Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment

In the ever-evolving landscape of cloud computing, fog and edge computing have become more prominent because of their natural property of proximity to demanding parts. With all the heterogeneity on the task processor side, generators have a variety of requirements in terms of complexity and latency....

Full description

Saved in:
Bibliographic Details
Main Authors: Alp Gokhan Hossucu, Suat Ozdemir
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11003872/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849732103175929856
author Alp Gokhan Hossucu
Suat Ozdemir
author_facet Alp Gokhan Hossucu
Suat Ozdemir
author_sort Alp Gokhan Hossucu
collection DOAJ
description In the ever-evolving landscape of cloud computing, fog and edge computing have become more prominent because of their natural property of proximity to demanding parts. With all the heterogeneity on the task processor side, generators have a variety of requirements in terms of complexity and latency. This study gathered all these different dimensions together in a robust ecosystem that can simulate a large number of various scenarios that meet changing requirements for task coordination and serves as a versatile platform for exploring strategies. A comprehensive multi-layered cloud simulation model that intricately considers both low-level edge/fog and cloud environment constraints is proposed. At the core of this contribution lies a novel task orchestration model that transforms the orchestration process into reinforcement learning training steps. The proposed approach offers substantial advantages in terms of task succession, energy efficiency, and resource utilization. The system was evaluated in a simulation developed under different fog computing environmental conditions in terms of edge device and task density. The results of the experiment proved the superiority of the proposed system over the existing round-robin heuristic-based algorithms and the offloading of policy baselines with an overall increase in precision 28%. In addition, a smart action space reduction technique is introduced to reduce the complexity of the action space, the proposed technique simplifies the decision-making process, leading to faster convergence and improved training efficiency.
format Article
id doaj-art-bdf7cc9185a342daa0f803f4182ac82e
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-bdf7cc9185a342daa0f803f4182ac82e2025-08-20T03:08:20ZengIEEEIEEE Access2169-35362025-01-0113850048502510.1109/ACCESS.2025.356978111003872Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation EnvironmentAlp Gokhan Hossucu0https://orcid.org/0000-0003-4699-1770Suat Ozdemir1https://orcid.org/0000-0002-4588-4538Department of Computer Engineering, Hacettepe University, Ankara, TürkiyeDepartment of Computer Engineering, Hacettepe University, Ankara, TürkiyeIn the ever-evolving landscape of cloud computing, fog and edge computing have become more prominent because of their natural property of proximity to demanding parts. With all the heterogeneity on the task processor side, generators have a variety of requirements in terms of complexity and latency. This study gathered all these different dimensions together in a robust ecosystem that can simulate a large number of various scenarios that meet changing requirements for task coordination and serves as a versatile platform for exploring strategies. A comprehensive multi-layered cloud simulation model that intricately considers both low-level edge/fog and cloud environment constraints is proposed. At the core of this contribution lies a novel task orchestration model that transforms the orchestration process into reinforcement learning training steps. The proposed approach offers substantial advantages in terms of task succession, energy efficiency, and resource utilization. The system was evaluated in a simulation developed under different fog computing environmental conditions in terms of edge device and task density. The results of the experiment proved the superiority of the proposed system over the existing round-robin heuristic-based algorithms and the offloading of policy baselines with an overall increase in precision 28%. In addition, a smart action space reduction technique is introduced to reduce the complexity of the action space, the proposed technique simplifies the decision-making process, leading to faster convergence and improved training efficiency.https://ieeexplore.ieee.org/document/11003872/Deep reinforcement learningedge computingfog computingq-learningsoftware-defined networkstask offloading
spellingShingle Alp Gokhan Hossucu
Suat Ozdemir
Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
IEEE Access
Deep reinforcement learning
edge computing
fog computing
q-learning
software-defined networks
task offloading
title Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
title_full Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
title_fullStr Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
title_full_unstemmed Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
title_short Context Aware Task Orchestration With Deep Reinforcement Learning in Real Time Fog Computing Simulation Environment
title_sort context aware task orchestration with deep reinforcement learning in real time fog computing simulation environment
topic Deep reinforcement learning
edge computing
fog computing
q-learning
software-defined networks
task offloading
url https://ieeexplore.ieee.org/document/11003872/
work_keys_str_mv AT alpgokhanhossucu contextawaretaskorchestrationwithdeepreinforcementlearninginrealtimefogcomputingsimulationenvironment
AT suatozdemir contextawaretaskorchestrationwithdeepreinforcementlearninginrealtimefogcomputingsimulationenvironment