A Traffic Prediction Method for Communication Base Station

A communication base station and flow prediction technology, which is applied in wireless communication, artificial life, electrical components, etc., can solve the problems of large communication base station flow prediction error and difficulty in effectively capturing nonlinear factors, so as to reduce the risk of convergence and balance the overall situation Search ability and local development, the effect of improving local development ability

Active Publication Date: 2022-05-10
HARBIN UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention is to solve the problem that the traditional linear time series method is difficult to effectively capture the complex nonlinear factors in the actual base station flow sequence, which leads to the problem of large prediction error of the current communication base station flow

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
  • A Traffic Prediction Method for Communication Base Station
  • A Traffic Prediction Method for Communication Base Station
  • A Traffic Prediction Method for Communication Base Station

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0067] This embodiment is a communication base station flow prediction method based on the improved gray wolf algorithm to optimize the support vector machine regression machine.

[0068] The present invention firstly collects the flow data of the communication base station and divides and processes them; secondly, sets the relevant parameters of SVR and sets the parameters of the improved gray wolf optimization algorithm; Finally, the optimized SVR is used to predict the test set data, and the output results are denormalized to obtain the prediction results of communication base station traffic. The present invention improves the standard gray wolf algorithm for SVR parameter optimization. Compared with the standard gray wolf algorithm optimized support vector machine regression machine prediction model, simulated annealing algorithm optimized BP neural network prediction model and other models in base station traffic prediction have higher prediction accuracy.

[0069] Aimi...

Embodiment

[0150] Carry out simulation based on the present invention, compare existing model simultaneously, apply the experimental result of the present invention and all the other three kinds of model results as follows:

[0151] In order to verify the high prediction accuracy of the LIGWO_SVR prediction model proposed by the present invention, the prediction results of the model are compared with the prediction results of the GWO_SVR model, the prediction results of the SA_BP model, the results of the PSO_BP model and the actual communication base station traffic data. The rest of the model parameters are set as follows: the Markov chain length of the SA_BP model is L=10, the initial temperature T ini =8, final temperature T fin =3, decay parameter Dec=0.85, Metropolis step factor M=0.2. PSO_BP model population size N=50, the maximum number of iterations t max =100, individual learning factor c1=1.49, social learning factor c2=1.49, inertia factor ω=0.2. The number of hidden layer...

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 communication base station traffic forecasting method, which relates to the technical field of communication base station traffic forecasting. In order to solve the problem that the traditional linear time series method is difficult to effectively capture the complex nonlinear factors in the actual base station traffic sequence, which leads to the problem of large prediction errors for the current communication base station traffic. The present invention firstly collects the traffic data of the communication base station and divides and processes it, then sets the relevant parameters of SVR and sets the parameters of the improved gray wolf optimization algorithm, and uses the improved gray wolf algorithm to obtain the penalty factor of the SVR and the optimal value of the kernel function parameters. Finally, the optimized SVR is used to predict the test set data, and the output results are denormalized to obtain the prediction results of communication base station traffic. It is mainly used for traffic prediction of communication base stations.

Description

technical field [0001] The invention relates to the technical field of flow prediction of communication base stations, in particular to a flow prediction method of communication base stations. Background technique [0002] High-precision network traffic forecasting is the basis of modern network intelligent management. Aiming at the parameter optimization problem of support vector machine in the process of network traffic forecasting modeling, with the goal of improving network traffic forecasting results, more and more scholars have proposed improved Gray Wolf Algorithmic Optimization of Support Vector Machine Network Traffic Prediction Models. Based on this technical background, the present invention improves and optimizes the gray wolf algorithm, and uses a support vector machine regression machine to improve the flow prediction accuracy of communication base stations. [0003] With the development of mobile communication technology, 4G and 5G have brought great convenie...

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 Patents(China)
IPC IPC(8): H04L41/147
CPCH04W24/06H04L41/147H04L41/142G06N3/006
Inventor 丁绍博王月茹洪佳昕黄逊郑天寒梁安田
Owner HARBIN UNIV OF SCI & TECH
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