Loading...
  • Table of Content
      01 October 2024, Volume 1 Issue 10 Previous Issue   
    For Selected: View Abstracts Toggle Thumbnails
    Research on New Cloud Networking for Computing Power Networks
    QI Yu CHEN Zi-yu GU Da-peng WEN Ke-xin TU Yan-li
    Computer & Telecommunication. 2024, 1 (10): 6-.   DOI: 10.15966/j.cnki.dnydx.2024.10.007
    As the two core elements of information infrastructure, computing power and network mutually promote and deeply inte‐ grate to promote the continuous evolution of computing power networks. Technologies such as L3VPN, SRv6/G-SRv6 are deployed in cloud private networks to provide unified support for cloud networking services, and to provide differentiated, lower latency, and higher reliability new cloud networking business products. This article conducts research on the application of new technologies such as SRV6 in cloud private network networking, providing differentiated business carrying capacity for different tenants and busi‐ nesses, supporting new cloud network business capabilities such as low latency, large bandwidth, and high reliability. The focus is on solving the current business needs of 2B industry customers, such as low latency, data backup, and large bandwidth, which cannot meet their cloud entry needs.
    Related Articles | Metrics
    Cognitive Radio Power Control Based on Deep Reinforcement Learning
    CHEN Ling-ling HUANG Fu-sen YU Yue
    Computer & Telecommunication. 2024, 1 (10): 10-.   DOI: 10.15966/j.cnki.dnydx.2024.10.006
    With the rapid development of technology, people's demand for wireless spectrum is increasing. However, due to limited spectrum resources, how to effectively utilize these resources has become a major challenge in the field of radio. To address this is‐ sue, we establish a cognitive wireless network model where primary and secondary users share the same spectrum resources and work in a non cooperative manner to improve the throughput of secondary users. Then, we use the SumTree Sampling Deep QNetwork (ST-DQN) algorithm for power control to ensure priority and diversity in sample selection. Finally, a series of simulation experiments are conducted using Python to compare and analyze the performance indicators of reward, loss function, and sub user throughput with traditional Q-learning and free exploration algorithms. We find that the ST-DQN algorithm performs better in power control.
    Related Articles | Metrics
  News More  


  Links More  


Copyright © Computer & Telecommunication, All Rights Reserved.
Powered by Beijing Magtech Co. Ltd