Title
Efficient Performance Monitoring for Ubiquitous Virtual Networks Based on Matrix Completion.
Abstract
Inspired by the concept of software-defined network and network function virtualization, vast virtual networks are generated to isolate and share wireless resources for different network operators. To achieve fine-grained resource control and scheduling among virtual networks (VNs), network performance monitoring is essential. However, due to limitation of hardware, real-time performance monitoring is impossible for a complete virtual network. In this paper, taking advantage of the low-rank characteristic of 90 virtual access points (VAPs) measurement data, we propose an intelligent measurement scheme, namely, adaptive and sequential sampling based on matrix completion (MC), which exploits from the MC to construct the complete data of VN performance from a partial direct monitoring data. First, to construct the initial measurement matrix, we propose a sampling correction model based on dispersion and coverage. Second, a stopping condition for the sequential sampling is introduced, based on the stopping condition, the sampling process for a period can stop without waiting for the matrix reconstruction to reach certain of accuracy level. Finally, the sampled VAPs are determined by referring the back forth completed matrixes' normalized mean absolute error. The experiments show that our approach can achieve a constant network perception and maintain a relatively low error rate with a small sampling rate.
Year
DOI
Venue
2018
10.1109/ACCESS.2018.2815548
IEEE ACCESS
Keywords
Field
DocType
Performance monitoring,low-rank,matrix completion,adaptive
Virtual network,Matrix completion,Scheduling (computing),Adaptive system,Computer science,Word error rate,Real-time computing,Sampling (statistics),Wireless sensor network,Distributed computing,Network performance
Journal
Volume
ISSN
Citations 
6
2169-3536
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Xinheng Wang1298.79
Chuan Xu214022.01
Guofeng Zhao34112.33
Kun Xie419738.39
Shui Yu52365208.84