Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management

This paper investigates resource management in device-to-device (D2D) networks coexisting with cellular user equipment (CUEs). We introduce a novel model for joint scheduling and resource management in D2D networks, taking into account environmental constraints. To preserve information freshness, me...

Full description

Saved in:
Bibliographic Details
Main Authors: Parisa Parhizgar, Mehdi Mahdavi, Mohammad Reza Ahmadzadeh, Melike Erol-Kantarci
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Vehicular Technology
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10758763/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259848605728768
author Parisa Parhizgar
Mehdi Mahdavi
Mohammad Reza Ahmadzadeh
Melike Erol-Kantarci
author_facet Parisa Parhizgar
Mehdi Mahdavi
Mohammad Reza Ahmadzadeh
Melike Erol-Kantarci
author_sort Parisa Parhizgar
collection DOAJ
description This paper investigates resource management in device-to-device (D2D) networks coexisting with cellular user equipment (CUEs). We introduce a novel model for joint scheduling and resource management in D2D networks, taking into account environmental constraints. To preserve information freshness, measured by minimizing the average age of information (AoI), and to effectively utilize energy harvesting (EH) technology to satisfy the network's energy needs, we formulate an online optimization problem. This formulation considers factors such as the quality of service (QoS) for both CUEs and D2Ds, available power, information freshness, and environmental sensing requirements. Due to the mixed-integer nonlinear nature and online characteristics of the problem, we propose a deep reinforcement learning (DRL) approach to solve it effectively. Numerical results show that the proposed joint scheduling and resource management strategy, utilizing the soft actor-critic (SAC) algorithm, reduces the average AoI by 20% compared to other baseline methods.
format Article
id doaj-art-6bb8802852ba411eaa84f7fd2a106e95
institution OA Journals
issn 2644-1330
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Vehicular Technology
spelling doaj-art-6bb8802852ba411eaa84f7fd2a106e952025-08-20T01:55:46ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302025-01-016526710.1109/OJVT.2024.350280310758763Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource ManagementParisa Parhizgar0https://orcid.org/0009-0002-7799-0789Mehdi Mahdavi1https://orcid.org/0000-0003-4701-9377Mohammad Reza Ahmadzadeh2https://orcid.org/0000-0001-9558-5854Melike Erol-Kantarci3https://orcid.org/0000-0001-6787-8457Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, IranDepartment of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, IranDepartment of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, IranSchool of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, CanadaThis paper investigates resource management in device-to-device (D2D) networks coexisting with cellular user equipment (CUEs). We introduce a novel model for joint scheduling and resource management in D2D networks, taking into account environmental constraints. To preserve information freshness, measured by minimizing the average age of information (AoI), and to effectively utilize energy harvesting (EH) technology to satisfy the network's energy needs, we formulate an online optimization problem. This formulation considers factors such as the quality of service (QoS) for both CUEs and D2Ds, available power, information freshness, and environmental sensing requirements. Due to the mixed-integer nonlinear nature and online characteristics of the problem, we propose a deep reinforcement learning (DRL) approach to solve it effectively. Numerical results show that the proposed joint scheduling and resource management strategy, utilizing the soft actor-critic (SAC) algorithm, reduces the average AoI by 20% compared to other baseline methods.https://ieeexplore.ieee.org/document/10758763/Age of informationD2D communicationdeep reinforcement learningenergy harvestingresource allocationscheduling
spellingShingle Parisa Parhizgar
Mehdi Mahdavi
Mohammad Reza Ahmadzadeh
Melike Erol-Kantarci
Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
IEEE Open Journal of Vehicular Technology
Age of information
D2D communication
deep reinforcement learning
energy harvesting
resource allocation
scheduling
title Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
title_full Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
title_fullStr Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
title_full_unstemmed Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
title_short Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management
title_sort enhancing information freshness and energy efficiency in d2d networks through drl based scheduling and resource management
topic Age of information
D2D communication
deep reinforcement learning
energy harvesting
resource allocation
scheduling
url https://ieeexplore.ieee.org/document/10758763/
work_keys_str_mv AT parisaparhizgar enhancinginformationfreshnessandenergyefficiencyind2dnetworksthroughdrlbasedschedulingandresourcemanagement
AT mehdimahdavi enhancinginformationfreshnessandenergyefficiencyind2dnetworksthroughdrlbasedschedulingandresourcemanagement
AT mohammadrezaahmadzadeh enhancinginformationfreshnessandenergyefficiencyind2dnetworksthroughdrlbasedschedulingandresourcemanagement
AT melikeerolkantarci enhancinginformationfreshnessandenergyefficiencyind2dnetworksthroughdrlbasedschedulingandresourcemanagement