{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:14:20Z","timestamp":1743092060007,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":12,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819922321"},{"type":"electronic","value":"9789819922338"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-2233-8_30","type":"book-chapter","created":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T03:18:45Z","timestamp":1682824725000},"page":"421-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MagicBatch: An Energy-Aware Scheduling Framework for\u00a0DNN Inference on\u00a0Heterogeneous Edge Servers in\u00a0Space-Air-Ground Computation"],"prefix":"10.1007","author":[{"given":"Di","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aolin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuangyu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,1]]},"reference":[{"key":"30_CR1","unstructured":"Crankshaw, D., Wang, X., Zhou, G., Franklin, M.J., Gonzalez, J.E., Stoica, I.: Clipper: a low-latency online prediction serving system. In: 14th USENIX NSDI, pp. 613\u2013627 (2017)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Cui, W., Wei, M., Chen, Q., Tang, X., Leng, J., Li, L., Guo, M.: Ebird: elastic batch for improving responsiveness and throughput of deep learning services. In: 37th ICCD, pp. 497\u2013505. IEEE (2019)","DOI":"10.1109\/ICCD46524.2019.00075"},{"issue":"18","key":"30_CR3","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1002\/wcm.1203","volume":"13","author":"HT Dinh","year":"2013","unstructured":"Dinh, H.T., Lee, C., Niyato, D., Wang, P.: A survey of mobile cloud computing: architecture, applications, and approaches. Wirel. Commun. Mob. Comput. 13(18), 1587\u20131611 (2013)","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Fu, Z., Ren, J., Zhang, D., Zhou, Y., Zhang, Y.: Kalmia: a heterogeneous QoS-aware scheduling framework for DNN tasks on edge servers. In: IEEE INFOCOM 2022, pp. 780\u2013789. IEEE (2022)","DOI":"10.1109\/INFOCOM48880.2022.9796661"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Jiang, J., Cui, B., Zhang, C., Yu, L.: Heterogeneity-aware distributed parameter servers. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp. 463\u2013478 (2017)","DOI":"10.1145\/3035918.3035933"},{"key":"30_CR6","unstructured":"Jiang, Y., Zhu, Y., Lan, C., Yi, B., Cui, Y., Guo, C.: A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters. In: 14th USENIX OSDI, pp. 463\u2013479 (2020)"},{"issue":"8","key":"30_CR7","doi-asserted-by":"publisher","first-page":"5456","DOI":"10.1109\/TII.2019.2961237","volume":"16","author":"B Lin","year":"2019","unstructured":"Lin, B., Huang, Y., Zhang, J., Hu, J., Chen, X., Li, J.: Cost-driven off-loading for DNN-based applications over cloud, edge, and end devices. IEEE Trans. Industr. Inf. 16(8), 5456\u20135466 (2019)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"10","key":"30_CR8","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.1109\/TPDS.2022.3144614","volume":"33","author":"SM Nabavinejad","year":"2022","unstructured":"Nabavinejad, S.M., Reda, S., Ebrahimi, M.: Coordinated batching and DVFS for DNN inference on GPU accelerators. IEEE Trans. Parallel Distrib. Syst. 33(10), 2496\u20132508 (2022)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"30_CR9","unstructured":"Narayanan, D., Santhanam, K., Kazhamiaka, F., Phanishayee, A., Zaharia, M.: Heterogeneity-aware cluster scheduling policies for deep learning workloads. In: 14th USENIX OSDI 2020, pp. 481\u2013498 (2020)"},{"key":"30_CR10","unstructured":"Olston, C., et al.: TensorFlow-serving: flexible, high-performance ML serving. arXiv preprint arXiv:1712.06139 (2017)"},{"key":"30_CR11","unstructured":"Park, J.H., et al.: HetPipe: enabling large DNN training on (Whimpy) heterogeneous GPU Clusters through integration of pipelined model parallelism and data parallelism. In: USENIX ATC, pp. 307\u2013321 (2020)"},{"key":"30_CR12","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.future.2022.01.004","volume":"130","author":"C Yao","year":"2022","unstructured":"Yao, C., Liu, W., Tang, W., Hu, S.: EAIS: energy-aware adaptive scheduling for CNN inference on high-performance GPUs. Futur. Gener. Comput. Syst. 130, 253\u2013268 (2022)","journal-title":"Futur. Gener. Comput. Syst."}],"container-title":["Lecture Notes in Computer Science","Big Data Intelligence and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-2233-8_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T03:22:59Z","timestamp":1682824979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-2233-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819922321","9789819922338"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-2233-8_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DataCom","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Intelligence and Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denarau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fiji","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"datacom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}