Unlock instant, AI-driven research and patent intelligence for your innovation.

Short wave multi-channel combined prediction method under condition of historical data missing

A technology of historical data and prediction methods, applied in the direction of baseband system components, etc., can solve problems such as limited prediction accuracy and limited application range

Active Publication Date: 2016-02-10
PLA UNIV OF SCI & TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem solved by the present invention is the problem of limited prediction accuracy and limited application range in existing shortwave channel prediction methods

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
  • Short wave multi-channel combined prediction method under condition of historical data missing
  • Short wave multi-channel combined prediction method under condition of historical data missing
  • Short wave multi-channel combined prediction method under condition of historical data missing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Such as figure 1 As shown, the short-wave multi-channel joint prediction method of the present invention under the condition of lack of historical data includes the following steps: 1. Formal representation of channel state data; 2. Multi-channel joint prediction modeling; 3. Multi-channel joint prediction; 4. Channel prediction performance evaluation. Each step is as follows:

[0034] Step 1. Formal representation of channel state data.

[0035] The purpose of this step is to represent the channel state data of multiple channels and multiple timeslots in a matrix form, so as to facilitate subsequent processing. Specifically, such as figure 2 As shown, let m represent the number of channels, n+1 represent the number of time slots, and represent the state data of multi-channel and multi-slots as a matrix X of m×(n+1), each element X in the matrix ij ,i∈{1,...,m}, j∈{1,...,n+1} represents the state data of the i-th channel in the j-th time slot, and each row of the m...

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 short wave multi-channel combined prediction method under a condition of historical data missing, which comprises the steps of formalized representation of channel state data, multi-channel combined prediction modeling, multi-channel combined prediction and channel prediction performance evaluation. The short wave multi-channel combined prediction method provided by the invention takes a practical application condition of incomplete historical data into consideration, thereby having a wider application range; and the correlation of the channel state at a time dimension and the correlation of the channel state at a frequency dimension are utilized, thereby having more reliable prediction accuracy.

Description

technical field [0001] The invention belongs to the field of short-wave communication and cognitive radio of wireless communication technology, and in particular relates to a short-wave multi-channel joint prediction method under the condition of lack of historical data. Background technique [0002] Channel prediction is a technique for inferring unknown channel states by using correlations between known channel states (such as channel occupancy conditions, channel quality conditions, etc.). Reliable channel state prediction is an important supporting technology to realize fast link establishment, throughput optimization, topology control and routing selection in HF communication network. Existing methods mainly use the correlation of the channel state in the time dimension (that is, between multiple consecutive time slots) to predict the channel state in the time domain. However, existing methods have the following limitations: [0003] (1) These methods mainly focus on ...

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): H04L25/02
Inventor 王金龙沈良丁国如任国春陈瑾吴启晖高翔高瞻郑学强
Owner PLA UNIV OF SCI & TECH