A service flow anomaly detection method for remote intelligent dispatching and switching of optical fiber core
A technology of intelligent scheduling and business flow, applied in the field of abnormal detection of network business flow, can solve problems such as unclear mechanism, achieve high accuracy and timeliness, and improve accuracy
Active Publication Date: 2022-03-01
STATE GRID LIAONING ELECTRIC POWER RES INST +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The maximum entropy-based baseline distribution is composed of pre-labeled training data, but the mechanism by which this baseline adapts to dynamic changes in network traffic remains unclear
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
[0063] The present invention is a business flow abnormality detection method oriented to the remote intelligent dispatching and exchange of the optical fiber core, which is used to detect abnormal components in the network traffic, such as figure 1 as shown, figure 1 It is a general flow chart of the embodiment of the abnormal service flow detection method of intelligent dispatching and switching of optical fiber core based on factor analysis in the present invention. Include the following steps:
[0064] Step 101: start;
[0065] Step 102: Given the network traffic as a known condition, determine the number of common factors k. The network traffic in the optical cable communication access network changes with time, so we can treat them as time series. Suppose y(t) represents the network traffic at time t. Then the time series y={y(t)|t=1,2,...} represents the change of network traffic over time. Without loss of generality, let the length of network traffic be n where n ...
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 belongs to network anomaly detection of an optical fiber communication access network, in particular to a service flow anomaly detection method oriented to remote intelligent dispatching and switching of optical fiber cores. Including giving the network traffic and the number of public factors k, constructing a random matrix Y; standardizing the original data to obtain a standardized data matrix R (R=Cov(Y)), obtaining the eigenvalues and eigenvectors of the matrix R, and calculating the variance and cumulative variance Contribution rate, to determine the public factor Y in network traffic c and a special factor Y in network traffic s ; After the public factors are solved, the factors are rotated to obtain the main factors that meet the appropriate rotation; the factor analysis model is established to evaluate the status of each sample in the entire model; the score of each factor is obtained, and the public factors in the flow and the special factors of the network flow are obtained. One time series obtains the feature function set of another time series: feature extraction; feature filtering, find out the abnormal part of the traffic, and save the result. The invention is used for detecting abnormal components in the network service flow, and has high accuracy and timeliness.
Description
technical field [0001] The invention belongs to the network anomaly detection of an optical fiber communication access network, in particular to a service flow anomaly detection method oriented to remote intelligent dispatching and exchange of optical fiber cores, in particular to a network service flow anomaly detection method. Background technique [0002] With the rapid development of new-generation network technology, network applications in the optical fiber communication access network present new types of traffic and lead to rapid growth of network traffic, followed by new business traffic anomalies in the optical fiber communication access network. Abnormal service traffic in optical fiber communication affects network performance and user experience quality. How to effectively detect and find out abnormal parts in network traffic has become a big challenge. More importantly, abnormal business traffic means abnormal operations of users or network devices. If the ab...
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 Patents(China)
IPC IPC(8): H04L9/40H04B10/85
CPCH04L63/1425H04B10/85
Inventor 李欢孟凡博刘扬陈得丰卢盛阳王东东杨智斌耿洪碧任帅南洋
Owner STATE GRID LIAONING ELECTRIC POWER RES INST