虛擬網(wǎng)絡(luò)切片中的在線異常檢測(cè)算法研究

王威麗; 陳前斌; 唐倫

doi:10.11999/JEIT190531

虛擬網(wǎng)絡(luò)切片中的在線異常檢測(cè)算法研究

doi: 10.11999/JEIT190531 cstr: 32379.14.JEIT190531

1.
重慶郵電大學(xué)通信與信息工程學(xué)院重慶 400065
2.
重慶郵電大學(xué)移動(dòng)通信重點(diǎn)實(shí)驗(yàn)室重慶 400065

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(61571073)，重慶市教委科學(xué)技術(shù)研究項(xiàng)目(KJZD-M201800601)

詳細(xì)信息

作者簡(jiǎn)介:
王威麗：女，1994年生，博士生，研究方向?yàn)樘摂M化網(wǎng)絡(luò)切片、人工智能算法等

陳前斌：男，1967年生，教授，博士生導(dǎo)師，研究方向?yàn)閭€(gè)人通信、多媒體信息處理與傳輸、下一代移動(dòng)通信網(wǎng)絡(luò)

唐倫：男，1973年生，教授，博士生導(dǎo)師，研究方向?yàn)樾乱淮鸁o(wú)線通信網(wǎng)絡(luò)、異構(gòu)蜂窩網(wǎng)絡(luò)

通訊作者:
陳前斌　cqb@cqupt.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問(wèn)數(shù): 2838
- HTML全文瀏覽量: 1034
- PDF下載量: 92
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-07-15
- 修回日期: 2020-02-12
- 網(wǎng)絡(luò)出版日期: 2020-03-03
- 刊出日期: 2020-06-22

Online Anomaly Detection for Virtualized Network Slicing

1.
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
2.
Key Laboratory of Mobile Communications, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Funds: The National Natural Science Foundation of China (61571073), The Science and Technology Research Program of Chongqing Municipal Education Commission (KJZD-M201800601)

摘要

摘要:
在虛擬化網(wǎng)絡(luò)切片場(chǎng)景中，底層物理網(wǎng)絡(luò)中一個(gè)物理節(jié)點(diǎn)(PN)或一條物理鏈路(PL)的異常會(huì)造成多個(gè)網(wǎng)絡(luò)切片的性能退化。因網(wǎng)絡(luò)中每個(gè)時(shí)刻都會(huì)產(chǎn)生新的測(cè)量數(shù)據(jù)，該文設(shè)計(jì)了兩種在線異常檢測(cè)算法實(shí)時(shí)監(jiān)督物理網(wǎng)絡(luò)的工作狀態(tài)。首先，該文提出了一種基于在線一類支持向量機(jī)(OCSVM)的PN異常檢測(cè)算法，該算法可根據(jù)每個(gè)時(shí)刻虛擬節(jié)點(diǎn)(VNs)的新測(cè)量數(shù)據(jù)進(jìn)行模型參數(shù)的更新而不需要任何標(biāo)簽數(shù)據(jù)；其次，基于虛擬鏈路兩端點(diǎn)間測(cè)量數(shù)據(jù)的自然相關(guān)性，該文提出基于在線典型相關(guān)分析(CCA)的PL異常檢測(cè)算法，該算法只需要少量標(biāo)簽數(shù)據(jù)就可以準(zhǔn)確分析出PL的異常情況。仿真結(jié)果驗(yàn)證了該文所提在線異常檢測(cè)算法的有效性和魯棒性。
- 虛擬網(wǎng)絡(luò)切片 /
- 異常檢測(cè) /
- 在線一類支持向量機(jī) /
- 在線典型相關(guān)分析
Abstract:
In virtualized network slicing scenario, one anomaly Physical Node (PN) or Physical Link (PL) in substrate networks will cause performance degradation of multiple network slices. For new measurements are achieved in each period, two online anomaly detection algorithms to monitor the working states of substrate networks in real time are designed. An online One-Class Support Vector Machine (OCSVM) algorithm is first proposed in this paper to detect the working states of PNs. Without requiring any labeled data, the model parameters of OCSVM can be updated based on the new measurements of Virtual Nodes (VNs) in each iteration. Then, an online Canonical Correlation Analysis (CCA) based PL anomaly detection algorithm is proposed according to the natural correlation of measurements between neighboring VNs of virtual links. With a small amount of labeled data, the algorithm can accurately analyze the working states of PLs. The simulation results verify the effectiveness and robustness of the proposed online anomaly detection algorithms for the virtualized network slicing.
- Virtualized network slicing /
- Anomaly detection /
- Online One-Class Support Vector Machine (OCSVM) /
- Online Canonical Correlation Analysis (CCA)

HTML全文

圖 1 網(wǎng)絡(luò)切片管理示意圖

下載: 全尺寸圖片幻燈片

圖 2 在線OCSVM算法和經(jīng)典OCSVM算法的性能對(duì)比圖

下載: 全尺寸圖片幻燈片

圖 3 在線OCSVM算法中${{w}}$和$\rho $的收斂過(guò)程

下載: 全尺寸圖片幻燈片

圖 4 在線CCA算法和CCA算法的性能對(duì)比圖

下載: 全尺寸圖片幻燈片

圖 5 在線異常檢測(cè)算法在真實(shí)網(wǎng)絡(luò)數(shù)據(jù)集上的性能對(duì)比圖

下載: 全尺寸圖片幻燈片

表 1 基于在線OCSVM的PN異常檢測(cè)算法

初始化：總迭代次數(shù)$T$，特征空間維度$D$，隨機(jī)初始化PN $q(0 \le q \le Q)$的估計(jì)值${{{w}}_q}(0),{\rho _q}(0)$和${\xi _q}(0)$
(1) for $t = 0,1,2,···,T$ do
(2)　PN $q$產(chǎn)生新的訓(xùn)練樣本${{{x}}_q}(t)$，使用隨機(jī)近似函數(shù)計(jì)算$\varphi ({{{x}}_q}(t))$的近似值${z_q}(t)$
(3)　根據(jù)式(8a)、式(8b)和式(8c)計(jì)算${{\text{?}} _{ { {{w} }_q} } }{f_q}(t),{{\text{?}}_{ {\rho _q} } }{f_q}(t)$和${{\text{?}} _{ {\xi _q} } }{f_q}(t)$
(4)　根據(jù)式(7a)、式(7b)和式(7c)計(jì)算${{{w}}_q}(t),{\rho _q}(t)$和${\xi _q}(t)$
(5)　計(jì)算$g({{{x}}_q}(t)) = {\rm{sgn}} ({{{w}}^{\rm{T}}}(t) \cdot {{{z}}_q}(t) - \rho (t))$
(6)　　if $g({{{x}}_q}(t)) = = 1$ then
(7)　　　判定當(dāng)前時(shí)刻PN $q$為正常節(jié)點(diǎn)，更新參數(shù)${{{w}}_q}(t),{\rho _q}(t)$和${\xi _q}(t)$
(8)　　else
(9)　　判定當(dāng)前時(shí)刻PN $q$為異常節(jié)點(diǎn)，保留$t - 1$時(shí)刻參數(shù)值，丟棄當(dāng)前值
(10) end for

下載: 導(dǎo)出CSV

表 2 基于在線CCA的PL異常檢測(cè)算法

初始化：初始標(biāo)簽采樣個(gè)數(shù)$t$，映射到物理路徑${\rm{P}}{{\rm{N}}_m}\mathop \to \limits^{{\rm{P}}{{\rm{L}}_{m,m + 1}}} {\rm{P}}{{\rm{N}}_{m + 1}}$兩端的${\rm{VN}}{{\rm{F}}_l}$和${\rm{VN}}{{\rm{F}}_{l + 1}}$測(cè)量數(shù)據(jù)${{U}}(t)$和${{Y}}(t)$，控制門限值$T_{r,{\rm{cl}}}^2$，迭　代次數(shù)$T$
(1)計(jì)算${{U}}(t)$和${{Y}}(t)$的協(xié)方差矩陣和均值向量：${{{\varSigma}} _{{{U}}(t)}},{{{\varSigma}} _{{{Y}}(t)}},{{{\varSigma}} _{{{U}}(t){{Y}}(t)}},[{c_1}(t)\;...\;{c_p}(t)]$和$[{d_1}(t)\;...\;{d_q}(t)]$
(2) for $t = t + 1:T$ do
(3)　根據(jù)式(16)、式(17)計(jì)算${{{\varSigma}} _{{{U}}(t)}}$, ${{{\varSigma}} _{{{Y}}(t)}}$和${{{\varSigma}} _{{{U}}(t){{Y}}(t)}}$
(4)　根據(jù)式(11)對(duì)矩陣${{K}}(t)$進(jìn)行奇異值分解
(5)　根據(jù)式(12)計(jì)算典型相關(guān)變量${{J}}(t)$和${{L}}(t)$
(6)　根據(jù)式(13)生成最優(yōu)異常檢測(cè)殘差${{r}}(t)$ 并建立${T^2}$檢驗(yàn)：$T_{r(t)}^2 = {{{r}}^{\rm{T}}}(t){{\varSigma}} _{r(t)}^{ - 1}{{r}}(t)$
(7)　if $T_{r(t)}^2 \le T_{r,{\rm{cl} } }^2$ then
(8)　　　判定${\rm{P}}{{\rm{L}}_{m,m + 1}}$為正常鏈路，更新協(xié)方差矩陣和均值向量
(9)　　else
(10)　　　判定${\rm{P}}{{\rm{L}}_{m,m + 1}}$為異常鏈路，保留上一時(shí)刻協(xié)方差矩陣和均值向量，丟棄當(dāng)前值
(11) end for

下載: 導(dǎo)出CSV

表 3 仿真參數(shù)

參數(shù)	數(shù)值
每條SFC包含的VNF數(shù)	4～6個(gè)
EMBB(到達(dá)率，數(shù)據(jù)包大小)	(10 packets/s,200 kbit/packets)
URLLC(到達(dá)率，數(shù)據(jù)包大小)	(100 packets/s,10 kbit/packets)
MMTC(到達(dá)率，數(shù)據(jù)包大小)	(500 packets/s,1 kbit/packets)
特征空間維度($D$)	100
初始標(biāo)簽采樣個(gè)數(shù)($t$)	10

下載: 導(dǎo)出CSV

參考文獻(xiàn)(17)

ORDONEZ-LUCENA J, AMEIGEIRAS P, LOPEZ D, et al. Network Slicing for 5G with SDN/NFV: Concepts, architectures, and challenges[J]. IEEE Communications Magazine, 2017, 55(5): 80–87. doi: 10.1109/MCOM.2017.1600935

ELAYOUBI S E, JEMAA S B, ALTMAN Z, et al. 5G RAN slicing for verticals: Enablers and challenges[J]. IEEE Communications Magazine, 2019, 57(1): 28–34. doi: 10.1109/MCOM.2018.1701319

OI A, ENDOU D, MORIYA T, et al. Method for estimating locations of service problem causes in service function chaining[C]. 2015 IEEE Global Communications Conference, San Diego, USA, 2016. doi: 10.1109/GLOCOM.2015.7416993.

YOUSAF F Z, BREDEL M, SCHALLER S, et al. NFV and SDN - key technology enablers for 5G networks[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(11): 2468–2478. doi: 10.1109/JSAC.2017.2760418

陳前斌, 楊友超, 周鈺, 等. 基于隨機(jī)學(xué)習(xí)的接入網(wǎng)服務(wù)功能鏈部署算法[J]. 電子與信息學(xué)報(bào), 2019, 41(2): 417–423. doi: 10.11999/JEIT180310

CHEN Qianbin, YANG Youchao, ZHOU Yu, et al. Deployment algorithm of service function chain of access network based on stochastic learning[J]. Journal of Electronics &Information Technology, 2019, 41(2): 417–423. doi: 10.11999/JEIT180310

COTRONEO D, NATELLA R, and ROSIELLO S. A fault correlation approach to detect performance anomalies in virtual network function chains[C]. The 2017 IEEE 28th International Symposium on Software Reliability Engineering, Toulouse, France, 2017. doi: 10.1109/ISSRE.2017.12.

SCH?LKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation, 2001, 13(7): 1443–1471. doi: 10.1162/089976601750264965

JIANG Qingchao and YAN Xuefeng. Multimode process monitoring using variational bayesian inference and canonical correlation analysis[J]. IEEE Transactions on Automation Science and Engineering, 2019, 16(4): 1814–1824. doi: 10.1109/TASE.2019.2897477

LI Xiaocan, XIE Kun, WANG Xin, et al. Online internet anomaly detection with high accuracy: A fast tensor factorization solution[C]. IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France, 2019: 1900–1908. doi: 10.1109/INFOCOM.2019.8737562.

DE LA OLIVA A, LI Xi, COSTA-PEREZ X, et al. 5G-TRANSFORMER: Slicing and orchestrating transport networks for industry verticals[J]. IEEE Communications Magazine, 2018, 56(8): 78–84. doi: 10.1109/MCOM.2018.1700990

MIAO Xuedan, LIU Ying, ZHAO Haiquan, et al. Distributed online one-class support vector machine for anomaly detection over networks[J]. IEEE Transactions on Cybernetics, 2019, 49(4): 1475–1488. doi: 10.1109/TCYB.2018.2804940

RAHIMI A and RECHT B. Random features for large-scale kernel machines[C]. The 20th International Conference on Neural Information Processing Systems, Charlotte, USA, 2007.

SHALEV-SHWARTZ S, SINGER Y, and SREBRO N. Pegasos: Primal estimated sub-GrAdient sOlver for SVM[C]. The 24th International Conference on Machine learning, Corvallis, USA, 2007. doi: 10.1145/1273496.1273598.

JIANG Qingchao, DING S X, WANG Yang, et al. Data-driven distributed local fault detection for large-scale processes based on the GA-regularized canonical correlation analysis[J]. IEEE Transactions on Industrial Electronics, 2017, 64(10): 8148–8157. doi: 10.1109/TIE.2017.2698422

任馳, 馬瑞濤. 網(wǎng)絡(luò)切片: 構(gòu)建可定制化的5G網(wǎng)絡(luò)[J]. 中興通訊技術(shù), 2018, 24(1): 26–30. doi: 10.3969/j.issn.1009-6868.2018.01.006

REN Chi and MA Ruitao. Network slicing: Building customizable 5G network[J]. ZTE Technology Journal, 2018, 24(1): 26–30. doi: 10.3969/j.issn.1009-6868.2018.01.006

XIE Kun, LI Xiaocan, WANG Xin, et al. On-line anomaly detection with high accuracy[J]. IEEE/ACM transactions on networking, 2018, 26(3): 1222–1235. doi: 10.1109/TNET.2018.2819507

FU Songwei and ZHANG Yan. The due/packet-delivery (v. 2015-04-01)[EB/OL]. https://doi.org/10.15783/C7NP4Z, 2015.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)