SLAs-Aware Online Task Scheduling Based on Deep Reinforcement Learning Method in Cloud Environment

Ran, Longyu; Shi, Xiaoyu; Shang, Mingsheng

doi:10.1109/hpcc/smartcity/dss.2019.00209

Cited by 26 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A stochastic policy gradient-based reinforcement learning technique was also used to detect performance concerns in cloud storage and take the required actions, such as load balancing and data movement, to improve storage performance. Authors in [9] used design Deep Deterministic Policy Gradient (DDPG) task scheduling approach which depends on deep reinforcement learning (DRL) method to diminish the reaction time and keep up the load balancing. Without any prior knowledge, the proposed algorithm may learn straight from its experience and make the proper scheduling decision for VMs for ongoing online task requests.…”

Section: Related Workmentioning

confidence: 99%

Action-Based Load Balancing Technique in Cloud Network Using Actor-Critic-Swarm Optimization

Pradhan

Bisoy

Sain

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Increasing scale of task in cloud network leads to problem in load balancing and its improvement in parameters. In this paper, we proposed a hybrid scheduling policy which is hybrid of both Particle Swarm Optimization (PSO) algorithm and actor-critic algorithm named as Hybrid Particle Swarm Optimization Actor Critic (HPSOAC) to solve this issue. This hybrid scheduling policy helps to each agent to improve an individual learning as well as learning through exchanging information among other agents. An experiment is carried out by the help of Python simulator with TensorFlow. Outcome shows that our proposed scheduling policy reduces 5.16% and 10.86% in energy consumption, reduces 7.13% and 10.04% in makespan time, and has marginally better resource utilization over Deep Q-network (DQN) and Q-learning based on Modified Particle Swarm Optimization (QMPSO) algorithm, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Action-Based Load Balancing Technique in Cloud Network Using Actor-Critic-Swarm Optimization

Pradhan

Bisoy

Sain

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Marahatta et al [34] developed energy-aware fault-tolerant dynamic application task scheduling (EFDTS) schema at the underlying VMs. The works [35], [36] proposed online application task and job scheduling mechanism based on deep reinforcement learning (DRL) to assign submitted tasks at different VMs from different QoS perspectives. Jiang et al [37] explored the characteristics of collocated jobs in Alibaba cluster [9].…”

Section: Task Schedulingmentioning

confidence: 99%

Proactive Failure-Aware Task Scheduling Framework for Cloud Computing

2021

View full text Add to dashboard Cite

Cloud computing is a widely adopted platform for executing tasks of different application types that belong to the end users. In the cloud, application task is prone to failure for several reasons, such as software bug or exception, virtual or physical infrastructure failure. Cloud service providers are responsible for managing availability of scheduled computing tasks in order to provide high level QoS for their customers. Protecting task against failure is a challenging and not a trivial mission due to dynamic, heterogeneous and large distributed structure of the cloud environment. The existing works in the literature focus on task failure prediction and neglect the remedy (post) actions. In this work, we first study and analyze three publicly available large cluster datasets from Google, Alibaba, and Trinity, to characterize task failure in cloud computing platform. We then propose a failure-aware task scheduling framework that can predict the termination status for a set of given tasks during the runtime, and take the appropriate remedy actions. The framework uses deep learning methods named Artificial and Convolutional Neural Network, ANN and CNN, for different prediction purposes. In addition, we formalize the actions selection problem as Integer Linear Programming (ILP) model and propose a heuristic optimization solution that aims to minimize the failure probability of tasks and their resources usage. The results show ANN and CNN can achieve prediction accuracy of up to 94% and 92%, respectively using Google dataset. Moreover, the framework can protect up to 40% of tasks that are predicted as failed using Alibaba dataset by taking the appropriate remedy actions, and hence save many of cluster's resources such as CPU and RAM.INDEX TERMS Task failure prediction, deep learning, task scheduling, cloud computing.

show abstract

“…In [32], the authors presented a framework for online task scheduling consisting of three components, namely task queue, country monitoring, and task scheduling. The main purpose of task scheduling was to perform substantial and dynamic tasks to reduce resources, according to the SLA requirements.…”

Section: Related Workmentioning

confidence: 99%

“…2 Time [10], [21], [25], [26], [29], [32], [35], [37], [39], [40], [41], [45], [47], [48], [50], [51], [52] 15%…”

Section: Related Workmentioning

confidence: 99%

A Survey on Improving QoS in Service Level Agreement for Cloud Computing Environment

Edinat

Al-Sayyed

Hudaib

2021

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

Cloud computing is considered one of the most important techniques in the field of distributed computing which contributes to maintain increased scalability and flexibility in computer processing. This is achieved because it, using the Internet, provides different resources and shared services with minimum costs. Cloud service providers (CSPs) offer many different services to their customers, where the customers’ needs are met seeking the highest levels of quality at the lowest considerate prices. The relationship between CSPs and customers must be determined in a formal agreement, and to ensure how the QoS between them will be fulfilled, a clear Service Level Agreement (SLA) must be called for. Several previously-proposed models used in the literature to improve the QoS in the SLA for cloud computing and to face many of the challenges in the SLA are reviewed in this paper. We also addressed the challenges that are related to the violations of SLAs, and how overcoming them will enhance customers’ satisfaction. Furthermore, we proposed a model based on Deep Reinforcement Learning (DRL) and an enhanced DRL agent (EDRLA). In this model, and by optimizing the learning process in EDRLA, proposed agents would be able to have optimal CSPs by improving the learning process in EDRLA. This improvement will be reflected in the agent's performance and considerably affect it, especially in identifying cloud computing requirements based on the QoS metrics.

show abstract

SLAs-Aware Online Task Scheduling Based on Deep Reinforcement Learning Method in Cloud Environment

Cited by 26 publications

References 19 publications

Action-Based Load Balancing Technique in Cloud Network Using Actor-Critic-Swarm Optimization

Action-Based Load Balancing Technique in Cloud Network Using Actor-Critic-Swarm Optimization

Proactive Failure-Aware Task Scheduling Framework for Cloud Computing

A Survey on Improving QoS in Service Level Agreement for Cloud Computing Environment

Contact Info

Product

Resources

About