D2D communication energy efficiency maximization power distribution method based on deep neural network

Abstract

The invention discloses a D2D communication energy efficiency maximization power distribution method based on a deep neural network, and is suitable for the field of communication. The method comprises the following steps: firstly, enabling a base station to select cellular users through a scheduling algorithm to share frequency resources with a plurality of selected D2D links for use; feeding back channel state information to the base station by the dispatched and activated cellular users and a plurality of pairs of D2D users; then enabling the base station to import the obtained channel state information of the cellular users and the D2D users into a trained deep neural network system to obtain a power distribution scheme with maximized D2D link energy efficiency; and finally, enabling the D2D link sending end to complete data transmission according to the power distribution scheme. The method can be effectively applied to an actual scene, the base station can quickly calculate the power distribution scheme after obtaining the real-time channel state information by using the trained deep neural network system, the method has the advantage of low time delay, the spectral efficiency can be improved to a greater extent, the energy efficiency is improved, and green communication is realized.

Description

technical field [0001] The present invention relates to a power allocation method for D2D communication energy efficiency maximization, in particular to a D2D communication energy efficiency maximization power allocation method based on a deep neural network, which is suitable for use in the field of mobile communication devices and device adaptive resource allocation. Background technique [0002] In recent years, deep learning (DL) has achieved great success in the fields of computer vision (CV), natural language processing (NLP) and automatic speech recognition (ASR), and has been tried to solve some problems in mobile communication, and At present, DL has been specifically applied in many aspects such as cognitive radio, resource management, line adaptation, modulation recognition, decoding and detection. [0003] DL is a branch of machine learning (ML). Through multi-layer nonlinear processing units, useful information can be extracted hierarchically from raw data in or...

AI Technical Summary

Problems solved by technology

In the communication scenario considered in the present invention, there are multiple optimization requirements. On the premise of ensuring the communication quality of cellular users, the access of multiple D2D links improves the spectrum efficiency and optimizes the energy efficiency of the D2D links at the same time. Traditional optimization When the algorithm solves such complex optimization problems, it often needs multiple iterations to reach the optimal solution, and some even cannot reach the global optimal solution.

If the number of iterations is large, the corresponding calculation time will be longer, which undoubtedly cannot meet the low-latency requirements in real-time communication, and DNN has an advantage in calculation timeliness. A well-trained neural network system can improve the timeliness of the output power allocation scheme. within milliseconds

Images