doi: 10.18178/ijfcc.2019.8.3.543
Grouping and Cooperating among APs for Energy Efficiency in 5G UUDN
Chunhong Duo
,
Yongqian Li
,
Baogang Li
,
Yabo Lv
- Department of Electronic and Communications Engineering, North China Electric Power University, Hebei, China.
Abstract
The user-centric ultra-dense network (UUDN) is considered as a promising technology for 5G. However, the massive deployment of access points (APs) would lead to a considerable increase in energy consumption. Considering user’s different service flow and system energy efficiency, we propose a user-centric access algorithm through renewable energy cooperation. Firstly, the access point group (APG), which consists of several APs, is dynamically organized to serve each user in UUDN. Then, to maximize the system energy efficiency, we propose a reinforcement learning approach to cooperate renewable energy. Q neural network which adopts a three-layer BP neural network solves the problem of Q learning in continuous state and discrete action. Meanwhile, by optimizing the resource allocation in a cooperative way, the proposed algorithm compared to the existing algorithms has better performance in satisfying user’s demand and improving system energy efficiency.
Keywords
- Energy cooperation
- energy harvesting
- reinforcement learning
- user-centric ultra-dense network (UUDN)
How to Cite
Chunhong Duo, Yongqian Li, Baogang Li, and Yabo Lv, "Grouping and Cooperating among APs for Energy Efficiency in 5G UUDN," International Journal of Future Computer and Communication, vol. 8, no. 3, pp. 72-79, 2019. https://doi.org/ 10.18178/ijfcc.2019.8.3.543
Copyright & License
Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).