Intelligent caching in UAV-aided networks
Intelligent caching in UAV-aided networks
Deployment of unmanned aerial vehicles (UAVs) as flying base stations to provide specific geographical area with air-to-ground wireless communications is expected to increase dramatically in the coming decades, owing to its flexibility, mobility and autonomy. Moreover, mobile edge computing (MEC) promises significant reduction in latency by caching popular contents at the mobile edge. In this paper, we propose a method to apply mobile edge caching on UAVs in wireless communication systems. By investigating the user request preference with the aid of latent Dirichlet allocation (LDA), the caching strategy can be optimized. In the proposed system, we consider the design of intelligent caching strategies when a number of UAVs are deployed to serve ground users, where each UAV has a limited storage capacity for caching useful user contents. We use LDA to extract the user request preferences in order to intelligently cache data in the UAVs, while we use K-means clustering to associate users with the UAVs. We consider three caching criteria, namely the user received signal to noise ratio (SNR), user preferences and the delay. Our simulation results show that, when compared to random caching, the average caching efficiency could be significantly improved from <formula><tex>$50 \%$</tex></formula> to <formula><tex>$70 \%$</tex></formula>, while the latency of our proposed system can also be greatly reduced.
5G mobile communication, Cloud computing, Delays, LDA, Servers, Signal to noise ratio, Training, UAV, Wireless communication, association, content, drone, mobile edge caching, wireless network
739-752
Zhang, Mingze
137e3c92-cc6a-4e9c-b724-936938ea3e79
El-Hajjar, Mohammed
3a829028-a427-4123-b885-2bab81a44b6f
Ng, Soon Xin
e19a63b0-0f12-4591-ab5f-554820d5f78c
13 November 2021
Zhang, Mingze
137e3c92-cc6a-4e9c-b724-936938ea3e79
El-Hajjar, Mohammed
3a829028-a427-4123-b885-2bab81a44b6f
Ng, Soon Xin
e19a63b0-0f12-4591-ab5f-554820d5f78c
Zhang, Mingze, El-Hajjar, Mohammed and Ng, Soon Xin
(2021)
Intelligent caching in UAV-aided networks.
IEEE Transactions on Vehicular Technology, 71 (1), .
(doi:10.1109/TVT.2021.3125396).
Abstract
Deployment of unmanned aerial vehicles (UAVs) as flying base stations to provide specific geographical area with air-to-ground wireless communications is expected to increase dramatically in the coming decades, owing to its flexibility, mobility and autonomy. Moreover, mobile edge computing (MEC) promises significant reduction in latency by caching popular contents at the mobile edge. In this paper, we propose a method to apply mobile edge caching on UAVs in wireless communication systems. By investigating the user request preference with the aid of latent Dirichlet allocation (LDA), the caching strategy can be optimized. In the proposed system, we consider the design of intelligent caching strategies when a number of UAVs are deployed to serve ground users, where each UAV has a limited storage capacity for caching useful user contents. We use LDA to extract the user request preferences in order to intelligently cache data in the UAVs, while we use K-means clustering to associate users with the UAVs. We consider three caching criteria, namely the user received signal to noise ratio (SNR), user preferences and the delay. Our simulation results show that, when compared to random caching, the average caching efficiency could be significantly improved from <formula><tex>$50 \%$</tex></formula> to <formula><tex>$70 \%$</tex></formula>, while the latency of our proposed system can also be greatly reduced.
Text
FINAL VERSION
- Accepted Manuscript
More information
Accepted/In Press date: 1 November 2021
e-pub ahead of print date: 8 November 2021
Published date: 13 November 2021
Additional Information:
Publisher Copyright:
IEEE
Keywords:
5G mobile communication, Cloud computing, Delays, LDA, Servers, Signal to noise ratio, Training, UAV, Wireless communication, association, content, drone, mobile edge caching, wireless network
Identifiers
Local EPrints ID: 452277
URI: http://eprints.soton.ac.uk/id/eprint/452277
ISSN: 0018-9545
PURE UUID: 37e725e3-4c4c-4dc3-9895-3e788c975f1e
Catalogue record
Date deposited: 03 Dec 2021 17:30
Last modified: 01 Nov 2024 02:44
Export record
Altmetrics
Contributors
Author:
Mingze Zhang
Author:
Mohammed El-Hajjar
Author:
Soon Xin Ng
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics