帶有特征感知的D2D內(nèi)容緩存策略
doi: 10.11999/JEIT190691
-
1.
重慶郵電大學(xué) 通信與信息工程學(xué)院 重慶 400065
-
2.
重慶高校市級(jí)光通信與網(wǎng)絡(luò)重點(diǎn)實(shí)驗(yàn)室 重慶 400065
-
3.
泛在感知與互聯(lián)重慶市重點(diǎn)實(shí)驗(yàn)室 重慶 400065
Feature-Aware D2D Content Caching Strategy
-
1.
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
-
2.
Optical Communication and Networks Key Laboratory of Chongqing, Chongqing 400065, China
-
3.
Ubiquitous Sensing and Networking Key Laboratory of Chongqing, Chongqing 400065, China
-
摘要: 設(shè)備到設(shè)備通信(D2D)可以有效地卸載基站流量,在D2D網(wǎng)絡(luò)中不僅需要共享大眾化內(nèi)容還需要個(gè)性化內(nèi)容緩存。該文對(duì)緩存內(nèi)容選擇問題進(jìn)行了深入研究,提出一種結(jié)合特征感知的內(nèi)容社交價(jià)值預(yù)測(cè)(CSVP)方法。價(jià)值預(yù)測(cè)不僅可以降低時(shí)延也可以減少緩存替換次數(shù)降低緩存成本。首先結(jié)合用戶特征和內(nèi)容特征計(jì)算內(nèi)容當(dāng)前價(jià)值,然后通過用戶社交關(guān)系計(jì)算未來(lái)價(jià)值。微基站根據(jù)內(nèi)容的價(jià)值為用戶提供個(gè)性化內(nèi)容緩存服務(wù),宏基站則在每個(gè)微基站的緩存內(nèi)容中選擇價(jià)值較大部分的內(nèi)容。仿真結(jié)果表明,該文提出的緩存策略可以有效緩解基站流量,與其他方法相比降低時(shí)延約20%~40%。
-
關(guān)鍵詞:
- 邊緣網(wǎng)絡(luò) /
- D2D通信 /
- 內(nèi)容緩存 /
- 探索-利用 /
- 價(jià)值預(yù)測(cè)
Abstract: Device to Device (D2D) communications can effectively offload base station traffic. In D2D networks, the popular content is not only needs to be shared, but also the individual content is needs to be cached. In this paper, the problem of cache content selection is researched. A Content Social Value Prediction(CSVP) method based on feature perception is proposed. Value prediction can not only reduce latency, but also reduce the number of cache replacements and reduce cache costs. Firstly, the current value of content is calculated by combining user features and content features, and then future value is calculated through user social relationships. The small base station provides the user with a personalized content caching service according to the value of the content, and the base station selects a content with a larger value in the individual cache content of each small base station as popular content. Simulation results show that the caching strategy based on the proposed method can alleviate the base station traffic effectively, and reduce the delay by about 20%~40%.-
Key words:
- Edge network /
- D2D communication /
- Content caching /
- Exploration - exploitation /
- Value prediction
-
表 1 算法1 內(nèi)容社交價(jià)值預(yù)測(cè)
輸入:$T,r,\alpha ,\lambda ,{\lambda _1},{\lambda _2},{\beta _1},{\beta _2},\xi $ 輸出:價(jià)值列表,觀察用戶請(qǐng)求情況 (1) 隨機(jī)初始化參數(shù)$\widehat {{U}},\widehat {{C}},{{L}},{{W}}$ (2) For t=1, 2, ···, T do (3) 感知內(nèi)容特征及用戶特征 (4) For all k ∈C do (5) 如果內(nèi)容是新內(nèi)容: (6) 初始化參數(shù):${{{A}}_k} \leftarrow {{{I}}_d}$, ${{{B}}_k} \leftarrow {0_{d*1}}$ (7) 結(jié)束 (8) 更新參數(shù):${\theta _{t,k}} \leftarrow {{A}}_{t,k}^{ - 1}{{{B}}_{t,k}}$,
${P_{t,i,k}} \leftarrow {{X}}_{t,k}^{\rm{T}}{\theta _k} + \alpha \sqrt {{{X}}_{t,k}^{\rm{T}}{{A}}_{t,k}^{ - 1}{{X}}_{t,k}^{\rm{T}}} $,
${{{A}}_{t,k}} \leftarrow {{{A}}_{t,k}} + {{{X}}_{t,k}}{{X}}_{t,k}^{\rm{T}}$, ${{{B}}_{t,k}} \leftarrow {{{B}}_{t,k}} + {r_t}{{{X}}_{t,k}}$(9) 當(dāng)式(29)的值沒有收斂時(shí): (10) 根據(jù)梯度更新參數(shù) (11) 結(jié)束 (12) 計(jì)算未來(lái)價(jià)值 (13) 計(jì)算總價(jià)值 (14) 結(jié)束 (15) 按降序輸出價(jià)值列表,觀察用戶請(qǐng)求情況 (16) 結(jié)束 下載: 導(dǎo)出CSV
表 2 仿真參數(shù)設(shè)置
參數(shù) 參數(shù)值 內(nèi)容庫(kù)數(shù)量 5000 內(nèi)容包大小 20 MB SBS-UE延時(shí) 20 ms BS-UE延時(shí) 50 ms CDN-UE延時(shí) 100 ms D2D延時(shí) 10 ms 下載: 導(dǎo)出CSV
-
Cisco. Cisco visual networking index: Global mobile data traffic forecast update, 2017–2022 white paper[EB/OL]. https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11-738429.html, 2019. REBECCHI F, DE AMORIM M D, and CONAN V. Droid: Adapting to individual mobility pays off in mobile data offloading[C]. 2014 IFIP Networking Conference, Trondheim, Norway, 2014: 1–9. doi: 10.1109/IFIPNetworking.2014.6857087. FANG Chao, YAO Haipeng, WANG Zhuwei, et al. A survey of mobile information-centric networking: research issues and challenges[J]. IEEE Communications Surveys & Tutorials, 2018, 20(3): 2353–2371. doi: 10.1109/COMST.2018.2809670 TATAR A, DE AMORIM M D, FDIDA S, et al. A survey on predicting the popularity of web content[J]. Journal of Internet Services and Applications, 2014, 5(1): 8. doi: 10.1186/s13174-014-0008-y CHANDRASEKARAN G, WANG N, and TAFAZOLLI R. Caching on the move: Towards D2D-based information centric networking for mobile content distribution[C]. The 40th IEEE Conference on Local Computer Networks, Clearwater Beach, USA, 2015: 312–320, doi: 10.1109/LCN.2015.7366325. KHAN F H and KHAN Z. Popularity-aware content caching for distributed wireless helper nodes[J]. Arabian Journal for Science and Engineering, 2017, 42(8): 3375–3389. doi: 10.1007/s13369-017-2505-3 TAGHIZADEH M and BISWAS S. Community based cooperative content caching in social wireless networks[C]. The 14th ACM International Symposium on Mobile Ad Hoc Networking and Computing, Bangalore, India, 2013: 257–262. doi: 10.1145/2491288.2491318. 柴蓉, 王令, 陳明龍, 等. 基于時(shí)延優(yōu)化的蜂窩D2D通信聯(lián)合用戶關(guān)聯(lián)及內(nèi)容部署算法[J]. 電子與信息學(xué)報(bào), 2019, 41(11): 2565–2570. doi: 10.11999/JEIT180408CHAI Rong, WANG Ling, CHEN Minglong, et al. Joint clustering and content deployment algorithm for cellular d2d communication based on delay optimization[J]. Journal of Electronics &Information Technology, 2019, 41(11): 2565–2570. doi: 10.11999/JEIT180408 MEGIDDO N and MODHA D S. ARC: A self-tuning, low overhead replacement cache[C]. The 2nd USENIX Conference on File and Storage Technologies, San Francisco, USA, 2003: 115–130. MEGIDDO N and MODHA D S. Outperforming LRU with an adaptive replacement cache algorithm[J]. Computer, 2004, 37(4): 58–65. doi: 10.1109/MC.2004.1297303 XIANG Lin, Ng D W K, GE Xiaohu, et al. Cache-aided non-orthogonal multiple access: The two-user case[J]. IEEE Journal of Selected Topics in Signal Processing, 2019, 13(3): 436–451. doi: 10.1109/JSTSP.2019.2907864 LI Lihong, CHU Wei, LANGFORD J, et al. A contextual-bandit approach to personalized news article recommendation[C]. The 19th International Conference on World Wide Web, Raleigh, USA, 2010: 661–670. doi: 10.1145/1772690.1772758. ZIPF G K. Selected studies of the principle of relative frequency in language[J]. Language, 1933, 9(1): 89–92. doi: 10.4159/harvard.9780674434929 JIANG Wei, FENG Gang, QIN Shuang, et al. Multi-agent reinforcement learning for efficient content caching in mobile D2D networks[J]. IEEE Transactions on Wireless Communications, 2019, 18(3): 1610–1622. doi: 10.1109/TWC.2019.2894403 WALSH T J, SZITA I, DIUK C, et al. Exploring compact reinforcement-learning representations with linear regression[C]. The 25th Conference on Uncertainty in Artificial Intelligence, Montreal, Canada, 2009, 591–598. MA Hao, ZHOU T C, LYU M R, et al. Improving recommender systems by incorporating social contextual information[J]. ACM Transactions on Information Systems, 2011, 29(2): 1–23. doi: 10.1145/1961209.1961212 YANG Bo, LEI Yu, LIU Jiming, et al. Social collaborative filtering by trust[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8): 1633–1647. doi: 10.1109/TPAMI.2016.2605085 -