Adaptive threshold channel occupation state prediction method based on LSTM neural network

Abstract

The invention discloses an adaptive threshold channel occupation state prediction method based on an LSTM neural network. The method comprises five parts of determining an adaptive quantization threshold, determining the length of a historical sequence, generating a model input and output set, optimizing the model hyper-parameters and predicting a real-time frequency spectrum, wherein determiningan adaptive quantization threshold is characterized by adaptively setting the quantization thresholds for different channels through probability density estimation; determining the historical sequencelength is to determine the appropriate length of the historical sequence inputted into the model through the autocorrelation function analysis, generating the model input and output set comprises thesub-steps of quantifying and dividing a data set according to an adaptive quantization threshold and a historical sequence length, the hyper-parameter optimization is to optimize the model through agrid search and cross validation combined method, and the real-time frequency spectrum prediction is to predict the real-time occupation state of the actually acquired frequency spectrum data. According to the method, the future spectrum occupation state can be accurately predicted, and a slave user is assisted to adjust the transmitting parameters in advance, and therefore the spectrum resource utilization rate is increased.

Description

technical field [0001] The invention relates to an adaptive threshold channel occupancy state prediction method based on an LSTM neural network, which belongs to the field of cognitive radio frequency spectrum prediction. Background technique [0002] With the development of wireless communication technology, the number of wireless frequency equipment is increasing rapidly, and the demand for spectrum is increasing day by day. However, a large number of spectrum analysis reports show that due to the static spectrum allocation strategy, the utilization rate of many licensed spectrums is insufficient, and there is a great waste of resources. Cognitive radio technology is proposed to enable unlicensed users (slave users) to opportunistically access and use the spectrum resources of primary users without affecting authorized users (primary users), thereby improving spectrum utilization to a certain extent. Alleviate the current situation of shortage of spectrum resources. [0...

AI Technical Summary

Problems solved by technology

The autoregressive moving average model requires the time series data to be stable, or stable after the difference is made, but usually the actual collected spectrum data generally does not meet this requirement, and the autoregressive moving average model can only capture linear relationships in essence, and cannot capture Non-linear relationship, and the changing law of the spectrum usually cannot be expressed by a simple linear relationship

The Hidden Markov Model assumes that the current state is only related to the previous state, but the actual frequency spectrum change law often does not meet this assumption

The support vector machine model is a machine learning method widely used in classification and regression prediction in recent years, but it is the same as the traditional machine learning method, the model performance is greatly affected by feature engineering, and the selection of features is very dependent on research personnel experience

Images