Method and system for recovering missing value in network flow measurement data
A technology for network traffic and measurement data, applied in the field of computer networks, which can solve problems such as low filling accuracy, inaccurate expression of factor vectors, and impact on recovery performance.
Pending Publication Date: 2022-07-01
HUNAN UNIV
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method and system for recovering missing values in network flow measurement data. The flow has periodic and stable time feature information, which leads to inaccurate expression of the factor vector, which affects the technical problems of recovery performance, and because it can only capture the simple linear correlation between the factor vector and the same feature dimension, which leads to the failure of this method. The technical problem of low actual filling accuracy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0062] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0063] It should be noted that, in the description of the embodiments of the present invention, the terms "comprising", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, thereby making a process, method, article or device including a series of elements Not only those elements are included, but other elements not expressly listed or inherent to such a process...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for recovering missing values in network flow measurement data, which comprises the following steps of: modeling the network flow data into a source node-destination node-measurement time slot three-dimensional tensor, mapping each source node, each destination node and each measurement time slot to a shared potential feature space (D-dimensional vector space) and embedding into a factor vector, a time factor vector is enhanced by using an attention-enhanced long-short-term memory network in consideration of a time pattern of network traffic; a new multi-mode fusion method is designed. Lightweight trilinear pooling is used as an interaction function of tensor filling to effectively model three-way and multi-order nonlinear correlation among different feature dimensions of potential factor vectors and accurately estimate missing values of network traffic. And combining the estimated values of all the missing values with all the measured values to obtain complete network flow data. The invention also discloses a system for recovering the missing value in the network flow measurement data.
Description
technical field [0001] The invention belongs to the field of computer networks, and more particularly, relates to a method and system for recovering missing values in network flow measurement data. Background technique [0002] Tasks such as network traffic engineering and anomaly detection rely on complete end-to-end network traffic data. Due to the lack of basic equipment to support measurement, the negative impact of high measurement cost on equipment, and the inevitable transmission loss, the network monitoring system has the problem of incomplete network traffic data, and only a part of the path (source node-destination node pair) is measured. or time slot. The key is to infer the missing values from the measured values of some source node-destination node pairs and time slots to recover the entire network traffic data. [0003] Existing network traffic data recovery methods are mainly based on sparse reconstruction technology, including the missing data recover...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08H04L9/40H04L43/0876
CPCG06N3/08H04L43/0876H04L63/1425G06N3/044
Inventor 欧阳与点谢鲲文吉刚李肯立
Owner HUNAN UNIV