A smart grid worm detection method
A smart grid and detection method technology, applied in electrical components, biological neural network models, digital transmission systems, etc., can solve the problems of high false alarm rate and false negative rate, and achieve the effect of improving detection accuracy and detection efficiency
Active Publication Date: 2022-07-26
SHENZHEN POWER SUPPLY BUREAU
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
These detection technologies require a smart meter communication network and a worm attack model, and the false alarm rate and false negative rate are high
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
[0035] The following descriptions of the various embodiments refer to the accompanying drawings to illustrate specific embodiments in which the invention may be practiced.
[0036] Please refer to figure 1 As shown, an embodiment of the present invention provides a smart grid worm detection method, including:
[0037] Step S1, the smart meter collects user information and power demand data, uploads the destination IP address and time stamp of the data packet to the concentrator, and the concentrator uploads the data packet to the data processor at predetermined time intervals;
[0038] Step S2, input the state vector for worm detection into the trained neural network, obtain the selection strategy of the worm detection threshold and select the worm detection threshold;
[0039] Step S3, the destination IP address of the data packet received by the data processor statistics, calculates its spectral flatness measure value, and judges whether to detect the worm according to the ...
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 smart grid worm detection method, which comprises the following steps: collecting user information and power demand data by a smart meter, uploading the destination IP address and time stamp of a data packet to a concentrator, and the concentrator uploading the data packet to a Data processor; input the state vector used for worm detection into the trained neural network, obtain the selection strategy of the worm detection threshold and select the worm detection threshold; the data processor calculates its spectral flatness measurement value, and according to the spectral flatness measurement value Judging whether the worm is detected with the magnitude relation of the worm detection threshold; the data processor counts the data detection results, updates the state vector, and calculates the reward value; calculates the cumulative reward function according to the updated state vector and the reward value, and updates Network weight parameters; continuously adjust the selection of the worm detection threshold until the reward function converges to achieve stable worm detection. The invention can reduce the false alarm rate and the false alarm rate, and shorten the detection time.
Description
technical field [0001] The invention relates to the technical field of smart grid security, in particular to a smart grid worm detection method. Background technique [0002] The power meters in the smart grid are closely connected and numerous, and are vulnerable to worm attacks, which can leak data and information of users' power consumption in the power grid system, and affect or destroy the power system and key infrastructure. If the worm virus cannot be detected in time, the worm virus will infect a large number of electricity meters in a short period of time, which will bring great security risks and even lead to network paralysis. [0003] The existing power grid worm detection technology monitors, collects and analyzes the log information of smart meters, and performs detection according to the propagation characteristics of worms. These detection technologies all require smart meter communication network and worm attack model, and the false alarm rate and false ala...
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): H04L9/40H04L43/106H04L43/16H04L41/14H04L41/142H04L41/0631G06N3/04
CPCH04L63/145H04L43/106H04L43/16H04L41/145H04L41/142H04L41/0631G06N3/045
Inventor 罗伟峰李鹏敏
Owner SHENZHEN POWER SUPPLY BUREAU