Online Learning-Based Discontinuous Reception (DRX) for Machine-Type Communications

4G systems employ discontinuous reception (DRX) mechanism to conserve energy by intermittently suspending network connections. Moving to 5G, a wide range of applications with diverse characteristics need to be supported. Especially, machine-type communication (MTC) has been identified as one of the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE internet of things journal 2019-06, Vol.6 (3), p.5550-5561
Main Authors: Zhou, Jianhong, Feng, Gang, Yum, Tak-Shing Peter, Yan, Mu, Qin, Shuang
Format: Article
Language:English
Subjects:
5G mobile communication
Actor–critic (AC)
Algorithms
Batteries
Communications traffic
Data communication
Delay
Delays
discontinuous reception (DRX)
Distance learning
Energy conservation
Energy efficiency
Energy management
Internet of Things
Machine learning
machine-type communication (MTC)
Optimization
Power consumption
Power demand
Power efficiency
Power management
reinforcement learning (RL)
Upper bounds
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:4G systems employ discontinuous reception (DRX) mechanism to conserve energy by intermittently suspending network connections. Moving to 5G, a wide range of applications with diverse characteristics need to be supported. Especially, machine-type communication (MTC) has been identified as one of the three generic 5G services. Compared with that of human-type communication (HTC), the traffic patterns of MTC could be very bursty and even nonstationary. Thus, using the legacy DRX mechanism will cause longer access delay and/or higher power consumption. In this paper, we propose a new online learning-based DRX mechanism, called AC-DRX, with aim to improve device energy efficiency for MTC services by adapting to varying traffic pattern. In AC-DRX, the time is slotted into intervals and actor-critic (AC) algorithm is used for adjusting DRX cycles by learning the traffic statistics at the beginning of every time interval. To accelerate the learning process, we propose a symmetric sampling method in the AC algorithm. Numerical results show that our proposed AC-DRX mechanism significantly outperforms the legacy DRX and extended DRX mechanisms in terms of both delay and energy efficiency. The performance is fairly close to the upper bound where perfect traffic knowledge is assumed known.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2019.2903347