Deep Learning-Inspired Message Passing Algorithm for Efficient Resource Allocation in Cognitive Radio Networks

Energy efficiency (EE) and spectrum efficiency (SE) have received significant attentions on optimizing the network performance in cognitive radio networks. In this paper, an EE+SE tradeoff based target is considered for the primary users (PUs) and the secondary users (SUs). First of all, considering...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on vehicular technology Vol. 68; no. 1; pp. 641 - 653
Main Authors: Liu, Miao, Song, Tiecheng, Hu, Jing, Yang, Jie, Gui, Guan
Format: Journal Article
Language:English
Published: New York IEEE 01.01.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Back propagation
Back propagation networks
Cognitive radio
Computer simulation
Computing time
Deep learning
Efficiency
efficiency tradeoff
Frequency division multiple access
Interference
IP networks
Message passing
Neural networks
Optimization
Power consumption
Resource allocation
Resource management
ISSN:0018-9545, 1939-9359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Energy efficiency (EE) and spectrum efficiency (SE) have received significant attentions on optimizing the network performance in cognitive radio networks. In this paper, an EE+SE tradeoff based target is considered for the primary users (PUs) and the secondary users (SUs). First of all, considering the orthogonal frequency division multiple access-based resource allocation (RA) for the underlying SUs, we formulate an objective function through minimizing a weighted sum of the secondary interference power, where the network performance of both PUs and SUs are guaranteed by the constraints on quality of service, power consumption and data rate. However, it is a NP-hard problem. In order to solve it, we propose a damped three dimensional (D3D) message-passing algorithm (MPA) based on deep learning. Specifically, a feed-forward neural network is devised and an analogous back propagation algorithm is developed to learn the optimal parameters of the D3D-MPA. To improve the computational efficiency of the allocation and the learning, a suboptimal RA scheme is deduced based on a damped two dimensional MPA. Finally, simulation results are provided to confirm the effectiveness of our proposed scheme.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2018.2883669