{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:53:17Z","timestamp":1773964397827,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Program of Changsha","award":["kh2301011"],"award-info":[{"award-number":["kh2301011"]}]},{"name":"Science and Technology Program of Changsha","award":["kh2301011"],"award-info":[{"award-number":["kh2301011"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373141, 62302157"],"award-info":[{"award-number":["62373141, 62302157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Research Projects of Hunan Province","award":["2024QK2010, 2024QK2009"],"award-info":[{"award-number":["2024QK2010, 2024QK2009"]}]},{"name":"Open Project Fund of the State Key Laboratory of Cyberspace Security Defense","award":["2024-MS-04"],"award-info":[{"award-number":["2024-MS-04"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07465-7","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T18:53:28Z","timestamp":1750704808000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A distributed skewed stream processing system based on scoring high-frequency key perception"],"prefix":"10.1007","volume":"81","author":[{"given":"Jiawei","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaolian","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"7465_CR1","doi-asserted-by":"crossref","unstructured":"Zaharia M, Das T, Li H, Hunter T, Shenker S, Stoica I (2013) Discretized streams: fault-tolerant streaming computation at scale. In: Proceedings of the Twenty-fourth ACM Symposium on Operating Systems Principles, pp 423\u2013438","DOI":"10.1145\/2517349.2522737"},{"key":"7465_CR2","unstructured":"Gu R, Yin H, Zhong W, Yuan C, Huang Y (2022) Meces: latency-efficient rescaling via prioritized state migration for stateful distributed stream processing systems. In: 2022 USENIX Annual Technical Conference (USENIX ATC 22), pp 539\u2013556"},{"issue":"1","key":"7465_CR3","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/s11227-022-04669-z","volume":"79","author":"H Hadian","year":"2023","unstructured":"Hadian H, Farrokh M, Sharifi M, Jafari A (2023) An elastic and traffic-aware scheduler for distributed data stream processing in heterogeneous clusters. The J Supercomput 79(1):461\u2013498","journal-title":"The J Supercomput"},{"key":"7465_CR4","doi-asserted-by":"crossref","unstructured":"Lee G, Maeng J, Park J, Seo J, Cho H, Yang Y, Um T, Lee J, Lee JW, Chun B-G (2023) Flowkv: a semantic-aware store for large-scale state management of stream processing engines. In: Proceedings of the Eighteenth European Conference on Computer Systems, pp 768\u2013783","DOI":"10.1145\/3552326.3567493"},{"issue":"10","key":"7465_CR5","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1109\/TC.2020.3019689","volume":"70","author":"H Chen","year":"2020","unstructured":"Chen H, Zhang F, Jin H (2020) Pstream: a popularity-aware differentiated distributed stream processing system. IEEE Trans Comput 70(10):1582\u20131597","journal-title":"IEEE Trans Comput"},{"key":"7465_CR6","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.ins.2021.10.049","volume":"584","author":"A Otero","year":"2022","unstructured":"Otero A, F\u00e9lix P, M\u00e1rquez DG, Garc\u00eda CA, Caffarena G (2022) A fault-tolerant clustering algorithm for processing data from multiple streams. Inform Sci 584:649\u2013664","journal-title":"Inform Sci"},{"key":"7465_CR7","doi-asserted-by":"crossref","unstructured":"Neumeyer L, Robbins B, Nair A, Kesari A (2010) S4: Distributed stream computing platform. In: 2010 IEEE International Conference on Data Mining Workshops, pp 170\u2013177. IEEE","DOI":"10.1109\/ICDMW.2010.172"},{"key":"7465_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108748","volume":"121","author":"X Xiao","year":"2022","unstructured":"Xiao X, Li C, Jiang B, Cai Q, Li K, Tang Z (2022) Adaptive search strategy based chemical reaction optimization scheme for task scheduling in discrete multiphysical coupling applications. Appl Soft Comput 121:108748","journal-title":"Appl Soft Comput"},{"key":"7465_CR9","doi-asserted-by":"crossref","unstructured":"Del Monte B, Zeuch S, Rabl T, Markl V (2022) Rethinking stateful stream processing with rdma. In: Proceedings of the 2022 International Conference on Management of Data, pp 1078\u20131092","DOI":"10.1145\/3514221.3517826"},{"key":"7465_CR10","unstructured":"Song WW, Um T, Elnikety S, Jeon M, Chun B-G (2023) Sponge: fast reactive scaling for stream processing with serverless frameworks. In: 2023 USENIX Annual Technical Conference (USENIX ATC 23), pp 301\u2013314"},{"issue":"3","key":"7465_CR11","doi-asserted-by":"publisher","first-page":"491","DOI":"10.14778\/3570690.3570699","volume":"16","author":"E Zapridou","year":"2022","unstructured":"Zapridou E, Mytilinis I, Ailamaki A (2022) Dalton: learned partitioning for distributed data streams. Proc VLDB Endowment 16(3):491\u2013504","journal-title":"Proc VLDB Endowment"},{"key":"7465_CR12","doi-asserted-by":"crossref","unstructured":"Liu G, Wang Z, Zhou AC, Mao R (2024) Adaptive key partitioning in distributed stream processing. CCF Transactions on High Performance Computing, 1\u201315","DOI":"10.1007\/s42514-023-00179-3"},{"issue":"8","key":"7465_CR13","doi-asserted-by":"publisher","first-page":"8236","DOI":"10.1007\/s11227-022-04991-6","volume":"79","author":"Q Wang","year":"2023","unstructured":"Wang Q, Zuo D, Zhang Z, Chen S, Liu T (2023) An adaptive non-migrating load-balanced distributed stream window join system. The J Supercomput 79(8):8236\u20138264","journal-title":"The J Supercomput"},{"issue":"4","key":"7465_CR14","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s10723-023-09700-y","volume":"21","author":"L Yang","year":"2023","unstructured":"Yang L, Xiao X, Zhang X, Hu Z, Tang Z (2023) A real-time partition generation mechanism for data skew mitigation in spark computing environment. J Grid Comput 21(4):62","journal-title":"J Grid Comput"},{"key":"7465_CR15","doi-asserted-by":"crossref","unstructured":"Roy P, Khan A, Alonso G (2016) Augmented sketch: Faster and more accurate stream processing. In: Proceedings of the 2016 International Conference on Management of Data, pp 1449\u20131463","DOI":"10.1145\/2882903.2882948"},{"key":"7465_CR16","doi-asserted-by":"crossref","unstructured":"Zhou Y, Yang T, Jiang J, Cui B, Yu M, Li X, Uhlig S (2018) Cold filter: A meta-framework for faster and more accurate stream processing. In: Proceedings of the 2018 International Conference on Management of Data, pp 741\u2013756","DOI":"10.1145\/3183713.3183726"},{"issue":"1","key":"7465_CR17","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.jalgor.2003.12.001","volume":"55","author":"G Cormode","year":"2005","unstructured":"Cormode G, Muthukrishnan S (2005) An improved data stream summary: the count-min sketch and its applications. Journal of Algorithms 55(1):58\u201375","journal-title":"Journal of Algorithms"},{"key":"7465_CR18","doi-asserted-by":"crossref","unstructured":"Gou X, He L, Zhang Y, Wang K, Liu X, Yang T, Wang Y, Cui B (2020) Sliding sketches: A framework using time zones for data stream processing in sliding windows. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1015\u20131025","DOI":"10.1145\/3394486.3403144"},{"key":"7465_CR19","doi-asserted-by":"crossref","unstructured":"Manku GS, Motwani R (2002) Approximate frequency counts over data streams. In: VLDB\u201902: Proceedings of the 28th International Conference on Very Large Databases, pp 346\u2013357 . Elsevier","DOI":"10.1016\/B978-155860869-6\/50038-X"},{"issue":"1","key":"7465_CR20","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1145\/762471.762473","volume":"28","author":"RM Karp","year":"2003","unstructured":"Karp RM, Shenker S, Papadimitriou CH (2003) A simple algorithm for finding frequent elements in streams and bags. ACM Trans Database Syst (TODS) 28(1):51\u201355","journal-title":"ACM Trans Database Syst (TODS)"},{"key":"7465_CR21","doi-asserted-by":"crossref","unstructured":"Metwally A, Agrawal D, Abbadi AE (2005) Efficient computation of frequent and top-k elements in data streams. In: International Conference on Database Theory, pp 398\u2013412. Springer","DOI":"10.1007\/978-3-540-30570-5_27"},{"issue":"1","key":"7465_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00778-009-0172-z","volume":"19","author":"G Cormode","year":"2010","unstructured":"Cormode G, Hadjieleftheriou M (2010) Methods for finding frequent items in data streams. The VLDB J 19(1):3\u201320","journal-title":"The VLDB J"},{"issue":"1","key":"7465_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-009-0267-2","volume":"26","author":"H Liu","year":"2011","unstructured":"Liu H, Lin Y, Han J (2011) Methods for mining frequent items in data streams: an overview. Knowl Inform Syst 26(1):1\u201330","journal-title":"Knowl Inform Syst"},{"key":"7465_CR24","doi-asserted-by":"crossref","unstructured":"Shahout R, Mitzenmacher M (2024) Learning-based heavy hitters and flow frequency estimation in streams. In: 2024 IEEE 32nd International Conference on Network Protocols (ICNP), pp 1\u201313 . IEEE","DOI":"10.1109\/ICNP61940.2024.10858542"},{"key":"7465_CR25","doi-asserted-by":"crossref","unstructured":"Charikar M, Chen K, Farach-Colton M (2002) Finding frequent items in data streams. In: International Colloquium on Automata, Languages, and Programming, pp 693\u2013703 Springer","DOI":"10.1007\/3-540-45465-9_59"},{"issue":"1","key":"7465_CR26","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1145\/1061318.1061325","volume":"30","author":"G Cormode","year":"2005","unstructured":"Cormode G, Muthukrishnan S (2005) What\u2019s hot and what\u2019s not: tracking most frequent items dynamically. ACM Trans Database Syst (TODS) 30(1):249\u2013278","journal-title":"ACM Trans Database Syst (TODS)"},{"key":"7465_CR27","unstructured":"Nguyen TT, Musco CN (2024) Partitioned-Learned Count-Min Sketch. https:\/\/openreview.net\/forum?id=7W4boWjb3Q"},{"key":"7465_CR28","doi-asserted-by":"crossref","unstructured":"Ma K, Liu S, Lin Y, Yu Z, Ji K (2017) Parallel grouping particle swarm optimization with stream processing paradigm. In: 2017 IEEE 19th International Conference on High Performance Computing and Communications Workshops (HPCCWS), pp 22\u201326 . IEEE","DOI":"10.1109\/HPCCWS.2017.00010"},{"issue":"2","key":"7465_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3303849","volume":"52","author":"H R\u00f6ger","year":"2019","unstructured":"R\u00f6ger H, Mayer R (2019) A comprehensive survey on parallelization and elasticity in stream processing. ACM Comput Surv (CSUR) 52(2):1\u201337","journal-title":"ACM Comput Surv (CSUR)"},{"key":"7465_CR30","doi-asserted-by":"crossref","unstructured":"Fang J, Zhang R, Fu TZ, Zhang Z, Zhou A, Zhu J (2017) Parallel stream processing against workload skewness and variance. In: Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing, pp 15\u201326","DOI":"10.1145\/3078597.3078613"},{"issue":"4","key":"7465_CR31","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/s00778-013-0335-9","volume":"23","author":"B Gedik","year":"2014","unstructured":"Gedik B (2014) Partitioning functions for stateful data parallelism in stream processing. The VLDB J 23(4):517\u2013539","journal-title":"The VLDB J"},{"key":"7465_CR32","doi-asserted-by":"crossref","unstructured":"Guo Q, Zhou Y (2017) Stateful load balancing for parallel stream processing. In: European Conference on Parallel Processing, pp 80\u201393. Springer","DOI":"10.1007\/978-3-319-75178-8_7"},{"key":"7465_CR33","doi-asserted-by":"crossref","unstructured":"Rivetti N, Querzoni L, Anceaume E, Busnel Y, Sericola B (2015) Efficient key grouping for near-optimal load balancing in stream processing systems. In: Proceedings of the 9th ACM International Conference on Distributed Event-Based Systems, pp 80\u201391","DOI":"10.1145\/2675743.2771827"},{"key":"7465_CR34","doi-asserted-by":"crossref","unstructured":"Nasir MAU, Morales GDF, Garcia-Soriano D, Kourtellis N, Serafini M (2015) The power of both choices: Practical load balancing for distributed stream processing engines. In: 2015 IEEE 31st International Conference on Data Engineering, pp 137\u2013148 . IEEE","DOI":"10.1109\/ICDE.2015.7113279"},{"key":"7465_CR35","doi-asserted-by":"crossref","unstructured":"Nasir MAU, Morales GDF, Kourtellis N, Serafini M (2016) When two choices are not enough: Balancing at scale in distributed stream processing. In: 2016 IEEE 32nd International Conference on Data Engineering (ICDE), pp 589\u2013600. IEEE","DOI":"10.1109\/ICDE.2016.7498273"},{"issue":"4","key":"7465_CR36","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1145\/285243.285287","volume":"28","author":"L Fan","year":"1998","unstructured":"Fan L, Cao P, Almeida J, Broder AZ (1998) Summary cache: a scalable wide-area web cache sharing protocol. ACM SIGCOMM Comput Commun Rev 28(4):254\u2013265","journal-title":"ACM SIGCOMM Comput Commun Rev"},{"issue":"11","key":"7465_CR37","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1016\/j.comnet.2009.02.019","volume":"53","author":"G Urdaneta","year":"2009","unstructured":"Urdaneta G, Pierre G, Van Steen M (2009) Wikipedia workload analysis for decentralized hosting. Comput Netw 53(11):1830\u20131845","journal-title":"Comput Netw"},{"key":"7465_CR38","doi-asserted-by":"crossref","unstructured":"Zhang Y, Liu Z, Wang R, Yang T, Li J, Miao R, Liu P, Zhang R, Jiang J (2021) Cocosketch: High-performance sketch-based measurement over arbitrary partial key query. In: Proceedings of the 2021 ACM SIGCOMM 2021 Conference, pp 207\u2013222","DOI":"10.1145\/3452296.3472892"},{"key":"7465_CR39","doi-asserted-by":"crossref","unstructured":"Wu Y, Jiang S, Dong S, Zhong Z, Chen J, Hu Y, Yang T, Uhlig S, Cui B (2023) Microscopesketch: Accurate sliding estimation using adaptive zooming. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp 2660\u20132671","DOI":"10.1145\/3580305.3599432"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07465-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07465-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07465-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T18:53:33Z","timestamp":1750704813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07465-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":39,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7465"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07465-7","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"16 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Written informed consent for publication was obtained from all participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"1073"}}