DDPG-Based Radio Resource Management for User Interactive Mobile Edge Networks

被引：9

作者：

Chen, Po-Chen ^{[1
]}

Chen, Yen-Chen ^{[1
]}

Huang, Wei-Hsiang ^{[1
]}

Huang, Chih-Wei ^{[1
]}

Tirkkonen, Olav ^{[2
]}

机构：

[1] Natl Cent Univ, Dept Commun Engn, Taoyuan, Taiwan

[2] Aalto Univ, Dept Commun & Networking, Espoo, Finland

来源：

2020 2ND 6G WIRELESS SUMMIT (6G SUMMIT) | 2020年

关键词：

Deep Deterministic Policy Gradient (DDPG); machine learning; reinforcement learning; radio resource management; mobile edge network; virtual reality;

D O I：

10.1109/6gsummit49458.2020.9083926

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The development of the fifth-generation (SG) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.

引用

页数：5

共 15 条

[1]

3GPP, TS 23.501

[2]

[Anonymous], 2015, COMPUTER SCI

[3]

[Anonymous], 2017, BIOMED RES INT, DOI DOI 10.1155/2017/3250485

[4] Virtual Reality Over Wireless Networks: Quality-of-Service Model and Learning-Based Resource Management [J].