Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Network abnormal flow prediction method based on improved radial basis function neural network algorithm

A technology based on neural networks and neural networks, applied in the field of network traffic early warning, can solve problems such as large fluctuations in communication traffic

Inactive Publication Date: 2020-01-17
STATE GRID HUBEI ELECTRIC POWER RES INST
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Smart substations often have large fluctuations in communication traffic due to emergencies, which have strong randomness

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
  • Network abnormal flow prediction method based on improved radial basis function neural network algorithm
  • Network abnormal flow prediction method based on improved radial basis function neural network algorithm
  • Network abnormal flow prediction method based on improved radial basis function neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention.

[0052] The embodiment of the present invention proposes a network abnormal traffic prediction method based on the improved radial basis neural network algorithm, which is mainly divided into the following three stages: RBF neural network initialization, optimization of RBF neural network parameters using QAPSO algorithm, and establishment of optimized RBF neural network Network forecasting model and traffic forecasting.

[0053] 1. RBF neural network initialization

[0054] (1) Preprocessing the training data set, generally adopting normalization processing;

[0055] (2) build the structure of RBF neural network: determine input and output, the input and output of the present invention all are the intelligent substation network traffic size based on time series;

[0056] (3) Determine hidden layer nod...

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 provides a network abnormal flow prediction method based on an improved radial basis function neural network algorithm. The method comprises the steps of initializing an RBF neural network, optimizing RBF neural network parameters by adopting a QAPSO algorithm, reconstructing an optimized RBF neural network prediction model according to the optimal parameters of the RBF neural network, and performing flow prediction by using the optimized RBF neural network prediction model. The invention aims to solve the problems of premature convergence, easiness in falling into a local optimal solution, insufficient search precision and the like of a PSO algorithm. On the basis of an APSO algorithm based on a self-adaptive thought and a QPSO algorithm based on a quantum theory, an APSO algorithm and a QPSO algorithm based on a quantum theory are combined. According to the method, a QAPSO algorithm with higher global convergence capability and global search precision is designed by combining the two algorithms, and RBF algorithm parameters are optimized by using the QAPSO algorithm, so that the prediction precision of the RBF neural network is improved.

Description

technical field [0001] The invention relates to the field of network traffic early warning, in particular to a network abnormal traffic prediction method based on an improved radial basis neural network algorithm. Background technique [0002] At present, the global power field has entered the era of intelligence, and ensuring the security of the smart substation communication system based on IEC61850 plays an increasingly important role in the safe operation of the smart grid. [0003] Network traffic early warning is an important part of power security protection, and a stable and high-precision abnormal traffic early warning system based on this will affect the safe operation and production of smart substations. Network traffic forecasting is the premise of abnormal network traffic early warning. It mainly includes two parts: extracting traffic characteristics and constructing a suitable forecasting model. Researching network traffic forecasting model is of great signific...

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
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/06G06N3/08
CPCG06N3/08H04L63/1425
Inventor 刘畅夏勇军王晋李晶王捷田里汪雪琼
Owner STATE GRID HUBEI ELECTRIC POWER RES INST
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
Eureka Blog
Learn More
PatSnap group products