{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:33Z","timestamp":1750219953049,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation of China","award":["62172454, 61972158"],"award-info":[{"award-number":["62172454, 61972158"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2021A1515011912, 2023B1515020120"],"award-info":[{"award-number":["2021A1515011912, 2023B1515020120"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605575","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"472-481","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DAG-Aware Optimization for Geo-Distributed Data Analytics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1292-7169","authenticated-orcid":false,"given":"Qingyuan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5009-3514","authenticated-orcid":false,"given":"Bin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0307-266X","authenticated-orcid":false,"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1590-5323","authenticated-orcid":false,"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8698-2356","authenticated-orcid":false,"given":"Chenghao","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476359"},{"key":"e_1_3_2_1_2_1","article-title":"Optimizing Network Transfers for Data Analytic Jobs Across Geo-Distributed Datacenters","volume":"33","author":"Chen Li","year":"2021","unstructured":"Li Chen, Shuhao Liu, and Baochun Li. 2021. Optimizing Network Transfers for Data Analytic Jobs Across Geo-Distributed Datacenters. IEEE Transactions on Parallel and Distributed Systems 33, 2 (2021).","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"Scheduling Jobs across Geo-Distributed Datacenters with Max-Min Fairness","author":"Chen Li","year":"2018","unstructured":"Li Chen, Shuhao Liu, Baochun Li, and Bo Li. 2018. Scheduling Jobs across Geo-Distributed Datacenters with Max-Min Fairness. IEEE Transactions on Network Science and Engineering 6 (2018). Issue 3."},{"key":"e_1_3_2_1_4_1","volume-title":"SDTP: Accelerating Wide-Area Data Analytics with Simultaneous Data Transfer and Processing","author":"Chen Yiting","year":"2021","unstructured":"Yiting Chen, Lailong Luo, Deke Guo, Ori Rottenstreich, and Jie Wu. 2021. SDTP: Accelerating Wide-Area Data Analytics with Simultaneous Data Transfer and Processing. IEEE Transactions on Cloud Computing (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_1_6_1","volume-title":"A Survey on Geographically Distributed Big-Data Processing Using MapReduce","author":"Dolev Shlomi","year":"2017","unstructured":"Shlomi Dolev, Patricia Florissi, Ehud Gudes, Shantanu Sharma, and Ido Singer. 2017. A Survey on Geographically Distributed Big-Data Processing Using MapReduce. IEEE Transactions on Big Data 5 (2017). Issue 1."},{"key":"e_1_3_2_1_7_1","unstructured":"Hadoop [n. d.]. Hadoop. https:\/\/hadoop.apache.org\/. Accessed: 2023-04-23."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2014.2355225"},{"key":"e_1_3_2_1_9_1","volume-title":"Proc.\u00a0of USENIX NSDI","author":"Hsieh Kevin","year":"2017","unstructured":"Kevin Hsieh, Aaron Harlap, Nandita Vijaykumar, Dimitris Konomis, Gregory\u00a0R. Ganger, Phillip\u00a0B. Gibbons, and Onur Mutlu. 2017. Gaia: Geo-distributed machine learning approaching LAN speeds. Proc.\u00a0of USENIX NSDI (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2773504"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190528"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806780"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850578.2850582"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc.\u00a0of SEC.","author":"Kumar Dhruv","year":"2021","unstructured":"Dhruv Kumar and RKS Sohaib Ahmad\u00a0Abhishek Chandra. 2021. AggNet: Cost-Aware Aggregation Networks for Geo-distributed Streaming Analytics. In Proc.\u00a0of SEC."},{"key":"e_1_3_2_1_15_1","volume-title":"An effective scheduling strategy based on hypergraph partition in geographically distributed datacenters. Computer Networks 170","author":"Li Chunlin","year":"2020","unstructured":"Chunlin Li, Yihan Zhang, Zhiqiang Hao, and Youlong Luo. 2020. An effective scheduling strategy based on hypergraph partition in geographically distributed datacenters. Computer Networks 170 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3281411.3281418"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2626285"},{"key":"e_1_3_2_1_18_1","article-title":"Wide-area spark streaming: Automated routing and batch sizing","volume":"30","author":"Li Wenxin","year":"2018","unstructured":"Wenxin Li, Di Niu, Yinan Liu, Shuhao Liu, and Baochun Li. 2018. Wide-area spark streaming: Automated routing and batch sizing. IEEE Transactions on Parallel and Distributed Systems 30, 6 (2018).","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.131"},{"key":"e_1_3_2_1_20_1","volume-title":"Approximation algorithms for bin packing: A survey. Approximation algorithms for NP-hard problems","author":"Jr G\u00a0Co","year":"1996","unstructured":"EG\u00a0Co man Jr, MR Garey, and DS Johnson. 1996. Approximation algorithms for bin packing: A survey. Approximation algorithms for NP-hard problems (1996)."},{"key":"e_1_3_2_1_21_1","unstructured":"Evangelos Michelioudakis and Anastasios Skarlatidis. [n. d.]. Optimus: an open-source mathematical optimization library. https:\/\/github.com\/vagmcs\/Optimus"},{"key":"e_1_3_2_1_22_1","article-title":"A survey on bandwidth-aware geo-distributed frameworks for big-data analytics","volume":"8","author":"Mohammed Bergui","year":"2021","unstructured":"Bergui Mohammed, Najah Said, and Nikola\u00a0S Nikolov. 2021. A survey on bandwidth-aware geo-distributed frameworks for big-data analytics. Journal of Big Data 8, 1 (2021).","journal-title":"Journal of Big Data"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00100"},{"key":"e_1_3_2_1_24_1","article-title":"Network Cost-Aware Geo-Distributed Data Analytics System","volume":"33","author":"Oh Kwangsung","year":"2021","unstructured":"Kwangsung Oh, Minmin Zhang, Abhishek Chandra, and Jon Weissman. 2021. Network Cost-Aware Geo-Distributed Data Analytics System. IEEE Transactions on Parallel and Distributed Systems 33, 6 (2021).","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Low latency geo-distributed data analytics. ACM SIGCOMM Computer Communication Review","author":"Pu Qifan","year":"2015","unstructured":"Qifan Pu, Ganesh Ananthanarayanan, Peter\u00a0Bodik Kandula, Srikanth Kandula, Aditya Akella, Paramvir Bahl, and Ion Stoica. 2015. Low latency geo-distributed data analytics. ACM SIGCOMM Computer Communication Review (2015)."},{"key":"e_1_3_2_1_26_1","unstructured":"TPC-DS [n. d.]. TPC Decision Support Benchmark. http:\/\/www.tpc.org\/tpcds\/."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc.\u00a0of USENIX OSDI.","author":"Viswanathan Raajay","year":"2016","unstructured":"Raajay Viswanathan, Ganesh Ananthanarayanan, and Aditya Akella. 2016. CLARINET : Wan-aware optimization for analytics queries. In Proc.\u00a0of USENIX OSDI."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"e_1_3_2_1_29_1","volume-title":"Multi-objective optimization of data deployment and scheduling based on the minimum cost in geo-distributed cloud. Computer Communications","author":"Xie Tianxing","year":"2022","unstructured":"Tianxing Xie, Chunlin Li, Na Hao, and Youlong Luo. 2022. Multi-objective optimization of data deployment and scheduling based on the minimum cost in geo-distributed cloud. Computer Communications (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2017.2712773"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755940"},{"key":"e_1_3_2_1_32_1","volume-title":"Proc.\u00a0of USENIX NSDI.","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauly, Michael\u00a0J Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proc.\u00a0of USENIX NSDI."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891053"},{"key":"e_1_3_2_1_34_1","article-title":"Cost-aware partitioning for efficient large graph processing in geo-distributed datacenters","volume":"31","author":"Zhou Amelie\u00a0Chi","year":"2019","unstructured":"Amelie\u00a0Chi Zhou, Bingkun Shen, Yao Xiao, Shadi Ibrahim, and Bingsheng He. 2019. Cost-aware partitioning for efficient large graph processing in geo-distributed datacenters. IEEE Transactions on Parallel and Distributed Systems 31, 7 (2019).","journal-title":"IEEE Transactions on Parallel and Distributed Systems"}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","acronym":"ICPP 2023","location":"Salt Lake City UT USA"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605575","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":34,"alternative-id":["10.1145\/3605573.3605575","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605575","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}