{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:11:41Z","timestamp":1775229101829,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T00:00:00Z","timestamp":1620259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T00:00:00Z","timestamp":1620259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872044"],"award-info":[{"award-number":["61872044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of Beijing Key Laboratory of Internet Culture and Digital Dissemination Research","award":["ICDDXN001"],"award-info":[{"award-number":["ICDDXN001"]}]},{"name":"Beijing Municipal Program for Top Talent"},{"name":"Beijing Municipal Program for Top Talent Cultivation","award":["CIT&TCD201804055"],"award-info":[{"award-number":["CIT&TCD201804055"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Peer-to-Peer Netw. Appl."],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s12083-021-01146-x","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T19:02:29Z","timestamp":1620327749000},"page":"3946-3958","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep reinforcement learning-based incentive mechanism design for short video sharing through D2D communication"],"prefix":"10.1007","volume":"14","author":[{"given":"Zhuo","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,6]]},"reference":[{"key":"1146_CR1","unstructured":"DouYin, https:\/\/www.douyin.com\/. Accessed 1 Nov 2020"},{"key":"1146_CR2","unstructured":"Youtube Go, https:\/\/www.youtube.com\/. Accessed 1 Nov 2020"},{"key":"1146_CR3","unstructured":"KuaiShou, https:\/\/www.kuaishou.com\/. Accessed 1 Nov 2020"},{"key":"1146_CR4","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.techfore.2018.03.016","volume":"133","author":"E Oughton","year":"2018","unstructured":"Oughton E, Frias Z, Russell T, et al. (2018) Towards 5g: scenario-based assessment of the future supply and demand for mobile telecommunications infrastructure. Technol Forecast Soc Chang 133:141\u2013155","journal-title":"Technol Forecast Soc Chang"},{"key":"1146_CR5","unstructured":"Cisco Annual Internet Report (2018\u20132023) White Paper, https:\/\/www.cisco.com\/c\/en\/us\/solutions\/collateral\/executive-perspectives\/annual-internet-report\/white-paper-c11-741490.htmlhttps:\/\/www.cisco.com\/c\/en\/us\/solutions\/collateral\/executive-perspectives\/annual-internet-report\/white-paper-c11-741490.html. Accessed 1 Nov 2020"},{"key":"1146_CR6","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1109\/MNET.001.1900345","volume":"34","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, et al. (2020) Autosight: distributed edge caching in short video network. IEEE Netw 34:194\u2013199","journal-title":"IEEE Netw"},{"key":"1146_CR7","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1109\/COMST.2017.2787609","volume":"20","author":"IU Din","year":"2018","unstructured":"Din IU, Hassan S, Khan MK, Guizani M, Ghazali O, Habbal A (2018) Caching in information-centric networking: strategies, challenges, and future research directions. IEEE Communications Surveys & Tutorials 20:1443\u20131474","journal-title":"IEEE Communications Surveys & Tutorials"},{"issue":"8","key":"1146_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MCOM.2014.6871674","volume":"52","author":"E Bastug","year":"2014","unstructured":"Bastug E, Bennis M, Debbah M (2014) Living on the edge: the role of proactive caching in 5G wireless networks. IEEE Commun Mag 52(8):82\u201389","journal-title":"IEEE Commun Mag"},{"key":"1146_CR9","doi-asserted-by":"crossref","unstructured":"Chen Z, Kountouris M (2016) D2D caching vs. small cell caching: where to cache content in a wireless network?. In: 2016 IEEE 17th international workshop on signal processing advances in wireless communications (SPAWC), pp 1\u20136","DOI":"10.1109\/SPAWC.2016.7536874"},{"key":"1146_CR10","doi-asserted-by":"crossref","unstructured":"Wu D, Zhou L, Cai Y, Qian Y (2018) Collaborative caching and matching for D2D content sharing. In: IEEE wireless communications, vol 25, pp 43\u201349","DOI":"10.1109\/MWC.2018.1700325"},{"key":"1146_CR11","doi-asserted-by":"crossref","unstructured":"Yu X, Tan C, Ma L, Zheng M, Bu Z (2017) Maximized traffic offloading by content sharing in D2D communication. In: 2017 IEEE 86th vehicular technology conference (VTC-Fall), pp 1\u20135","DOI":"10.1109\/VTCFall.2017.8288094"},{"issue":"4","key":"1146_CR12","first-page":"1801","volume":"16","author":"A Asadi","year":"2014","unstructured":"Asadi A, Wang Q, Mancuso V (2014) A survey on device-to-device communication in cellular networks. IEEE Commun 16(4):1801\u20131819","journal-title":"IEEE Commun"},{"issue":"11","key":"1146_CR13","doi-asserted-by":"publisher","first-page":"2571","DOI":"10.1109\/TMM.2017.2700621","volume":"19","author":"D Wu","year":"2017","unstructured":"Wu D, Zhou L, Cai Y (2017) Social-aware rate based content sharing mode selection for D2D content sharing scenarios. IEEE Transactions on Multimedia 19(11):2571\u20132582","journal-title":"IEEE Transactions on Multimedia"},{"key":"1146_CR14","doi-asserted-by":"crossref","unstructured":"Chen Z, Liu Y, Zhou B, Tao M (2016) Caching incentive design in wireless D2D networks: a Stackelberg game approach. In: 2016 IEEE international conference on communications (ICC), Kuala Lumpur, pp 1\u20136","DOI":"10.1109\/ICC.2016.7511284"},{"key":"1146_CR15","doi-asserted-by":"crossref","unstructured":"Satyanarayanan M (2017) The emergence of edge computing, vol 50, pp 30\u201339","DOI":"10.1109\/MC.2017.9"},{"key":"1146_CR16","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1007\/s12083-018-0695-4","volume":"12","author":"M Zhao","year":"2019","unstructured":"Zhao M, Wang W, Wang Y et al (2019) Load scheduling for distributed edge computing: a communication-computation tradeoff. Peer-to-Peer Netw Appl 12:1418\u20131432","journal-title":"Peer-to-Peer Netw Appl"},{"issue":"2","key":"1146_CR17","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1109\/COMST.2019.2894727","volume":"21","author":"R Yang","year":"2019","unstructured":"Yang R, Yu FR, Si P, Yang Z, Zhang Y (2019) Integrated blockchain and edge computing systems: a survey, some research issues and challenges. IEEE Communications Surveys & Tutorials 21(2):1508\u20131532","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"1146_CR18","doi-asserted-by":"crossref","unstructured":"Imran A, Zoha A (2014) Challenges in 5G: how to empower SON with big data for enabling 5G. Network IEEE 28(6)","DOI":"10.1109\/MNET.2014.6963801"},{"key":"1146_CR19","doi-asserted-by":"crossref","unstructured":"Al-Habashna A, Wainer G (2020) QoE awareness in progressive caching and DASH-based D2D video streaming in cellular networks[J]. Wireless Networks: The Journal of Mobile Communication, Computation and Information 26(3)","DOI":"10.1007\/s11276-019-02055-x"},{"issue":"4","key":"1146_CR20","first-page":"978","volume":"35","author":"Y Pan","year":"2017","unstructured":"Pan Y, Pan C, Zhu H, Ahmed QZ, Chen M, Wang J (2017) On consideration of content preference and sharing willingness in D2D assisted offloading. IEEE Journal on Selected Areas in Communications 35(4):978\u2013993","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"1","key":"1146_CR21","doi-asserted-by":"publisher","first-page":"28","DOI":"10.23919\/JCC.2020.01.002","volume":"17","author":"Q Sun","year":"2020","unstructured":"Sun Q, Tian L, Zhou Y, Shi J, Zhang Z (2020) Incentive scheme for slice cooperation based on D2D communication in 5G networks. China Communications 17(1):28\u201341","journal-title":"China Communications"},{"issue":"10","key":"1146_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSAC.2015.2435356","volume":"33","author":"Y Zhang","year":"2015","unstructured":"Zhang Y, Song L, Saad W et al (2015) Contract-based incentive mechanisms for device-to-device communications in cellular networks. IEEE Journal on Selected Areas in Communications 33(10):1\u20131","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"1146_CR23","doi-asserted-by":"crossref","unstructured":"Yang L, Zhu H, Wang H et al (2019) Incentive propagation mechanism of computation offloading in fog-enabled D2D networks. In: 2018 IEEE 23rd international conference on digital signal processing (DSP)","DOI":"10.1109\/ICDSP.2018.8631842"},{"issue":"4","key":"1146_CR24","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1109\/TVT.2019.2894851","volume":"68","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Liu P, Feng J et al (2019) Computation resource allocation and task assignment optimization in vehicular fog computing: a contract-matching approach. IEEE Transactions on Vehicular Technology 68(4):3113\u20133125","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"1146_CR25","doi-asserted-by":"crossref","unstructured":"Jiang J, Zhang S, Li B et al (2015) Maximized cellular traffic offloading via device-to-device content sharing, vol 34, pp 82\u201391","DOI":"10.1109\/JSAC.2015.2452493"},{"issue":"1","key":"1146_CR26","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/JSAC.2015.2452493","volume":"34","author":"J Jiang","year":"2015","unstructured":"Jiang J, Zhang S, Li B et al (2015) Maximized cellular traffic offloading via device-to-device content sharing. IEEE Journal on Selected Areas in Communications 34(1):82\u201391","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"3","key":"1146_CR27","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MNET.2019.1800386","volume":"33","author":"D Zeng","year":"2019","unstructured":"Zeng D, Gu L, Pan S, Cai J, Guo S (2019) Resource management at the network edge: a deep reinforcement learning approach. IEEE Network 33(3):26\u201333","journal-title":"IEEE Network"},{"issue":"10","key":"1146_CR28","doi-asserted-by":"publisher","first-page":"2316","DOI":"10.1109\/TMC.2019.2927314","volume":"19","author":"Y Zhan","year":"2020","unstructured":"Zhan Y, Liu CH, Zhao Y, Zhang J, Tang J (2020) Free market of multi-leader multi-follower mobile crowdsensing: an incentive mechanism design by deep reinforcement learning. IEEE Transactions on Mobile Computing 19(10):2316\u20132329","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"4","key":"1146_CR29","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TITS.2020.3014263","volume":"22","author":"Y Zhao","year":"2021","unstructured":"Zhao Y, Liu CH (2021) Social-aware incentive mechanism for vehicular crowdsensing by deep reinforcement learning. IEEE Trans Intell Transp Syst 22(4):2314\u20132325","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"7","key":"1146_CR30","doi-asserted-by":"publisher","first-page":"6360","DOI":"10.1109\/JIOT.2020.2967772","volume":"7","author":"Y Zhan","year":"2020","unstructured":"Zhan Y, Li P, Qu Z, Zeng D, Guo S (2020) A learning-based incentive mechanism for federated learning. IEEE Internet of Things Journal 7(7):6360\u20136368","journal-title":"IEEE Internet of Things Journal"},{"issue":"4","key":"1146_CR31","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/MNET.001.1900215","volume":"34","author":"R Zhang","year":"2020","unstructured":"Zhang R, Yu FR, Liu J et al (2020) Blockchain-incentivized D2D and mobile edge caching: a deep reinforcement learning approach. IEEE Network 34(4):150\u2013157","journal-title":"IEEE Network"},{"issue":"7540","key":"1146_CR32","first-page":"529","volume":"518","author":"M Volodymyr","year":"2019","unstructured":"Volodymyr M, Koray K, David S et al (2019) Human-level control through deep reinforcement learning. Nature 518(7540):529\u201333","journal-title":"Nature"},{"key":"1146_CR33","doi-asserted-by":"crossref","unstructured":"Chen M, Wang H, Chu X (2020) Continuous incentive mechanism for d2d content sharing: a deep reinforcement learning approach. In: 2020 IEEE international conference on communications workshops (ICC Workshops), pp 1\u20136","DOI":"10.1109\/ICCWorkshops49005.2020.9145226"},{"key":"1146_CR34","doi-asserted-by":"crossref","unstructured":"Zhao N, Liang Y, Pei Y (2018) Dynamic contract incentive mechanism for cooperative wireless networks. In: IEEE transactions on vehicular technology, vol 67, pp 10970\u201310982","DOI":"10.1109\/TVT.2018.2865951"},{"key":"1146_CR35","doi-asserted-by":"crossref","unstructured":"Wang H, Yang Y, Wang E, Wang L, Li Q, Yu Z (2020) Incentive mechanism for mobile devices in dynamic crowd sensing system. In: IEEE transactions on human-machine systems","DOI":"10.1109\/THMS.2020.3032102"},{"key":"1146_CR36","doi-asserted-by":"crossref","unstructured":"Wang H, Guo S, Cao J, Guo M (2018) Melody: a long-term dynamic quality-aware incentive mechanism for crowd sourcing. In: IEEE transactions on parallel and distributed systems, vol 29, pp 901\u2013914","DOI":"10.1109\/TPDS.2017.2775232"},{"key":"1146_CR37","doi-asserted-by":"crossref","unstructured":"Zhang T, Wang H, He J (2016) An incentive mechanism under Hidden-Action for device-to-device content sharing. In: 2016 IEEE 13th international conference on signal processing (ICSP), pp 1288\u20131292","DOI":"10.1109\/ICSP.2016.7878034"},{"issue":"4","key":"1146_CR38","doi-asserted-by":"publisher","first-page":"1801","DOI":"10.1109\/COMST.2014.2319555","volume":"16","author":"A Asadi","year":"2014","unstructured":"Asadi A, Wang Q, Mancuso V (2014) A survey on device-to-device communication in cellular networks. IEEE Communications Surveys & Tutorials 16(4):1801\u20131819","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"1146_CR39","doi-asserted-by":"crossref","unstructured":"La QD, Quek TQS, Lee J et al (2016) Deceptive attack and defense game in honeypot-enabled networks for the internet of things, vol 3, pp 1025\u20131035","DOI":"10.1109\/JIOT.2016.2547994"},{"issue":"2","key":"1146_CR40","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/JSAC.2019.2959182","volume":"38","author":"L Gu","year":"2020","unstructured":"Gu L, Zeng D, Li W, Guo S, Zomaya AY, Jin H (2020) Intelligent VNF orchestration and flow scheduling via model-assisted deep reinforcement learning. IEEE Journal on Selected Areas in Communications 38(2):279\u2013291","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"1146_CR41","unstructured":"Sutton RS, Mcallester D, Singh S et al (1999) Policy gradient methods for reinforcement learning with function approximation. Submitted to Advances in Neural Information Processing Systems"},{"key":"1146_CR42","unstructured":"Van Hasselt H, Guez A, Silver D (2015) Deep reinforcement learning with double q-learning. arXiv:1509.06461"},{"issue":"6","key":"1146_CR43","first-page":"A187","volume":"8","author":"TP Lillicrap","year":"2015","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A et al (2015) Continuous control with deep reinforcement learning. Computerence 8(6):A187","journal-title":"Computerence"},{"key":"1146_CR44","unstructured":"Mnih V, Badia AP, Mirza M et al (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp 1928\u20131937"},{"key":"1146_CR45","doi-asserted-by":"crossref","unstructured":"Li Z, Chen H, Lin K et al (2021) From edge data to recommendation: a double attention-based deformable convolutional network. Peer-to-Peer Netw Appl","DOI":"10.1007\/s12083-020-01037-7"}],"container-title":["Peer-to-Peer Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-021-01146-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12083-021-01146-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-021-01146-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,23]],"date-time":"2021-10-23T12:33:37Z","timestamp":1634992417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12083-021-01146-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,6]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1146"],"URL":"https:\/\/doi.org\/10.1007\/s12083-021-01146-x","relation":{},"ISSN":["1936-6442","1936-6450"],"issn-type":[{"value":"1936-6442","type":"print"},{"value":"1936-6450","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,6]]},"assertion":[{"value":"30 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}