{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:19:00Z","timestamp":1771467540545,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2105564,2236987,2402383,2348066"],"award-info":[{"award-number":["2105564,2236987,2402383,2348066"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/ccgrid64434.2025.00032","type":"proceedings-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:36:08Z","timestamp":1751304968000},"page":"315-324","source":"Crossref","is-referenced-by-count":1,"title":["CarbonDIS: Carbon-Aware DNN Inference Scheduling on Heterogeneous GPUs"],"prefix":"10.1109","author":[{"given":"Seyed Morteza","family":"Nabavinejad","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Jia","sequence":"additional","affiliation":[{"name":"University of Rhode Island"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubbhi","family":"Taneja","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Guo","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","author":"Crankshaw","year":"2017","journal-title":"in USENIX NSDI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3314388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.01.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3042320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532366"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"ref9","article-title":"Once for all: Train one network and specialize it for efficient deployment","volume-title":"International Conference on Learning Representations","author":"Cai","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3604930.3605708"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3493399"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575709"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3563357.3564079"},{"key":"ref15","volume-title":"Electricity map","author":"Map","year":"2024"},{"key":"ref16","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"Xiao","year":"2018","journal-title":"in OSDI\u201918"},{"key":"ref17","first-page":"947","article-title":"Analysis of large-scale multi-tenant {GPU} clusters for {DNN} training workloads","author":"Jeon","year":"2019","journal-title":"in ATC\u201919"},{"key":"ref18","first-page":"443","article-title":"Serving dnns like clockwork: Performance predictability from the bottom up","author":"Gujarati","year":"2020","journal-title":"in OSDI\u201920"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3340518"},{"key":"ref20","year":"2024","journal-title":"WattTime"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref22","volume-title":"Tensorflow hub","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"ref24","first-page":"10096","article-title":"Efficientnetv 2: Smaller models and faster training","volume-title":"International conference on machine learning. PMLR","author":"Tan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref30","first-page":"4510","article-title":"Mobilenetv 2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018","journal-title":"in CVPR\u201918"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-32"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303958"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref34","first-page":"1041","article-title":"Cocktail: A multidimensional optimization for model serving in cloud","author":"Gunasekaran","year":"2022","journal-title":"in USENIX NSDI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2942020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3473334"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567508"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.52"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486993"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3144614"}],"event":{"name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Troms\u00f8, Norway","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,22]]}},"container-title":["2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11044421\/11044790\/11044817.pdf?arnumber=11044817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:32:51Z","timestamp":1751347971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ccgrid64434.2025.00032","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}