当前位置: X-MOL 学术IEEE Trans. Netw. Serv. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Anomaly-aware Network Traffic Estimation via Outlier-robust Tensor Completion
IEEE Transactions on Network and Service Management ( IF 5.3 ) Pub Date : 2020-12-01 , DOI: 10.1109/tnsm.2020.3024932
Qianqian Wang , Lei Chen , Qin Wang , Hongbo Zhu , Xianbin Wang

Accurately estimating network traffic from the partial measurements plays a crucial role in network management. However, the potential anomaly existing in real networks usually makes this goal difficult to achieve. Existing network traffic estimation methods generally impute network traffic independent of anomaly detection, which incurs significant performance degradation with network anomaly. To address this issue in the realistic network scenario, we propose a novel anomaly-aware network traffic estimation method to recover network traffic data concurrently with network anomaly detection. Specifically, by exploiting the inherent spatio-temporal characteristics, we first formulate the network traffic estimation as a low-rank tensor completion problem. Then, an outlier-robust tensor completion (OrTC) model is constructed by introducing both L2,1-norm regularization and ${\mathrm {L}}_{F}$ -norm regularization, which can not only well fit the intrinsic low-rank property of real traffic data, but also is robust against both the dense noise and the sparse anomaly. Furthermore, an effective optimization algorithm OrTC-AM is designed to solve the non-convex and non-smooth OrTC model based on the popular alternating minimization method. Finally, the extensive experiments performed on the public dataset demonstrate that our proposed OrTC-AM method outperforms the previously widely used network traffic estimation methods.

中文翻译:

通过异常稳健的张量完成进行异常感知网络流量估计

从部分测量中准确估计网络流量在网络管理中起着至关重要的作用。然而,真实网络中存在的潜在异常通常使这一目标难以实现。现有的网络流量估计方法通常独立于异常检测来估算网络流量,这会导致网络异常的显着性能下降。为了在现实网络场景中解决这个问题,我们提出了一种新颖的异常感知网络流量估计方法,以在网络异常检测的同时恢复网络流量数据。具体来说,通过利用固有的时空特性,我们首先将网络流量估计制定为低秩张量完成问题。然后,通过引入 L2、1-范数正则化和 ${\mathrm {L}}_{F}$ -范数正则化,不仅可以很好地拟合真实交通数据的内在低秩属性,而且对密集噪声和稀疏异常。此外,基于流行的交替最小化方法,设计了一种有效的优化算法OrTC-AM来解决非凸非光滑的OrTC模型。最后,在公共数据集上进行的大量实验表明,我们提出的 OrTC-AM 方法优于以前广泛使用的网络流量估计方法。基于流行的交替最小化方法,设计了一种有效的优化算法OrTC-AM来解决非凸非光滑的OrTC模型。最后,在公共数据集上进行的大量实验表明,我们提出的 OrTC-AM 方法优于以前广泛使用的网络流量估计方法。基于流行的交替最小化方法,设计了一种有效的优化算法OrTC-AM来解决非凸非光滑的OrTC模型。最后,在公共数据集上进行的大量实验表明,我们提出的 OrTC-AM 方法优于以前广泛使用的网络流量估计方法。
更新日期:2020-12-01
down
wechat
bug