Robust network compressive sensing

Chen, Yichao; Qiu, Lili; Zhang, Yin; Xue, Guangtao; Hu, Zhenxian

doi:10.1145/2639108.2639129

Cited by 70 publications

(23 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, sparsity methods or the related compressive sensing (CS) methods have been significantly investigated [9]- [12]. Mathematically, sparsity methods aim to tackle this sparse signal recovery problem in the form of…”

Section: B Sparse Representation and Dictionary Learningmentioning

confidence: 99%

“…One is used to learn and distill the parameters related to traffic characteristics, and the other part is to conduct the experiments to verify and validate the accuracy of the proposed framework in Algorithm 2. Specifically, we compare our predictionx p with the ground truth x in terms of the normalized mean absolute error (NMAE) [12], which is defined as…”

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

The Learning and Prediction of Application-Level Traffic Data in Cellular Networks

Zhao

Zheng

et al. 2017

IEEE Trans. Wireless Commun.

116

View full text Add to dashboard Cite

Abstract-Traffic learning and prediction is at the heart of the evaluation of the performance of telecommunications networks and attracts a lot of attention in wired broadband networks. Now, benefiting from the big data in cellular networks, it becomes possible to make the analyses one step further into the application level. In this paper, we firstly collect a significant amount of application-level traffic data from cellular network operators. Afterwards, with the aid of the traffic "big data", we make a comprehensive study over the modeling and prediction framework of cellular network traffic. Our results solidly demonstrate that there universally exist some traffic statistical modeling characteristics at a service or application granularity, including α-stable modeled property in the temporal domain and the sparsity in the spatial domain. But, different service types of applications possess distinct parameter settings. Furthermore, we propose a new traffic prediction framework to encompass and explore these aforementioned characteristics and then develop a dictionary learning-based alternating direction method to solve it. Finally, we examine the effectiveness and robustness of the proposed framework for different types of application-level traffic. Our simulation results prove that the proposed framework could offer a unified solution for application-level traffic learning and prediction and significantly contribute to solve the modeling and forecasting issues.

show abstract

Section: B Sparse Representation and Dictionary Learningmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

The Learning and Prediction of Application-Level Traffic Data in Cellular Networks

Zhao

Zheng

et al. 2017

IEEE Trans. Wireless Commun.

116

View full text Add to dashboard Cite

show abstract

“…Zhang et al [56] interpolate incomplete traffic matrices with structure regularized low-rank matrix factorization and local interpolation procedures. LENS [10] models the traffic matrices as the sum of multiple matrices that are positively correlated with the traffic matrix. Our work is a complement to these studies by proposing a new model that keeps the low-rank interpretation and adapts well to skewed latent factors.…”

Section: Related Workmentioning

confidence: 99%

A Skewness-Aware Matrix Factorization Approach for Mesh-Structured Cloud Services

Barlet‐Ros³

et al. 2019

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Online cloud services need to fulfill clients' requests scalably and fast, otherwise, users' experience and providers' revenue could be severely degraded. State-of-the-art cloud services are increasingly deployed as a distributed service mesh. Service to service communication is frequent in the mesh. Unfortunately, problematic events may occur between any pair of nodes in the mesh, therefore, it is vital to maximize the network visibility for efficient network troubleshooting and application optimization. A state-of-the-art approach is to model pairwise RTTs based on a latent factor model represented as a low-rank matrix factorization. A latent factor corresponds to a rank-1 component in the factorization model, and is shared by all node pairs. However, different node pairs usually experience a skewed set of hidden factors like divergent routing paths, dynamic path conditions, or transient network congestions, which cannot be captured by existing latent factor models. In this paper, we propose a skewness-aware matrix factorization method named SMF. We decompose the matrix factorization into the basic units of rank-one latent factors, and progressively combine rank-one factors for different node pairs. We present a unifying framework to automatically and adaptively select the rank-one factors for each node pair, which not only preserves the low rankness of the matrix model, but also adapts to skewed network latency distributions. Over real-world RTT data sets, SMF significantly improves the relative error by a factor of 0.2x to 10x, converges fast and stably, and compactly captures fine-grained local and global network latency structures.

show abstract

“…Compressive sensing is a generic data reconstruction technique based on the structure and redundancy of real-world signals or datasets [3][4][5][6]. So far, compressive sensing has been widely applied to different realms [7][8][9][10][11].…”

Section: Data Reconstruction and Sensor Deploymentmentioning

confidence: 99%

“…For instance, [6] proposed the robust network compressive sensing and proved its efficiency based on a large amount of evaluation, and compressive sensing technology has been utilized for network traffic estimation [7], localization in mobile networks [9], soil moisture sensing [10] and data gathering [11,12]. In FIWEX, we combine compressive sensing with indoor white space exploration in an innovative way and efficiently explore indoor white spaces with a high accuracy.…”

Section: Related Workmentioning

confidence: 99%

Fiwex

Liu

et al. 2015

Proceedings of the 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing

View full text Add to dashboard Cite

Exploring the utilization of white spaces (vacant VHF and UHF TV channels) is a promising way to satisfy the rapid growth of the radio frequency (RF) demand. Although a few outdoor white space exploration methods have been proposed in the past few years, researches that focus on indoor white space exploration just emerge recently. In this paper, we propose a novel cost-efficient indoor white space exploration method by exploiting the location dependence and channel dependence of TV channels' signal strength in indoor environments. We measure the UHF TV channels in a building, and study the temporal and spatial features of indoor white spaces. Based on the extracted features, we design a cost-eFficient Indoor White space EXploration mechanism, namely FIWEX. Furthermore, we build a prototype of FIWEX and extensively evaluate its performance in real world environments. The evaluation results show that FIWEX can identify 47.8% more indoor white spaces with 38.4% less false alarms compared with the best known existing solution.

show abstract

Robust network compressive sensing

Cited by 70 publications

References 39 publications

The Learning and Prediction of Application-Level Traffic Data in Cellular Networks

The Learning and Prediction of Application-Level Traffic Data in Cellular Networks

A Skewness-Aware Matrix Factorization Approach for Mesh-Structured Cloud Services

Fiwex

Contact Info

Product

Resources

About