{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:44:48Z","timestamp":1791391488198,"version":"4.3.3"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62125206"],"award-info":[{"award-number":["62125206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Major Program of the National Natural Science Foundation of Zhejiang","award":["LD24F020014"],"award-info":[{"award-number":["LD24F020014"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Auton. Adapt. Syst."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>In the field of edge computing, the increasing demand for high Quality of Service (QoS), particularly in dynamic multimedia streaming applications (e.g., Augmented Reality\/Virtual Reality and online gaming), has prompted the need for effective solutions. Nevertheless, adopting an edge paradigm grounded in distributed computing has exacerbated the issue of tail latency. Given a limited variety of multimedia services supported by edge servers and the dynamic nature of user requests, employing traditional queuing methods to model tail latency in distributed edge computing is challenging, substantially exacerbating head-of-line (HoL) blocking. In response to this challenge, we have developed a learning-based scheduling method to mitigate the overall tail latency, which adaptively selects appropriate edge servers for execution as incoming distributed tasks vary with unknown size. To optimize the utilization of the edge computing paradigm, we leverage the Laplace transform to theoretically derive an upper bound for the response time of edge servers. Subsequently, we integrate this upper bound into reinforcement learning to facilitate tail-learning and enable informed decisions for autonomous distributed scheduling. The experiment results demonstrate the efficiency in reducing tail latency compared to existing methods.<\/jats:p>","DOI":"10.1145\/3737289","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T12:36:37Z","timestamp":1748349397000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Tail-Learning: Adaptive Learning Method for Mitigating Tail Latency in Autonomous Edge Systems"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5788-6542","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University of Finance and Economics, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1167-5387","authenticated-orcid":false,"given":"Yinuo","family":"Deng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2850-6815","authenticated-orcid":false,"given":"Hailiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3924-6561","authenticated-orcid":false,"given":"Tianlv","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-6095","authenticated-orcid":false,"given":"Shuiguang","family":"Deng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8056997"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10165515"},{"key":"e_1_3_2_4_2","volume-title":"Deep Learning","author":"Bengio Yoshua","year":"2017","unstructured":"Yoshua Bengio, Ian Goodfellow, and Aaron Courville. 2017. Deep Learning. Vol. 1. MIT Press. Cambridge, MA, USA."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2018.2816263"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400831470"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS51825.2021.9484492"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456238"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108591034"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194017500334"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139226424"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/SmartWorld.2018.00118"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11678"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/1096491"},{"key":"e_1_3_2_17_2","volume-title":"Designing Data-Intensive Applications: The Big Ideas behind Reliable, Scalable, and Maintainable Systems","author":"Kleppmann Martin","year":"2017","unstructured":"Martin Kleppmann. 2017. Designing Data-Intensive Applications: The Big Ideas behind Reliable, Scalable, and Maintainable Systems. O\u2019Reilly Media, Inc."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380117"},{"issue":"2","key":"e_1_3_2_19_2","first-page":"1","article-title":"Enki: A diversity-driven approach to test and train robust learning-enabled systems","volume":"15","author":"Langford Michael Austin","year":"2021","unstructured":"Michael Austin Langford and Betty H. C. Cheng. 2021. Enki: A diversity-driven approach to test and train robust learning-enabled systems. ACM Transactions on Autonomous and Adaptive Systems (TAAS) 15, 2 (2021), 1\u201332.","journal-title":"ACM Transactions on Autonomous and Adaptive Systems (TAAS)"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.14778\/3538598.3538600"},{"key":"e_1_3_2_21_2","article-title":"Reinforcement learning based edge-end collaboration for multi-task scheduling in 6G enabled intelligent autonomous transport systems","author":"Li Peisong","year":"2025","unstructured":"Peisong Li, Ziren Xiao, Honghao Gao, Xinheng Wang, and Ye Wang. 2025. Reinforcement learning based edge-end collaboration for multi-task scheduling in 6G enabled intelligent autonomous transport systems. IEEE Transactions on Intelligent Transportation Systems. DOI: 10.1109\/TITS.2024.3525356","journal-title":"IEEE Transactions on Intelligent Transportation Systems. DOI: 10.1109\/TITS.2024.3525356"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582080"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620881"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885778"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2780236"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132618"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3429441"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2019.00031"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00026"},{"key":"e_1_3_2_30_2","volume-title":"Probability and Computing: Randomization and Probabilistic Techniques in Algorithms and Data Analysis","author":"Mitzenmacher Michael","year":"2017","unstructured":"Michael Mitzenmacher and Eli Upfal. 2017. Probability and Computing: Randomization and Probabilistic Techniques in Algorithms and Data Analysis. Cambridge University Press."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617835"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00023"},{"key":"e_1_3_2_33_2","unstructured":"Alexander No\u00e9. 2007. Matroska file format (under construction!). Retrieved January 19 2011 from http:\/\/web.archive.orgweb\/20070821155146\/www.matroska.org\/technical\/specs\/matroska.pdf"},{"key":"e_1_3_2_34_2","volume-title":"Modern Control Engineering (5th ed.)","author":"Ogata Katsuhiko","year":"2010","unstructured":"Katsuhiko Ogata. 2010. Modern Control Engineering (5th ed.). Pearson."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605552"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16123"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2019.00034"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3239339"},{"key":"e_1_3_2_39_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. MIT Press."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2971325"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3344341.3368816"},{"key":"e_1_3_2_43_2","unstructured":"The Verge. n.d. Niantic\u2019s New AR Features for Pok\u00e9mon Go Aim to Blend the Virtual and Real Worlds. Retrieved from https:\/\/www.theverge.com\/2020\/5\/26\/21269862\/niantic-pokemon-go-reality-blending-ar-features-release-update"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2920835"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.07.007"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2667522.2667524"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815358"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3172121"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00331"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3123535"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3304112.3325612"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547807"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2020.3013600"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2019.00041"}],"container-title":["ACM Transactions on Autonomous and Adaptive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3737289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T13:29:02Z","timestamp":1764163742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3737289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":54,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3737289"],"URL":"https:\/\/doi.org\/10.1145\/3737289","relation":{},"ISSN":["1556-4665","1556-4703"],"issn-type":[{"value":"1556-4665","type":"print"},{"value":"1556-4703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"assertion":[{"value":"2023-12-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}