Cross-Band Spectrum Prediction Algorithm Based on Data Conversion Using Generative Adversarial Networks

作     者：Chuang Peng Rangang Zhu Mengbo Zhang Lunwen Wang Chuang Peng;Rangang Zhu;Mengbo Zhang;Lunwen Wang

作者机构：College of Electronic EngineeringNational University of Defense TechnologyHefei 230037China 

出 版 物：《中国通信:英文版》 (China Communications)

年 卷 期：2023年第20卷第10期

页      面：136-152页

核心收录：

学科分类：0401[教育学-教育学] 04[教育学] 

基　　金：supported by the fund coded,National Natural Science Fund program(No.11975307) China National Defence Science and Technology Innovation Special Zone Project(19-H863-01-ZT-003-003-12) 

主　　题：cognitive radio cross-band spectrum prediction deep learning generative adversarial network 

摘      要：Spectrum prediction is one of the new techniques in cognitive radio that predicts changes in the spectrum state and plays a crucial role in improving spectrum sensing *** models previously trained in the source band tend to perform poorly in the new target band because of changes in the *** addition,cognitive radio devices require dynamic spectrum access,which means that the time to retrain the model in the new band is *** increase the amount of data in the target band,we use the GAN to convert the data of source band into target ***,we analyze the data differences between bands and calculate FID scores to identify the available bands with the slightest difference from the target predicted *** original GAN structure is unsuitable for converting spectrum data,and we propose the spectrum data conversion GAN(SDC-GAN).The generator module consists of a convolutional network and an LSTM module that can integrate multiple features of the data and can convert data from the source band to the target ***,we use the generated target band data to train the prediction *** experimental results validate the effectiveness of the proposed algorithm.