Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs

Zehua Guo

doi:10.1007/978-981-19-4874-9_3

Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs

Zehua Guo^*

^*此作品的通讯作者

自动化学院

科研成果: 书/报告/会议事项章节 › 章节 › 同行评审

摘要

In this chapter, we introduce a dynamic controller workload balancing scheme named MARVEL using emerging MARL for switch migration. We design a DRL framework for each agent in the MARL model. The DRL-based solution takes the workload pattern in the control plane as input and generates the migration decision as the output. When training is done, the DRL agent can quickly and accurately decide how to migrate switches among the controllers.

源语言	英语
主期刊名	SpringerBriefs in Computer Science
出版商	Springer
页	23-38
页数	16
DOI	https://doi.org/10.1007/978-981-19-4874-9_3
出版状态	已出版 - 2022

出版系列

姓名	SpringerBriefs in Computer Science
ISSN（印刷版）	2191-5768
ISSN（电子版）	2191-5776

访问文件

10.1007/978-981-19-4874-9_3

其它文件与链接

链接到 Scopus 的出版物

引用此

Guo, Z. (2022). Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs. 在 SpringerBriefs in Computer Science (页码 23-38). (SpringerBriefs in Computer Science). Springer. https://doi.org/10.1007/978-981-19-4874-9_3

@inbook{a68ad6793b85431ba811eda1aa0b65c0,

title = "Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs",

abstract = "In this chapter, we introduce a dynamic controller workload balancing scheme named MARVEL using emerging MARL for switch migration. We design a DRL framework for each agent in the MARL model. The DRL-based solution takes the workload pattern in the control plane as input and generates the migration decision as the output. When training is done, the DRL agent can quickly and accurately decide how to migrate switches among the controllers.",

author = "Zehua Guo",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.",

year = "2022",

doi = "10.1007/978-981-19-4874-9_3",

language = "English",

series = "SpringerBriefs in Computer Science",

publisher = "Springer",

pages = "23--38",

booktitle = "SpringerBriefs in Computer Science",

address = "Germany",

}

TY - CHAP

T1 - Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs

AU - Guo, Zehua

PY - 2022

Y1 - 2022

N2 - In this chapter, we introduce a dynamic controller workload balancing scheme named MARVEL using emerging MARL for switch migration. We design a DRL framework for each agent in the MARL model. The DRL-based solution takes the workload pattern in the control plane as input and generates the migration decision as the output. When training is done, the DRL agent can quickly and accurately decide how to migrate switches among the controllers.

AB - In this chapter, we introduce a dynamic controller workload balancing scheme named MARVEL using emerging MARL for switch migration. We design a DRL framework for each agent in the MARL model. The DRL-based solution takes the workload pattern in the control plane as input and generates the migration decision as the output. When training is done, the DRL agent can quickly and accurately decide how to migrate switches among the controllers.

UR - http://www.scopus.com/inward/record.url?scp=85139861097&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-4874-9_3

DO - 10.1007/978-981-19-4874-9_3

M3 - Chapter

AN - SCOPUS:85139861097

T3 - SpringerBriefs in Computer Science

SP - 23

EP - 38

BT - SpringerBriefs in Computer Science

PB - Springer

ER -

Multi-Agent Reinforcement Learning-Based Controller Load Balancing in SD-WANs

摘要

出版系列

访问文件

其它文件与链接

指纹

引用此