Single frequency point frequency spectrum prediction method based on optimum long short-term memory model

Abstract

The present invention discloses a single frequency point frequency spectrum prediction method based on an optimum long short-term memory model. The method is employed to mine inherent laws and the correlation between frequency spectrum data through historical frequency spectrum data measured on a channel and grasp the developing law of the frequency spectrum state so as to predict the frequency spectrum state of a future moment. The method comprises the steps of: constructing a data set, and sliding a window with a fixed length, wherein the frequency spectrum data of the next slot time is taken as predicted tags; performing hyper-parameter optimization, combining cross validation based on Furuta experiment design method, and selecting good model configuration; establishing a prediction model based on the deep learning from the aspect of the classification, and performing training for the training set; inputting a test set into the trained prediction model, and obtaining a prediction result at the next slot time. The single frequency point frequency spectrum prediction method can predict the frequency spectrum evolvement rule.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, in particular, it is a single-frequency-point spectrum prediction method based on an optimized long-short-term memory model. Background technique [0002] With the development of wireless communication technology and the increase of mobile devices, the demand for spectrum usage has exploded. In addition, spectrum resources are allocated in a fixed manner, and some frequency bands have the problem of low efficiency. Therefore, the current situation that limited spectrum resource utilization is not high has led to a contradiction between user frequency demand and spectrum resource supply, and spectrum resources are increasingly scarce. In order to solve this kind of contradiction and improve spectrum utilization, cognitive radio proposes a dynamic spectrum access strategy, that is, unlicensed users use the idle time slots of the channel to communicate without causing harmful interfe...

AI Technical Summary

Problems solved by technology

In fact, the binary sequence has a lot to do with the selection of the threshold, and a large amount of original data information is lost, which is not conducive to understanding and mastering the specific evolution of the spectrum state

When predicting channel quality, the time series is often predicted from the perspective of regression through autoregressive moving average model (ARIMA) or support vector regression model (SVR), but these models still have some shortcomings

ARIMA models tend to use the mean of historical data as the predicted value, while SVR models lack a structured way to determine model parameters

Images