Related Experiment Video
Updated: Dec 16, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.8K
Application of deep neural network and deep reinforcement learning in wireless communication
Plos One
|July 3, 2020
Summary
Deep neural networks and deep reinforcement learning enhance wireless communication by enabling faster convergence and higher success rates in spectrum sharing. This accelerates the development of future wireless networks.
Area of Science:
- Wireless Communication
- Artificial Intelligence
- Machine Learning
Background:
- Wireless communication systems face challenges in efficient spectrum utilization.
- Cognitive radio aims to improve spectrum sharing between primary and secondary users.
Purpose of the Study:
- To explore the application of deep neural networks (DNNs) and deep reinforcement learning (DRL) in wireless communication.
- To accelerate the development of the wireless communication industry through intelligent algorithms.
Main Methods:
- A cognitive radio scenario with one primary and one secondary user was simulated.
- An intelligent power algorithm model based on DNNs and DRL was constructed and simulated using MATLAB.
- Two power control strategies were analyzed and compared.
Main Results:
- The proposed DRL-based DQN algorithm demonstrated a higher convergence rate compared to traditional DCPC algorithms.
- The algorithm achieved a high success rate in spectrum sharing.
- The second power control strategy was more conservative, requiring more iterations but achieving a success rate of 1.
Conclusions:
- DNNs and DRL effectively improve algorithm performance in wireless scenarios.
- The proposed approach offers a faster convergence rate and higher success rate for wireless communication networks.
- This study provides an experimental basis for advancing future wireless communication technologies.
