Full metadata record
DC FieldValueLanguage
dc.contributor.authorLin, Pei-Yingen_US
dc.contributor.authorChiu, Hsiao-Tingen_US
dc.contributor.authorGau, Rung-Hungen_US
dc.date.accessioned2019-10-05T00:09:46Z-
dc.date.available2019-10-05T00:09:46Z-
dc.date.issued2019-01-01en_US
dc.identifier.isbn978-1-7281-1217-6en_US
dc.identifier.issn1550-2252en_US
dc.identifier.urihttp://hdl.handle.net/11536/152946-
dc.description.abstractIn this paper, we propose a novel approach for proactive edge caching in wireless small cell networks. Specifically, we propose using a recurrent neural network for predicting the content popularity with low computational complexity. The mean estimation error of the adopted recurrent neural network could be very close to that of the optimal linear prediction filter utilizing all past history. Based on the predicted content popularity, we formulate and solve a minimum cost flow problem in order to optimally place content files at edge caches. Since the computational complexity of the adopted recurrent neural network is relatively low and the minimum cost flow problem can be solved in polynomial time, the proposed approach is feasible in practice. Simulation results show that the proposed approach outperforms a greedy approach and can significantly reduce the bandwidth consumption of the backhaul network.en_US
dc.language.isoen_USen_US
dc.subjectmachine learningen_US
dc.subjectrecurrent neural networksen_US
dc.subjectstochastic processesen_US
dc.subjectwireless small cell networksen_US
dc.subjectproactive cachingen_US
dc.subjectcombinatorial network optimizationen_US
dc.titleMachine Learning-Driven Optimal Proactive Edge Caching in Wireless Small Cell Networksen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2019 IEEE 89TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2019-SPRING)en_US
dc.citation.spage0en_US
dc.citation.epage0en_US
dc.contributor.department電信工程研究所zh_TW
dc.contributor.departmentInstitute of Communications Engineeringen_US
dc.identifier.wosnumberWOS:000482655600306en_US
dc.citation.woscount0en_US
Appears in Collections:Conferences Paper