Heterogeneous wireless D2D network link scheduling method based on graph neural network

Abstract

The invention discloses a heterogeneous wireless D2D network link scheduling method based on a graph neural network. The method comprises the following steps: constructing a heterogeneous wireless D2D network; determining a training set and a test set; modeling the heterogeneous wireless D2D networks in the training set and the test set into a heterogeneous graph; constructing a heterogeneous graph convolutional neural network model, and initializing a neural network weight; using the training set to train the heterogeneous graph convolutional neural network model, and using the test set to verify to obtain a trained heterogeneous graph convolutional neural network; and inputting data to the trained heterogeneous graph convolutional neural network, and outputting a link scheduling strategy. The method is used for wireless resource scheduling of the D2D network, and the transmission rate performance of the heterogeneous D2D network is maximized.

Description

technical field [0001] The present invention relates to the technical field of wireless communication networks, in particular to a method for scheduling links of heterogeneous wireless D2D networks based on graph neural networks. Background technique [0002] D2D (Device to Device) technology is one of the key technologies in the development of 5G wireless communication. D2D technology enables user communication equipment within a certain distance to communicate directly, aiming to reduce the load of the serving base station. There are three types of D2D communication methods. The first is dedicated mode, where D2D pairs exchange data directly without involving base stations. Spectrum resources allocated in this transmission mode are only dedicated to a certain pair and are not shared with other users. The second type is the sharing mode, in which the same spectrum resources can be shared between cellular users and D2D users, and between D2D users and D2D users. The thir...

AI Technical Summary

Problems solved by technology

[0003] Most of these machine learning methods are based on homogeneous wireless communication networks. Due to the different types of D2D devices in heterogeneous wireless D2D networks, different numbers of antennas may be used for communication between devices. Traditional machine learning techniques cannot extract heterogeneous network features. Difficult to generalize across heterogeneous networks

Images