scholarly journals DeepChunk: Deep Q-Learning for Chunk-Based Caching in Wireless Data Processing Networks

2019 ◽  
Vol 5 (4) ◽  
pp. 1034-1045
Author(s):  
Yimeng Wang ◽  
Yongbo Li ◽  
Tian Lan ◽  
Vaneet Aggarwal
Keyword(s):  
Data Processing ◽  
Wireless Data ◽  
Q Learning ◽  
Processing Networks

scholarly journals A Resource Allocation Algorithm for Ultra-Dense Networks Based on Deep Reinforcement Learning

2021 ◽  
Vol 16 (2) ◽  
Author(s):  
Huashuai Zhang ◽  
Tingmei Wang ◽  
Haiwei Shen
Keyword(s):  
Resource Allocation ◽  
Reinforcement Learning ◽  
Data Traffic ◽  
Wireless Data ◽  
Resource Allocation Algorithm ◽  
Allocation Algorithm ◽  
Q Learning ◽  
Dense Networks ◽  
Target Network ◽  
Wireless Resource Allocation

The resource optimization of ultra-dense networks (UDNs) is critical to meet the huge demand of users for wireless data traffic. But the mainstream optimization algorithms have many problems, such as the poor optimization effect, and high computing load. This paper puts forward a wireless resource allocation algorithm based on deep reinforcement learning (DRL), which aims to maximize the total throughput of the entire network and transform the resource allocation problem into a deep Q-learning process. To effectively allocate resources in UDNs, the DRL algorithm was introduced to improve the allocation efficiency of wireless resources; the authors adopted the resource allocation strategy of the deep Q-network (DQN), and employed empirical repetition and target network to overcome the instability and divergence of the results caused by the previous network state, and to solve the overestimation of the Q value. Simulation results show that the proposed algorithm can maximize the total throughput of the network, while making the network more energy-efficient and stable. Thus, it is very meaningful to introduce the DRL to the research of UDN resource allocation.

GaAs fiber-optic modules for optical data processing networks

1991 ◽  
Vol 9 (12) ◽  
pp. 1755-1763 ◽  
Author(s):  
J.F. Ewen ◽  
K.P. Jackson ◽  
R.J.S. Bates ◽  
E.B. Flint
Keyword(s):  
Data Processing ◽  
Fiber Optic ◽  
Optical Data ◽  
Optical Data Processing ◽  
Processing Networks

Queueing Theory Applied to Data Processing Networks

1982 ◽  
Vol 12 (4) ◽  
pp. 21-32
Author(s):  
Bruce E. Krell ◽  
Maria Arminlo
Keyword(s):  
Data Processing ◽  
Queueing Theory ◽  
Processing Networks

Study on the Smart Handheld Wireless Oscilloscope

2013 ◽  
Vol 416-417 ◽  
pp. 1325-1330 ◽  
Author(s):  
Jun Jiang ◽  
Huan Qu ◽  
Shu Lin Tian
Keyword(s):  
Data Processing ◽  
Acquisition System ◽  
Handheld Devices ◽  
Sampled Data ◽  
Wireless Data ◽  
Operation System ◽  
Real Time Processing ◽  
Digital Oscilloscope ◽  
Handheld Device ◽  
System Composition

As the digital acquisition system is featured by increasingly higher technical targets and more complicated applicable conditions, the traditional digital oscilloscope has become incapable of meeting the requirements of real-time processing of sampled data and waveform display on one hand, and unqualified for field test in hard risky conditions on the other. This paper aims for comprehensively enhancing the digital oscilloscopes data processing, image display, human-machine interface and portable adaptability. To that end, it approaches the system composition of improved oscilloscope, and renders a chance to wirelessly connect the oscilloscope with any of the Smart Handheld Devices with Android operation system through the added wireless data interactive channel, which forms a smart handheld wireless oscilloscope. Such oscilloscope adopts the divisional coordination between data acquisition system and Smart Handheld Device to greatly improve data processing, waveform display and HMI, and realize wireless operation of remote test as a result.

Sign in / Sign up

Export Citation Format

Share Document