Resource Allocation Based on Deep Neural Networks for Cognitive Radio Networks

TL;DR

This paper proposes a deep neural network-based resource allocation strategy for cognitive radio networks, achieving real-time performance and efficiency in computation time compared to traditional methods.

Contribution

It introduces a novel DNN-based resource allocation method and a training approach tailored for CRNs, addressing real-time implementation challenges.

Findings

DNN-based strategy reduces computation time.

The proposed method outperforms conventional schemes.

Efficient training method for neural networks in CRNs.

Abstract

Resource allocation is of great importance in the next generation wireless communication systems, especially for cognitive radio networks (CRNs). Many resource allocation strategies have been proposed to optimize the performance of CRNs. However, it is challenging to implement these strategies and achieve real-time performance in wireless systems since most of them need accurate and timely channel state information and/or other network statistics. In this paper a resource allocation strategy based on deep neural networks (DNN) is proposed and the training method is presented to train the neural networks. Simulation results show that our proposed strategy based on DNN is efficient in terms of the computation time compared with the conventional resource allocation schemes.