A method for predicting channel state transition probability in cognitive radio network

Abstract

A method for predicting channel state transition probability in a cognitive radio network based on a two-stage Q learn method comprises two learning processes, namely a channel state transition probability learn process and a channel state learning process. The channel state transition probability learning process and the channel state learning process are both based on a Q learning method, and the channel state learning process can learn the channel state according to the channel state transition probability learned by the channel state transition probability learning process and output the learned channel state. This method can predict the changing authorized channel state in real time. In addition, the method does not need to assume in advance that the authorized user or the disturber satisfies any probability distribution. Moreover, the proposed method fully considers the correctness of the channel state transition probability used to predict the sample state.

Description

technical field [0001] The invention relates to a method for predicting channel state transition probability in a cognitive radio network, and belongs to the technical field of radio networks. Background technique [0002] Over the past few decades, wireless networks have supported ever-increasing demands for higher data rates in order to meet consumer demands for fast, secure, and intelligent wireless networks. However, the current wireless network system is facing a bottleneck brought about by spectrum resources. This bottleneck makes it difficult to enhance performance in the limited available frequency band. Therefore, in order to further enhance the performance of wireless networks, new communication cases are required. The industry has predicted that wireless networks will require more spectrum resources to serve more high-speed communication users. Moreover, current spectrum resources need to be utilized more effectively. In order to utilize limited spectrum resou...

AI Technical Summary

Problems solved by technology

However, due to the limitation of spectrum sensing time of unlicensed users, spectrum sensing method and communication environment, the observed channel state may deviate from the actual channel state to a certain extent

[0012] 2. Most articles need to predict the channel state transition probability in advance, which will bring a certain degree of delay to the communication of cognitive radio users

However, in real cognitive radio networks, the channel state transition probabilities may be time-varying

[0013] 3. The channel state transition probability prediction method in some articles needs to satisfy a certain probability distribution, and cannot be generally used in cognitive radio networks

Images