Q value model.

<div><p>With the increasing popularity of cloud computing services, their large and dynamic load characteristics have rendered task scheduling an NP-complete problem.To address the problem of large-scale task scheduling in a cloud computing environment, this paper proposes a novel cloud...

Full description

Saved in:
Bibliographic Details
Main Author: Delong Cui (21730915) (author)
Other Authors: Zhiping Peng (5783078) (author), Kaibin Li (1571551) (author), Qirui Li (6578297) (author), Jieguang He (17100746) (author), Xiangwu Deng (6612770) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852017399090380800
author Delong Cui (21730915)
author2 Zhiping Peng (5783078)
Kaibin Li (1571551)
Qirui Li (6578297)
Jieguang He (17100746)
Xiangwu Deng (6612770)
author2_role author
author
author
author
author
author_facet Delong Cui (21730915)
Zhiping Peng (5783078)
Kaibin Li (1571551)
Qirui Li (6578297)
Jieguang He (17100746)
Xiangwu Deng (6612770)
author_role author
dc.creator.none.fl_str_mv Delong Cui (21730915)
Zhiping Peng (5783078)
Kaibin Li (1571551)
Qirui Li (6578297)
Jieguang He (17100746)
Xiangwu Deng (6612770)
dc.date.none.fl_str_mv 2025-08-21T17:40:54Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0329669.g003
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Q_value_model_/29961876
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
service level agreement
scale task scheduling
rendered task scheduling
one potential shortcoming
employs hierarchical scheduling
could impact real
classical heuristic algorithms
cloud task scheduling
experimental results demonstrate
skillfully balances cost
cost nodes within
cloud computing services
cloud computing environment
updating network parameters
performance heavily depends
framework &# 8217
allocate tasks first
dynamic load characteristics
designed using drl
cloud computing
cloud environments
experiments demonstrate
dynamic changes
load situations
load balancing
load balance
xlink ">
virtual machines
using low
training data
still shortcomings
resource utilization
paper proposes
overdue time
overall improvement
optimizing objectives
method used
machine learning
increasing popularity
framework defines
continuously learning
continuous learning
computational overhead
dc.title.none.fl_str_mv Q value model.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>With the increasing popularity of cloud computing services, their large and dynamic load characteristics have rendered task scheduling an NP-complete problem.To address the problem of large-scale task scheduling in a cloud computing environment, this paper proposes a novel cloud task scheduling framework using hierarchical deep reinforcement learning (DRL) to address the challenges of large-scale task scheduling in cloud computing. The framework defines a set of virtual machines (VMs) as a VM cluster and employs hierarchical scheduling to allocate tasks first to the cluster and then to individual VMs. The scheduler, designed using DRL, adapts to dynamic changes in the cloud environments by continuously learning and updating network parameters. Experiments demonstrate that it skillfully balances cost and performance. In low-load situations, costs are reduced by using low-cost nodes within the Service Level Agreement (SLA) range; in high-load situations, resource utilization is improved through load balancing. Compared with classical heuristic algorithms, it effectively optimizes load balancing, cost, and overdue time, achieving a 10% overall improvement. The experimental results demonstrate that this approach effectively balances cost and performance, optimizing objectives such as load balance, cost, and overdue time. One potential shortcoming of the proposed hierarchical deep reinforcement learning (DRL) framework for cloud task scheduling is its complexity and computational overhead. Implementing and maintaining a DRL-based scheduler requires significant computational resources and expertise in machine learning. There are still shortcomings in the method used in this study. First, the continuous learning and updating of network parameters might introduce latency, which could impact real-time task scheduling efficiency. Furthermore, the framework’s performance heavily depends on the quality and quantity of training data, which might be challenging to obtain and maintain in a dynamic cloud environment.</p></div>
eu_rights_str_mv openAccess
id Manara_70e88fa80eab00c8adcd293ea9b6d0da
identifier_str_mv 10.1371/journal.pone.0329669.g003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29961876
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Q value model.Delong Cui (21730915)Zhiping Peng (5783078)Kaibin Li (1571551)Qirui Li (6578297)Jieguang He (17100746)Xiangwu Deng (6612770)Science PolicySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedservice level agreementscale task schedulingrendered task schedulingone potential shortcomingemploys hierarchical schedulingcould impact realclassical heuristic algorithmscloud task schedulingexperimental results demonstrateskillfully balances costcost nodes withincloud computing servicescloud computing environmentupdating network parametersperformance heavily dependsframework &# 8217allocate tasks firstdynamic load characteristicsdesigned using drlcloud computingcloud environmentsexperiments demonstratedynamic changesload situationsload balancingload balancexlink ">virtual machinesusing lowtraining datastill shortcomingsresource utilizationpaper proposesoverdue timeoverall improvementoptimizing objectivesmethod usedmachine learningincreasing popularityframework definescontinuously learningcontinuous learningcomputational overhead<div><p>With the increasing popularity of cloud computing services, their large and dynamic load characteristics have rendered task scheduling an NP-complete problem.To address the problem of large-scale task scheduling in a cloud computing environment, this paper proposes a novel cloud task scheduling framework using hierarchical deep reinforcement learning (DRL) to address the challenges of large-scale task scheduling in cloud computing. The framework defines a set of virtual machines (VMs) as a VM cluster and employs hierarchical scheduling to allocate tasks first to the cluster and then to individual VMs. The scheduler, designed using DRL, adapts to dynamic changes in the cloud environments by continuously learning and updating network parameters. Experiments demonstrate that it skillfully balances cost and performance. In low-load situations, costs are reduced by using low-cost nodes within the Service Level Agreement (SLA) range; in high-load situations, resource utilization is improved through load balancing. Compared with classical heuristic algorithms, it effectively optimizes load balancing, cost, and overdue time, achieving a 10% overall improvement. The experimental results demonstrate that this approach effectively balances cost and performance, optimizing objectives such as load balance, cost, and overdue time. One potential shortcoming of the proposed hierarchical deep reinforcement learning (DRL) framework for cloud task scheduling is its complexity and computational overhead. Implementing and maintaining a DRL-based scheduler requires significant computational resources and expertise in machine learning. There are still shortcomings in the method used in this study. First, the continuous learning and updating of network parameters might introduce latency, which could impact real-time task scheduling efficiency. Furthermore, the framework’s performance heavily depends on the quality and quantity of training data, which might be challenging to obtain and maintain in a dynamic cloud environment.</p></div>2025-08-21T17:40:54ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0329669.g003https://figshare.com/articles/figure/Q_value_model_/29961876CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/299618762025-08-21T17:40:54Z
spellingShingle Q value model.
Delong Cui (21730915)
Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
service level agreement
scale task scheduling
rendered task scheduling
one potential shortcoming
employs hierarchical scheduling
could impact real
classical heuristic algorithms
cloud task scheduling
experimental results demonstrate
skillfully balances cost
cost nodes within
cloud computing services
cloud computing environment
updating network parameters
performance heavily depends
framework &# 8217
allocate tasks first
dynamic load characteristics
designed using drl
cloud computing
cloud environments
experiments demonstrate
dynamic changes
load situations
load balancing
load balance
xlink ">
virtual machines
using low
training data
still shortcomings
resource utilization
paper proposes
overdue time
overall improvement
optimizing objectives
method used
machine learning
increasing popularity
framework defines
continuously learning
continuous learning
computational overhead
status_str publishedVersion
title Q value model.
title_full Q value model.
title_fullStr Q value model.
title_full_unstemmed Q value model.
title_short Q value model.
title_sort Q value model.
topic Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
service level agreement
scale task scheduling
rendered task scheduling
one potential shortcoming
employs hierarchical scheduling
could impact real
classical heuristic algorithms
cloud task scheduling
experimental results demonstrate
skillfully balances cost
cost nodes within
cloud computing services
cloud computing environment
updating network parameters
performance heavily depends
framework &# 8217
allocate tasks first
dynamic load characteristics
designed using drl
cloud computing
cloud environments
experiments demonstrate
dynamic changes
load situations
load balancing
load balance
xlink ">
virtual machines
using low
training data
still shortcomings
resource utilization
paper proposes
overdue time
overall improvement
optimizing objectives
method used
machine learning
increasing popularity
framework defines
continuously learning
continuous learning
computational overhead