Organizations deploy a hierarchy of clusters \u2013 cameras, private clusters, public clouds \u2013 for analyzing live video feeds from their cameras. Video analytics queries have many implementation options which impact their resource demands and accuracy of outputs. Our objective is to select the \u201cquery plan\u201d \u2013 implementations (and their knobs) \u2013 and place it across the hierarchy of clusters, and merge common components across queries to maximize the average query accuracy. This is a challenging task, because we have to consider multi-resource (network and compute) demands and constraints in the hierarchical cluster and search in an exponentially large search space for plans, placements, and merging. We propose VideoEdge, a system that introduces dominant demand to identify the best tradeoff between multiple resources and accuracy, and narrows the search space by identifying a \u201cPareto band\u201d of promising configurations. VideoEdge also balances the resource benefits and accuracy penalty of merging queries. Deployment results show that VideoEdge improves accuracy by 25.4 times and 5.4 times compared to fair allocation of resources and a recent solution for video query planning (VideoStorm), respectively, and is within 6% of optimum.<\/p>\n","protected":false},"excerpt":{"rendered":"
Organizations deploy a hierarchy of clusters \u2013 cameras, private clusters, public clouds \u2013 for analyzing live video feeds from their cameras. Video analytics queries have many implementation options which impact their resource demands and accuracy of outputs. Our objective is to select the \u201cquery plan\u201d \u2013 implementations (and their knobs) \u2013 and place it across […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13547],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-498539","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-systems-and-networking","msr-locale-en_us"],"msr_publishername":"","msr_edition":"ACM\/IEEE Symposium on Edge Computing (SEC)","msr_affiliation":"","msr_published_date":"2018-10-25","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":"507521","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"cascade","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2018\/07\/cascade.pdf","id":507521,"label_id":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Chien-Chun Hung","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Ganesh Ananthanarayanan","user_id":31834,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ganesh Ananthanarayanan"},{"type":"user_nicename","value":"Peter Bod\u00edk","user_id":33239,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Peter Bod\u00edk"},{"type":"text","value":"Leana Golubchik","user_id":0,"rest_url":false},{"type":"text","value":"Minlan Yu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Victor Bahl","user_id":31167,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Victor Bahl"},{"type":"user_nicename","value":"Matthai Philipose","user_id":32834,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Matthai Philipose"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[144899],"msr_project":[382664,212082],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/498539"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/498539\/revisions"}],"predecessor-version":[{"id":498542,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/498539\/revisions\/498542"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=498539"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=498539"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=498539"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=498539"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=498539"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=498539"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=498539"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=498539"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=498539"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=498539"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=498539"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=498539"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=498539"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=498539"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=498539"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}