Method and system for intrusion detection of distribution terminal unit (DTU) based on machine learning

A power distribution terminal and intrusion detection technology, which is applied in transmission systems, instruments, electrical components, etc., can solve the problems that the intrusion detection system is difficult to meet the requirements, and achieve good versatility and portability, fast calculation speed, and fast operation speed Effect

CN112187820AActive Publication Date: 2021-01-05SHENZHEN POWER SUPPLY BUREAU +2
5 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-01-05

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method and system for intrusion detection of a DTU based on machine learning, belonging to the field of intelligent power grid security. The method comprises the following steps: port identification, data acquisition, transmission, data processing and dimension reduction of the DTU, construction of a classifier based on a neural network and a least square support vector machine, an intrusion behavior detection experiment of the DTU, and timely sounding of an alarm when abnormity occurs. According to the invention, high-dimensional feature data are reduced by adoptinga principal component analysis method, and then a model is established by utilizing features after dimension reduction; secondly, dual verification is performed by adopting the least square support vector machine and a neural network algorithm so as to improve detection accuracy and reduce a false alarm rate; and finally, the framework of the intrusion detection system adopts a modular design, sothe system is suitable for intrusion detection in the field of intelligent power grids, and is good in portability and universality.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of smart grid security, and more specifically relates to a machine learning-based DTU intrusion detection method and system for power distribution terminals. Background technique

[0002] Distribution network automation and intelligence have played a role in promoting the optimal allocation of national energy resources, the safe and stable operation of the power system, and the development of national strategic emerging industries. In recent years, as the power system and communication network have become more closely integrated, security threats from the Internet have become more complex and diverse, and distribution network information security issues have become more prominent. In particular, distribution terminal micro-grid controllers are frequently attacked by networks, which seriously hinders normal production and operation of the power system. As the core device in the distribution network, the intelligent di...

Examples

Embodiment Construction

[0046] The present invention will be further explained below in conjunction with the accompanying drawings and embodiments.

[0047] The present invention provides a DTU intrusion detection method and system based on machine learning, such as figure 2 As shown, the system is composed of three subsystems: data collection, data transmission and data processing. It uses the network traffic and related network information of power distribution terminals to perform intrusion detection on power industrial control attacks. The work flow chart of the intrusion detection system is as follows: figure 2 shown.

[0048] The specific working method of the system is as follows:

[0049] Step 1: Construct a machine learning-based intrusion detection system framework according to the requirements in power grid system applications. Specific steps are as follows:

[0050] Step 1.1: Establish a data collection subsystem with DTU as the client.

[0051] Step 1.2: Establish a data transmissi...