A Cloud QoS-driven Scheduler based on Deep Reinforcement Learning

Tran, Minh-Ngoc; Kim, Young-Han

doi:10.1109/ictc52510.2021.9621055

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tran et al 31 introduces the Q-learning approach in order to address the issue of directed acyclic graph tasks in data-centres. To reduce energy usage, k-means clustering and dynamic VM migration have been used to create energy-efficient dynamic resource management.…”

Section: Related Workmentioning

confidence: 99%

Energy Optimized Workflow Scheduling in IaaS Cloud: A Flower Pollination based Approach

Jaiprakash,

Arya,

Gupta

et al. 2023

Preprint

View full text Add to dashboard Cite

The energy consumption of cloud data centers is a critical concern that could affect both the environment and the availability of energy resources. For this, the global community and industries are taking measures to address this issue that is caused by the high electricity consumption of servers, Heating, Ventilation, and Air Conditioning (HVAC) in the data centers. With this context, this paper presents a novel approach for scheduling energy-efficient workflows (EEWS) in cloud computing using the MaxUtil model. The proposed approach incorporates the flower pollination algorithm (FPA), a popular meta-heuristic algorithm inspired by nature. The primary objectives of the proposed scheduling scheme are to minimize energy consumption and workflow processing time (makespan). The proposed algorithm involves two key phases: (i) assigning tasks to available virtual machines (VMs) and (ii) scheduling the tasks based on optimal criteria. As per our knowledge, this is the first study that focuses on optimizing energy consumption and makespan in cloud computing workflow scheduling using FPA. The proposed approch employs an effective representation of pollen and dynamic fitness function with multi-objective. The advantage of FPA lies in its speed of convergence and providing feasible solutions. Extensive studies have been conducted across five different scientific workflows from various fields. The proposed algorithm outperforms traditional workflow scheduling algorithms based on particle swarm optimization (PSO), gravitational search algorithms (GSA) and genetic algorithm (GA). The proposed algorithm outperforms GA, PSO, and GSA in the majority of cases, according to simulation findings. In addition, a well-known statistical test known as variance analysis (ANOVA) is used to validate the experimental results of the suggested algorithm. Based on the result’s of ANOVA test, the article claims that the suggested algorithm is superior to existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Energy Optimized Workflow Scheduling in IaaS Cloud: A Flower Pollination based Approach

Jaiprakash,

Arya,

Gupta

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The metrics list can be used to help researchers in their future study and is used in the assessment of newly developed algorithms in the field of cloud computing evaluation. (Tran & Kim, 2021) developed what they called an intelligent and efficient QoS-driven Deep Reinforcement Learning-based (QoS-DRL) cloud task scheduling strategy. The developed strategy focuses on QoS guarantee requirement of a cloud computing environment.…”

Section: Quality Of Service (Qos) Based Algorithmsmentioning

confidence: 99%

Classification and Performance Study of Task Scheduling Algorithms in Cloud Computing Environment

2022

IKM

View full text Add to dashboard Cite

Cloud computing is becoming very common in recent years and is growing rapidly due to its attractive benefits and features such as resource pooling, accessibility, availability, scalability, reliability, cost saving, security, flexibility, on-demand services, pay-per-use services, use from anywhere, quality of service, resilience, etc. With this rapid growth of cloud computing, there may exist too many users that require services or need to execute their tasks simultaneously by resources provided by service providers. To get these services with the best performance, and minimum cost, response time, makespan, effective use of resources, etc. an intelligent and efficient task scheduling technique is required and considered as one of the main and essential issues in the cloud computing environment. It is necessary for allocating tasks to the proper cloud resources and optimizing the overall system performance. To this end, researchers put huge efforts to develop several classes of scheduling algorithms to be suitable for the various computing environments and to satisfy the needs of the various types of individuals and organizations. This research article provides a classification of proposed scheduling strategies and developed algorithms in cloud computing environment along with the evaluation of their performance. A comparison of the performance of these algorithms with existing ones is also given. Additionally, the future research work in the reviewed articles (if available) is also pointed out. This research work includes a review of 88 task scheduling algorithms in cloud computing environment distributed over the seven scheduling classes suggested in this study. Each article deals with a novel scheduling technique and the performance improvement it introduces compared with previously existing task scheduling algorithms.

show abstract

Improved Double Deep Q Network-Based Task Scheduling Algorithm in Edge Computing for Makespan Optimization

Zeng,

Liu,

Shen

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Edge computing nodes undertake an increasing number of tasks with the rise of business density.Therefore, how to efficiently allocate large-scale and dynamic workloads to edge computing resources has become a critical challenge. This study proposes an edge task scheduling approach based on an improved Double Deep Q Network (DQN), which is adopted to separate the calculations of target Q values and the selection of the action in two networks. A new reward function is designed, and a control unit is added to the experience replay unit of the agent. The management of experience data are also modified to fully utilize its value and improve learning efficiency. Reinforcement learning agents usually learn from an ignorant state, which is inefficient. As such, this study proposes a novel particle swarm optimization algorithm with an improved fitness function, which can generate optimal solutions for task scheduling. These optimized solutions are provided for the agent to pre-train network parameters to obtain a better cognition level. The proposed algorithm is compared with six other methods in simulation experiments. Results show that the proposed algorithm outperforms other benchmark methods regarding makespan.

show abstract

A Cloud QoS-driven Scheduler based on Deep Reinforcement Learning

Cited by 4 publications

References 4 publications

Energy Optimized Workflow Scheduling in IaaS Cloud: A Flower Pollination based Approach

Energy Optimized Workflow Scheduling in IaaS Cloud: A Flower Pollination based Approach

Classification and Performance Study of Task Scheduling Algorithms in Cloud Computing Environment

Improved Double Deep Q Network-Based Task Scheduling Algorithm in Edge Computing for Makespan Optimization

Contact Info

Product

Resources

About