Method for detecting network flow abnormality of power secondary system based on unsupervised learning
A power secondary system and unsupervised learning technology, applied in the field of power communication security, can solve problems such as abnormal causes that have not been explored, and achieve the effect of reducing losses and improving efficiency
Inactive Publication Date: 2018-06-22
NINGBO POWER SUPPLY COMPANY STATE GRID ZHEJIANG ELECTRIC POWER +2
View PDF2 Cites 13 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The above literatures have achieved certain research results in the research of power system data network traffic anomaly detection technology, but they have not discussed the reasons for the anomaly.
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
[0049] The technical content of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0050] In order to analyze the traffic behavior of many devices and servers in the secondary system, the unsupervised machine learning algorithm based on SOM network is used to analyze the collected device logs in the secondary system, so as to realize traffic anomaly detection and abnormal reason analysis.
[0051] Such as figure 1 As shown, the non-supervised learning-based network flow anomaly detection method of the power secondary system provided by the present invention includes the following steps: first, collecting log information of equipment in the secondary system, and performing preprocessing to obtain historical training data; then , use the historical training data to train the SOM network, and obtain the final detection model through cross-checking; finally, collect the log information of the equipment ...
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 detecting the network flow abnormality of a power secondary system based on unsupervised learning, and the method comprises the following steps: S1, collecting thelog information of equipment in the secondary system, carrying out the preprocessing, and obtaining historical training data; S2, carrying out the training of the SOM network through the historical training data, and obtaining a final detection model through cross check; S3, collecting the log information of equipment in the secondary system in real time, obtaining an input vector, inputting theinput vector into the final detection model, and obtaining the state value of the current network flow according to the state value of the input vector. The method can achieve the timely and effectivediscovery of the network flow abnormality, improves the processing efficiency of the network abnormality, and effectively reduces the loss caused by the network abnormality.
Description
technical field [0001] The invention relates to a network traffic detection method, in particular to a non-supervised learning-based power secondary system network traffic anomaly detection method; it belongs to the technical field of electric power communication security. Background technique [0002] The power secondary system refers to the system composed of all levels of power monitoring system and dispatching data network (SPDnet), and all levels of management information system and power data communication network (SPTnet). The power secondary system is an important part of power system security, and is closely related to the safe operation of power grid dispatching and control systems. There are a large number of safety equipment and business systems in the power secondary system, and the network composed of them is large in scale and complex in structure, accompanied by a large number of data communication services. Therefore, real-time monitoring of network traffic...
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): H04L29/06H04L12/26G06N3/08H04L12/24
CPCH04L63/1425G06N3/088H04L41/142H04L41/145H04L43/028
Inventor 龚向阳胡铁军戚军谢宏章杜锡江昊周飞焦旭明周媛马骁吕超王景高明慧梁野董晨晖林祺蓉王俏俏
Owner NINGBO POWER SUPPLY COMPANY STATE GRID ZHEJIANG ELECTRIC POWER