Energy-Aware Dynamic VNF Splitting in O-RAN Using Deep Reinforcement Learning

被引：5

作者：

Amiri, Esmaeil ^{[1
]}

Wang, Ning ^{[1
]}

Shojafar, Mohammad ^{[1
]}

Tafazolli, Rahim ^{[1
]}

机构：

[1] Univ Surrey, 5G 6GIC, Guildford GU2 7XH, England

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2023年 / 12卷 / 11期

基金：

英国工程与自然科学研究理事会;

关键词：

Open RAN (O-RAN); virtual network function (VNF); energy efficiency; deep reinforcement learning (DRL); NETWORK FUNCTION PLACEMENT;

D O I：

10.1109/LWC.2023.3298548

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This letter proposes an innovative energy-efficient Radio Access Network (RAN) disaggregation and virtualization method for Open RAN (O-RAN) that effectively addresses the challenges posed by dynamic traffic conditions. In this case, the energy consumption is primarily formulated as a multi-objective optimization problem and then solved by integrating Advantage Actor-Critic (A2C) algorithm with a sequence-to-sequence model due to sequentially of RAN disaggregation and long-term dependencies. According to the results, our proposed solution for dynamic Virtual Network Functions (VNF) splitting outperforms approaches that do not involve VNF splitting, significantly reducing energy consumption. The solution achieves up to 56% and 63% for business and residential areas under traffic conditions, respectively.

引用

页码：1891 / 1895

页数：5

共 42 条

[41] Energy Efficiency Optimization for SWIPT-Based D2D-Underlaid Cellular Networks Using Multiagent Deep Reinforcement Learning
Muy, Sengly
Ron, Dara
Lee, Jung-Ryun
[J]. IEEE SYSTEMS JOURNAL, 2022, 16 (02): : 3130 - 3138
[42] Sub-Connected Hybrid Precoding and Trajectory Optimization Using Deep Reinforcement Learning for Energy-Efficient Millimeter-Wave UAV Communications
Silvirianti
Shin, Soo Young
[J]. IEEE WIRELESS COMMUNICATIONS LETTERS, 2023, 12 (09) : 1642 - 1646

← 1 2 3 4 5 →