2022
DOI: 10.1109/ojcoms.2022.3175927
|View full text |Cite
|
Sign up to set email alerts
|

Adapting Deep Learning for Content Caching Frameworks in Device-to-Device Environments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 23 publications
0
3
0
Order By: Relevance
“…In the absence of prior knowledge, Souradeep Chakraborty et al 32 propose an "R2‐D2D" framework, which uses an LSTM stacked with a recently developed full‐scale convolutional neural network (CNN) 33 to make caching decisions. Rahul Bajpai et al 31 add attention mechanisms to the deep learning framework to carry out D2D content cache for time series prediction. This strategy can better adapt to realistic scenarios under the condition of minimum hypothesis.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…In the absence of prior knowledge, Souradeep Chakraborty et al 32 propose an "R2‐D2D" framework, which uses an LSTM stacked with a recently developed full‐scale convolutional neural network (CNN) 33 to make caching decisions. Rahul Bajpai et al 31 add attention mechanisms to the deep learning framework to carry out D2D content cache for time series prediction. This strategy can better adapt to realistic scenarios under the condition of minimum hypothesis.…”
Section: Related Workmentioning
confidence: 99%
“…28 Jiang et al 29 designe a D2D caching strategy using multiagent reinforcement learning, and used Q-learning to learn how to coordinate the caching decisions. Li et al 30 use the echo state network (ESN) and long short-term memory (LSTM) network 31 to predict user mobility and content popularity, not only improving the cache hit rate but they also reduced the request content delivery delay and energy consumption. In the absence of prior knowledge, Souradeep Chakraborty et al 32 propose an εR2-D2Dε framework, which uses an LSTM stacked with a recently developed full-scale convolutional neural network (CNN) 33 to make caching decisions.…”
Section: Related Workmentioning
confidence: 99%
“…networks to improve the content delivery process [6]. In cacheenabled wireless networks, the popular contents are usually fetched from the core network during off-peak times [7], [8], and the users can directly receive the requested contents from the edge nodes rather than from the core network. As a result, the transmission latency can be significantly reduced since the data is closer to the users.…”
Section: Introductionmentioning
confidence: 99%