","post_type":"msr-project","post_date":"2022-06-24 04:09:36","post_modified":"2022-10-25 05:28:06","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/aiops\/","post_excerpt":"In the past fifteen years, the most significant paradigm shift in the computing industry is the migration to cloud computing, which brings unprecedented opportunities of digital transformation to business, society, and human life. The implication of this is profound. It means that cloud computing platforms have become part of the basic infrastructure of the world. Therefore, the non-functional properties of cloud computing platforms, including availability, reliability, performance, efficiency, security, sustainability, etc., become immensely important. The…","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/855579"}]}},{"ID":807190,"post_title":"Green Cloud Computing","post_name":"green-cloud-computing","post_type":"msr-project","post_date":"2021-12-23 02:19:55","post_modified":"2022-10-24 01:23:16","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/green-cloud-computing\/","post_excerpt":"We are actively pursuing a sustainable form of cloud computing, Green Cloud Computing, to reduce the energy consumption and cut down carbon emission accordingly.","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/807190"}]}}]},"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/723331","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/723331\/revisions"}],"predecessor-version":[{"id":723337,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/723331\/revisions\/723337"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=723331"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=723331"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=723331"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=723331"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=723331"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=723331"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=723331"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=723331"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=723331"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=723331"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=723331"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=723331"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=723331"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}