DRL-Scheduling: An Intelligent QoS-Aware Job Scheduling Framework for Applications in Clouds

Wei, Yi; Pan, Li; Liu, Shijun; Wu, Lei; Meng, Xiangxu

doi:10.1109/access.2018.2872674

Cited by 75 publications

(30 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…AlphaGo’s success in particular attracted great attention to the DQN [ 42 ]. The DQN was mainly adopted in applications that play Atari games in previous studies [ 43 ], and in recent studies, it has been used as a way to solve the JSP [ 8 ]. The JSP is NP-hard and is a very difficult computational problem.…”

Section: Related Workmentioning

confidence: 99%

“…In particular, reinforcement learning has positive results in efficiently finding high-quality solutions to scheduling problems [ 5 ]. With the recent development of neural networks and reinforcement learning (RL) technology, various complex problems have been successfully solved by the deep-Q network (DQN), which combines deep learning (DL) and RL [ 6 , 7 ] and has been successfully used in the manufacturing industry [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach to the Job Shop Scheduling Problem Based on the Deep Q-Network in a Cooperative Multi-Access Edge Computing Ecosystem

Moon

Yang

Jeong

2021

Sensors

View full text Add to dashboard Cite

In this study, based on multi-access edge computing (MEC), we provided the possibility of cooperating manufacturing processes. We tried to solve the job shop scheduling problem by applying DQN (deep Q-network), a reinforcement learning model, to this method. Here, to alleviate the overload of computing resources, an efficient DQN was used for the experiments using transfer learning data. Additionally, we conducted scheduling studies in the edge computing ecosystem of our manufacturing processes without the help of cloud centers. Cloud computing, an environment in which scheduling processing is performed, has issues sensitive to the manufacturing process in general, such as security issues and communication delay time, and research is being conducted in various fields, such as the introduction of an edge computing system that can replace them. We proposed a method of independently performing scheduling at the edge of the network through cooperative scheduling between edge devices within a multi-access edge computing structure. The proposed framework was evaluated, analyzed, and compared with existing frameworks in terms of providing solutions and services.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Approach to the Job Shop Scheduling Problem Based on the Deep Q-Network in a Cooperative Multi-Access Edge Computing Ecosystem

Moon

Yang

Jeong

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Una vez revisadas las propuestas de solución al JSSP, a continuación, se analizan en detalle los tres tipos de algoritmos más interesantes para nuestra investigación: aprendizaje profundo, aprendizaje por refuerzo y aprendizaje reforzado profundo. (Wei et al, 2018). Q hace referencia a la función utilizada la cual se actualiza según el valor máximo esperado del siguiente estado y un valor de recompensa.…”

Section: Propuestas De La Literatura Para La Solución Del Jsspunclassified

“…Una vez que se ha realizado la acción, el entorno pasará a un nuevo estado. Al mismo tiempo, el agente recibirá una recompensa que refleja el valor de la transición de estado(Wei et al, 2018). Una variante de RL es el aprendizaje reforzado profundo (Deep Reinforced Learning -DRL).…”

unclassified

Aplicación de algoritmos de aprendizaje automático a la programación de órdenes de producción en talleres de trabajo: una revisión de la literatura reciente

Pérez-Cubero

Mula

2020

DyO

View full text Add to dashboard Cite

El propósito de este artículo es identificar y analizar los algoritmos de aprendizaje automático propuestos recientemente, para dar solución al problema de programación y secuenciación de órdenes de producción en talleres de trabajo, a través de una revisión sistemática de las últimas publicaciones realizadas en este campo. Este estudio pretende proporcionar a los investigadores un punto de partida para la selección de los algoritmos de aprendizaje automático más prometedores para la solución de este tipo de problema, identificar las áreas de investigación más interesantes en la actualidad y proponer líneas de investigación futuras.

show abstract

“…The computation resource allocation problem in edge computing is formulated as an MDP, and multiple replay memories were utilized for the deep Q-network (DQN) algorithm to minimize the total delay and resource utilization [ 31 ]. In [ 32 ], a DQN-based task scheduling was studied in cloud computing to maximize the number of successful tasks by considering the delay requirement. The authors in [ 33 ] investigated joint task offloading and resource allocation for computationally-intensive tasks in fog computing.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning-Based Task Scheduling in IoT Edge Computing

Sheng

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

Edge computing (EC) has recently emerged as a promising paradigm that supports resource-hungry Internet of Things (IoT) applications with low latency services at the network edge. However, the limited capacity of computing resources at the edge server poses great challenges for scheduling application tasks. In this paper, a task scheduling problem is studied in the EC scenario, and multiple tasks are scheduled to virtual machines (VMs) configured at the edge server by maximizing the long-term task satisfaction degree (LTSD). The problem is formulated as a Markov decision process (MDP) for which the state, action, state transition, and reward are designed. We leverage deep reinforcement learning (DRL) to solve both time scheduling (i.e., the task execution order) and resource allocation (i.e., which VM the task is assigned to), considering the diversity of the tasks and the heterogeneity of available resources. A policy-based REINFORCE algorithm is proposed for the task scheduling problem, and a fully-connected neural network (FCN) is utilized to extract the features. Simulation results show that the proposed DRL-based task scheduling algorithm outperforms the existing methods in the literature in terms of the average task satisfaction degree and success ratio.

show abstract

DRL-Scheduling: An Intelligent QoS-Aware Job Scheduling Framework for Applications in Clouds

Cited by 75 publications

References 32 publications

A Novel Approach to the Job Shop Scheduling Problem Based on the Deep Q-Network in a Cooperative Multi-Access Edge Computing Ecosystem

A Novel Approach to the Job Shop Scheduling Problem Based on the Deep Q-Network in a Cooperative Multi-Access Edge Computing Ecosystem

Aplicación de algoritmos de aprendizaje automático a la programación de órdenes de producción en talleres de trabajo: una revisión de la literatura reciente

Deep Reinforcement Learning-Based Task Scheduling in IoT Edge Computing

Contact Info

Product

Resources

About