Distributed generation island detection method based on meta learning

A technology of distributed power generation and island detection, which is applied in the directions of instruments, knowledge expression, and data processing applications, can solve the problems of reducing the accuracy of classification algorithms and overfitting, and achieve the effects of good adaptability, improved adaptability, and high detection accuracy

Inactive Publication Date: 2014-05-07
SHANGHAI JIAO TONG UNIV
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the above-mentioned defects in the prior art and provide a meta-learning based method that solves the problem that the weakly correlated features in the sample will reduce the accuracy of the classification algorithm and cause over-fitting problems, good adaptability, and high detection accuracy. Islanding Detection Method for Distributed Generation

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Distributed generation island detection method based on meta learning
  • Distributed generation island detection method based on meta learning
  • Distributed generation island detection method based on meta learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] The present invention performs the training and testing model and parameters of island detection, such as figure 2 shown. The system includes 3 distributed power sources DG1-3. The main grid adopts infinite power supply, and the distributed power supply adopts the synchronous motor model. The sampling frequency is 4000Hz, and the island detection time limit is set to 250ms.

[0075] Taking DG1 as an example, islanding events, local loads and other DG switching events are considered in the simulation of the present invention, and voltage disturbance events are also considered, see Table 1 for details. In a voltage disturbance event, the voltage swell and sag amplitude is 20-30%, the duration is 3-4 system cycles, that is, 0.06-0.08s, the voltage pulse amplitude is 2.5-3 times the voltage amplitude, and the duration is 3~5ms. In addition, this paper also fully considers the influence of power imbalance (PI, power imbalance) on the island detection accuracy. This pap...

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

No PUM Login to view more

Abstract

The invention relates to a distributed generation island detection method based on meta learning. The distributed generation island detection method based on meta learning comprises the following steps that (1) key features for island detection are recognized by using an RELIEF algorithm, so that a key feature set is obtained; (2) classification prediction is carried out on the original key feature set through a plurality of basic learning devices; (3) the classification results of the basic learning devices serve as feature items to be added to a training set, and a new sample set T is generated; (4) a meta learning device uses the sample set T as a training set, and carries out relearning on the classification results of the basic learning devices to obtain a final detection result. Compared with the prior art, the distributed generation island detection method based on meta learning solves the problems that due to weak correlation features in samples, accuracy of a classification algorithm can be reduced, and overfitting is caused, and has the advantages of being good in applicability, high in detection accuracy and the like.

Description

technical field [0001] The invention relates to a distributed power generation technology, in particular to a distributed power generation island detection method based on meta-learning. Background technique [0002] It is an important feature of smart grid to connect a large amount of distributed generation (DG) to the system in a friendly manner. From the perspective of system operation, personnel and equipment safety or power quality, distributed generation is required to have the function of island detection. Existing island detection methods mainly include passive detection method, active detection method, and switch state detection method. The switch state detection method relies on real-time communication technology, and has problems such as reliability and cost. Therefore, the current research interest in island detection mainly focuses on passive or active detection. Compared with relay protection, various detection thresholds of island detection protection often ...

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
no application Login to view more
IPC IPC(8): G06Q50/06G06N5/02
Inventor 杨珮鑫张沛超谭啸风
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products