template.pdf (1.05 MB)
Deep learning-based edge caching for multi-cluster heterogeneous networks
journal contribution
posted on 2019-05-24, 08:55 authored by Jiachen Yang, Jipeng Zhang, Chaofan Ma, Huihui Wang, Juping Zhang, Gan Zheng© 2019, Springer-Verlag London Ltd., part of Springer Nature. In this work, we consider a time and space evolution cache refreshing in multi-cluster heterogeneous networks. We consider a two-step content placement probability optimization. At the initial complete cache refreshing optimization, the joint optimization of the activated base station density and the content placement probability is considered. And we transform this optimization problem into a GP problem. At the following partial cache refreshing optimization, we take the time–space evolution into consideration and derive a convex optimization problem subjected to the cache capacity constraint and the backhaul limit constraint. We exploit the redundant information in different content popularity using the deep neural network to avoid the repeated calculation because of the change in content popularity distribution at different time slots. Trained DNN can provide online response to content placement in a multi-cluster HetNet model instantaneously. Numerical results demonstrate the great approximation to the optimum and generalization ability.
History
School
- Mechanical, Electrical and Manufacturing Engineering
Published in
Neural Computing and ApplicationsVolume
32Issue
19Pages
15317 - 15328Citation
YANG, J. ... et al., 2020. Deep learning-based edge caching for multi-cluster heterogeneous networks. Neural Computing and Applications, 32 (19), pp.15317-15328.Publisher
© Springer (part of Springer Nature)Version
- AM (Accepted Manuscript)
Publisher statement
This is a post-peer-review, pre-copyedit version of an article published in Neural Computing and Applications. The final authenticated version is available online at: https://doi.org/10.1007/s00521-019-04040-z.Acceptance date
2019-01-14Publication date
2019-02-18ISSN
0941-0643eISSN
1433-3058Publisher version
Language
- en