A Neural Network-based Combined Spectrum Sensing Method for Internet of Vehicles and Its Application

Abstract

The invention provides a neural network-based combined spectrum sensing method for Internet of Vehicles, including: obtaining its covariance matrix, extracting characteristic parameters through the energy value of the received signal and the eigenvalue of the covariance matrix; dividing the training set, verification set and test set; use the characteristic parameters as input parameters, and use the existence of the main user as output parameters to establish a neural network; use a training set and a verification set to train and verify the neural network to obtain a spectrum-aware neural network, and then use a test set to Adjust the spectrum sensing neural network; receive new received signals, perform spectrum sensing, and obtain spectrum sensing results. The invention also provides a vehicle networking. The combined spectrum sensing method for the Internet of Vehicles of the present invention comprehensively considers the characteristics of the signal energy value and the covariance matrix, and utilizes the strong multi-classification ability of the neural network, thereby improving the success rate of spectrum sensing in the Internet of Vehicles environment and effectively improving the frequency spectrum in the Internet of Vehicles environment. perceived performance.

Description

technical field [0001] The invention belongs to the field of the Internet of Vehicles, and in particular relates to a combined spectrum sensing method for the Internet of Vehicles and an application thereof. Background technique [0002] As a key technology in intelligent transportation, the Internet of Vehicles (Internet of Vehicles) perceives the road environment by completing vehicle-to-vehicle and vehicle-to-road communications, so as to realize reasonable route planning and avoid congestion and reduce traffic accidents. In recent years, with the improvement of living standards, the Internet of Vehicles has brought huge challenges to the wireless spectrum resources of the Internet of Vehicles due to the surge of new users. To this end, the dynamic spectrum sharing technology, namely cognitive radio (CR, cognitive radio), will be used to solve the problem of lack of wireless spectrum resources in the Internet of Vehicles. [0003] The concept of cognitive radio is spect...

AI Technical Summary

Problems solved by technology

[0006] However, the existing dual-threshold detection method based on signal energy has very low accuracy of spectrum sensing in the case of low signal-to-noise ratio, and the accuracy of spectrum sensing is only about 5% when the signal-to-noise ratio is -20dB

Images