Standard

Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. / Allahverdyan, Alexander ; Zhadan, Anastasiia ; Kondratov, Ivan ; Mikheev, Vikenty ; Petrosian, Ovanes ; Romanovskii, Aleksei ; Kharin, Vitaliy .

в: Lecture Notes in Computer Science, № 13969, 08.07.2023, стр. 335–349.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

Harvard

Allahverdyan, A, Zhadan, A, Kondratov, I, Mikheev, V, Petrosian, O, Romanovskii, A & Kharin, V 2023, 'Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling', Lecture Notes in Computer Science, № 13969, стр. 335–349. https://doi.org/10.1007/978-3-031-36625-3_27

APA

Allahverdyan, A., Zhadan, A., Kondratov, I., Mikheev, V., Petrosian, O., Romanovskii, A., & Kharin, V. (2023). Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. Lecture Notes in Computer Science, (13969), 335–349. https://doi.org/10.1007/978-3-031-36625-3_27

Vancouver

Allahverdyan A, Zhadan A, Kondratov I, Mikheev V, Petrosian O, Romanovskii A и пр. Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. Lecture Notes in Computer Science. 2023 Июль 8;(13969):335–349. https://doi.org/10.1007/978-3-031-36625-3_27

Author

Allahverdyan, Alexander ; Zhadan, Anastasiia ; Kondratov, Ivan ; Mikheev, Vikenty ; Petrosian, Ovanes ; Romanovskii, Aleksei ; Kharin, Vitaliy . / Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. в: Lecture Notes in Computer Science. 2023 ; № 13969. стр. 335–349.

BibTeX

@article{dc065871f057470d8802551d82a7ad6b,
title = "Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling",
abstract = "Scheduling is important for improving performance in a distributed heterogeneous computing environment where workflows represented as a directed acyclic graph (DAG). The DAG task scheduling problem has been extensively studied, and many modern heuristic algorithms such as DONF and others have been proposed. Goal of this study is to propose an Artificial Neural Network (ANN) based scheduling scheme with Monte Carlo Tree Search (MCTS). Numerical representation of each DAG node are used as inputs to the ANN, and the outputs are the execution priority of the node. The MCTS method utilized to determine the actual scheduling policies; The proposed algorithm shows an improvement of up to 42% on certain graph topologies with average performance gain of 7.05% over the best scheduling algorithm. Algorithm managed to cover 40.01% of the proximity interval from the best scheduling algorithm to the global optimal solution obtained via the Mixed-Integer Linear Programming approach.",
keywords = "Monte Carlo Tree Search, Neural networks, Scheduling, Directed Acyclic Graph, Monte Carlo Tree Search, Neural networks, Scheduling, Directed Acyclic Graph",
author = "Alexander Allahverdyan and Anastasiia Zhadan and Ivan Kondratov and Vikenty Mikheev and Ovanes Petrosian and Aleksei Romanovskii and Vitaliy Kharin",
note = "Allahverdyan, A. et al. (2023). Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. In: Tan, Y., Shi, Y., Luo, W. (eds) Advances in Swarm Intelligence. ICSI 2023. Lecture Notes in Computer Science, vol 13969. Springer, Cham. https://doi.org/10.1007/978-3-031-36625-3_27",
year = "2023",
month = jul,
day = "8",
doi = "10.1007/978-3-031-36625-3_27",
language = "English",
pages = "335–349",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Nature",
number = "13969",

}

RIS

TY - JOUR

T1 - Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling

AU - Allahverdyan, Alexander

AU - Zhadan, Anastasiia

AU - Kondratov, Ivan

AU - Mikheev, Vikenty

AU - Petrosian, Ovanes

AU - Romanovskii, Aleksei

AU - Kharin, Vitaliy

N1 - Allahverdyan, A. et al. (2023). Monte Carlo Tree Search with Adaptive Estimation for DAG Scheduling. In: Tan, Y., Shi, Y., Luo, W. (eds) Advances in Swarm Intelligence. ICSI 2023. Lecture Notes in Computer Science, vol 13969. Springer, Cham. https://doi.org/10.1007/978-3-031-36625-3_27

PY - 2023/7/8

Y1 - 2023/7/8

N2 - Scheduling is important for improving performance in a distributed heterogeneous computing environment where workflows represented as a directed acyclic graph (DAG). The DAG task scheduling problem has been extensively studied, and many modern heuristic algorithms such as DONF and others have been proposed. Goal of this study is to propose an Artificial Neural Network (ANN) based scheduling scheme with Monte Carlo Tree Search (MCTS). Numerical representation of each DAG node are used as inputs to the ANN, and the outputs are the execution priority of the node. The MCTS method utilized to determine the actual scheduling policies; The proposed algorithm shows an improvement of up to 42% on certain graph topologies with average performance gain of 7.05% over the best scheduling algorithm. Algorithm managed to cover 40.01% of the proximity interval from the best scheduling algorithm to the global optimal solution obtained via the Mixed-Integer Linear Programming approach.

AB - Scheduling is important for improving performance in a distributed heterogeneous computing environment where workflows represented as a directed acyclic graph (DAG). The DAG task scheduling problem has been extensively studied, and many modern heuristic algorithms such as DONF and others have been proposed. Goal of this study is to propose an Artificial Neural Network (ANN) based scheduling scheme with Monte Carlo Tree Search (MCTS). Numerical representation of each DAG node are used as inputs to the ANN, and the outputs are the execution priority of the node. The MCTS method utilized to determine the actual scheduling policies; The proposed algorithm shows an improvement of up to 42% on certain graph topologies with average performance gain of 7.05% over the best scheduling algorithm. Algorithm managed to cover 40.01% of the proximity interval from the best scheduling algorithm to the global optimal solution obtained via the Mixed-Integer Linear Programming approach.

KW - Monte Carlo Tree Search

KW - Neural networks

KW - Scheduling

KW - Directed Acyclic Graph

KW - Monte Carlo Tree Search

KW - Neural networks

KW - Scheduling

KW - Directed Acyclic Graph

UR - https://www.mendeley.com/catalogue/5cf75292-a4f0-37c7-884b-caedefeaec73/

U2 - 10.1007/978-3-031-36625-3_27

DO - 10.1007/978-3-031-36625-3_27

M3 - Article

SP - 335

EP - 349

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - 13969

ER -

ID: 114434622