Optimizing Energy Efficiency in UAV-Assisted Networks Using Deep Reinforcement Learning

Babatunji Omoniwa; Boris Galkin; Ivana Dusparic

doi:10.1109/LWC.2022.3167568

Optimizing Energy Efficiency in UAV-Assisted Networks Using Deep Reinforcement Learning

Babatunji Omoniwa
, Boris Galkin
, Ivana Dusparic

Trinity College Dublin

Research output: Contribution to journal › Article › peer-review

Abstract

In this letter, we study the energy efficiency (EE) optimization of unmanned aerial vehicles (UAVs) providing wireless coverage to static and mobile ground users. Recent multi-agent reinforcement learning approaches optimise the system's EE using a 2D trajectory design, neglecting interference from nearby UAV cells. We aim to maximize the system's EE by jointly optimizing each UAV's 3D trajectory, number of connected users, and the energy consumed, while accounting for interference. Thus, we propose a cooperative Multi-Agent Decentralized Double Deep Q-Network (MAD-DDQN) approach. Our approach outperforms existing baselines in terms of EE by as much as 55 - 80%.

Original language	English
Pages (from-to)	1590-1594
Number of pages	5
Journal	IEEE Wireless Communications Letters
Volume	11
Issue number	8
DOIs	https://doi.org/10.1109/LWC.2022.3167568
Publication status	Published - 1 Aug 2022
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Deep reinforcement learning
Energy efficiency
Multi-agent system
UAV base stations

Access to Document

10.1109/LWC.2022.3167568

Cite this

@article{f55ec86abf134926bfa673cd9f58c76b,

title = "Optimizing Energy Efficiency in UAV-Assisted Networks Using Deep Reinforcement Learning",

abstract = "In this letter, we study the energy efficiency (EE) optimization of unmanned aerial vehicles (UAVs) providing wireless coverage to static and mobile ground users. Recent multi-agent reinforcement learning approaches optimise the system's EE using a 2D trajectory design, neglecting interference from nearby UAV cells. We aim to maximize the system's EE by jointly optimizing each UAV's 3D trajectory, number of connected users, and the energy consumed, while accounting for interference. Thus, we propose a cooperative Multi-Agent Decentralized Double Deep Q-Network (MAD-DDQN) approach. Our approach outperforms existing baselines in terms of EE by as much as 55 - 80\%.",

keywords = "Deep reinforcement learning, Energy efficiency, Multi-agent system, UAV base stations",

author = "Babatunji Omoniwa and Boris Galkin and Ivana Dusparic",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2022",

month = aug,

day = "1",

doi = "10.1109/LWC.2022.3167568",

language = "English",

volume = "11",

pages = "1590--1594",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "IEEE Communications Society",

number = "8",

}

TY - JOUR

T1 - Optimizing Energy Efficiency in UAV-Assisted Networks Using Deep Reinforcement Learning

AU - Omoniwa, Babatunji

AU - Galkin, Boris

AU - Dusparic, Ivana

PY - 2022/8/1

Y1 - 2022/8/1

N2 - In this letter, we study the energy efficiency (EE) optimization of unmanned aerial vehicles (UAVs) providing wireless coverage to static and mobile ground users. Recent multi-agent reinforcement learning approaches optimise the system's EE using a 2D trajectory design, neglecting interference from nearby UAV cells. We aim to maximize the system's EE by jointly optimizing each UAV's 3D trajectory, number of connected users, and the energy consumed, while accounting for interference. Thus, we propose a cooperative Multi-Agent Decentralized Double Deep Q-Network (MAD-DDQN) approach. Our approach outperforms existing baselines in terms of EE by as much as 55 - 80%.

AB - In this letter, we study the energy efficiency (EE) optimization of unmanned aerial vehicles (UAVs) providing wireless coverage to static and mobile ground users. Recent multi-agent reinforcement learning approaches optimise the system's EE using a 2D trajectory design, neglecting interference from nearby UAV cells. We aim to maximize the system's EE by jointly optimizing each UAV's 3D trajectory, number of connected users, and the energy consumed, while accounting for interference. Thus, we propose a cooperative Multi-Agent Decentralized Double Deep Q-Network (MAD-DDQN) approach. Our approach outperforms existing baselines in terms of EE by as much as 55 - 80%.

KW - Deep reinforcement learning

KW - Energy efficiency

KW - Multi-agent system

KW - UAV base stations

UR - https://www.scopus.com/pages/publications/85128692144

U2 - 10.1109/LWC.2022.3167568

DO - 10.1109/LWC.2022.3167568

M3 - Article

AN - SCOPUS:85128692144

SN - 2162-2337

VL - 11

SP - 1590

EP - 1594

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 8

ER -

Optimizing Energy Efficiency in UAV-Assisted Networks Using Deep Reinforcement Learning

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this