Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Multi-step Prediction Method of Mobile Communication Traffic

A mobile communication and multi-step forecasting technology, applied in wireless communication, special data processing applications, instruments, etc., can solve the problems of poor linear model adaptability and low prediction accuracy, reduce algorithm complexity, improve prediction accuracy, and solve blind sexual effect

Inactive Publication Date: 2011-12-28
HARBIN INST OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as a multi-period time series closely related to people's daily life, the traffic sequence has multi-scale and non-stationary characteristics. The linear model has poor adaptability to it and low prediction accuracy.

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 Multi-step Prediction Method of Mobile Communication Traffic
  • A Multi-step Prediction Method of Mobile Communication Traffic
  • A Multi-step Prediction Method of Mobile Communication Traffic

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0012] Specific embodiment one: a kind of multi-step prediction method of mobile communication traffic, this method is finished by the following steps:

[0013] Step 1: Carry out Fourier transform to mobile communication traffic data, use described Fourier spectrum analysis result as the prior knowledge of wavelet decomposition integration;

[0014] Step 2: According to the prior knowledge of the Fourier spectrum obtained in Step 1, the maximum overlap discrete wavelet transform algorithm is used to select the Haar wavelet base and the number of decomposition layers, and the wavelet decomposition is performed on the dialogue traffic sequence to obtain the components corresponding to the Fourier spectrum The trend item and each detail item;

[0015] Step 3: According to the prior knowledge obtained in Step 1, integrate the detailed items in Step 2 into periodic items;

[0016] Step 4: Use the product seasonal ARIMA model to predict the trend item obtained in step 2 and the per...

specific Embodiment approach 2

[0033] Specific implementation mode two: this implementation mode is an embodiment of specific implementation mode one:

specific Embodiment approach

[0035] 1. Carry out Fourier spectral analysis on the traffic data of a community in Harbin City, Heilongjiang Province, see figure 1 , the analysis process is: firstly the traffic sequence is sampled at equal intervals, the sampling period is 1 hour, and the unit of the traffic is Ireland (Erl); the result of the Fourier spectrum analysis shows the traffic time The sequence data has obvious periodic characteristics in the spectral components such as 6, 8, 12, 24, 84, and 168 hours, and the periodic components are arranged in order of amplitude from large to small, as follows: T = 24 hours, T = Spectrum components such as 12 hours, T=6 hours, T=8 hours, T=168 hours, T=84 hours, etc., see figure 2 . Using said spectral components as prior knowledge of wavelet decomposition;

[0036] Two, according to the above-mentioned prior knowledge of Fourier spectrum, adopt the maximum overlapping discrete wavelet transform algorithm described in step 2 in the specific embodiment one, ca...

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

A multi-step prediction method for mobile communication traffic, which relates to the field of mobile communication traffic prediction, which solves the low prediction accuracy of existing mobile communication traffic using autoregressive moving average series models and blindness in the process of using wavelet decomposition sex. Its specific implementation process is: using the results of Fourier spectral analysis as prior knowledge, guiding the decomposition process based on the maximum overlapping discrete wavelet transform, and extracting the detail items and trend items corresponding to the Fourier spectral components . In view of the increase of algorithm complexity brought by wavelet decomposition, the prior knowledge of Fourier spectrum is used to streamline and integrate the wavelet sub-layer, and the integrated trend item and period item are respectively predicted by the product seasonal summation autoregressive moving average model, Add up the predicted results to get the predicted value. The method of the invention is also applicable to the prediction of actual multi-period time series such as resident tap water flow, city bus flow, elevator passenger flow and network flow.

Description

technical field [0001] The invention relates to the field of mobile communication traffic prediction, in particular to an ARMA series model prediction algorithm and a priori knowledge-based maximum overlap discrete wavelet transform decomposition and integration algorithm. Background technique: [0002] Now the number of mobile communication users and the volume of traffic maintain a momentum of rapid growth. The long-term and stable operation of mobile networks depends on timely and effective network planning and optimization. When the mobile communication traffic exceeds a certain capacity, it is very easy to cause the switching system to be overloaded, causing network congestion, causing irreparable losses to mobile communication operators and users. Therefore, predicting the changing trend of mobile communication traffic based on traffic statistics and other business information can provide decision support for issues such as peak warning, base station configuration, and...

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): H04W16/18H04W24/06G06F17/00
Inventor 彭宇乔立岩刘大同雷苗郭嘉王建民
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products