摘要
Software defined radio(SDR)is a wireless communication technology that uses modern software to control the traditional“pure hardware circuit”.It can provide an effective and secure solution to the problem of building multi-mode,multi-frequency and multifunction wireless communication equipment.Although the concept and application of SDR have been studied a lot,there is little discussion about the operating efficiency of the established system.For the purpose of shortening the delay of mapping and reducing the high computing load in the cloud,a radio monitoring system based on edge computing is developed to achieve the flexible,extensible and real-time monitoring of high-performance SDR applications.To promote the edge intelligence of deep learning(DL)service deployment through edge computing(EC),we developed an edge intelligence algorithm of convolutional neural network(CNN)based on attention mechanism to carry out modulation recognition(MR)of the edge signal and make MR closer to the antenna terminal.Through the experiment of the system and the edge algorithm,this thesis verifies the effectiveness of the developed multifunction radio signal monitoring system.
基金
supported by the National Natural Science Foundation of China under Grant 62061039
in part by Key project of Ningxia Natural Science Foundation under Grant 2020AAC02006.
