arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.03022cs.NIcs.LGcs.MA

分布式控制器软件定义网络中用于请求调度的多智能体深度强化学习

Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking

University of Waikato（怀卡托大学）；Victoria University of Wellington（惠灵顿维多利亚大学）

Victoria Huang, Gang Chen, Qiang Fu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于多智能体深度强化学习的MA-PPO算法，通过多智能体马尔可夫决策过程建模，自动设计分布式控制器SDN中的请求调度策略，显著优于人工和单智能体策略。

摘要：

近期，分布式控制器架构在软件定义网络（SDN）中迅速普及。然而，使用分布式控制器引入了一个新的重要请求调度（RD）问题，其目标是让每个SDN交换机在所有控制器之间正确调度请求，以优化网络性能。此目标可以通过设计RD策略来指导每个交换机上的请求分配来实现。在本文中，我们提出了一种多智能体深度强化学习（MA-DRL）方法，以自动设计具有高适应性和高性能的RD策略。这是通过以多智能体马尔可夫决策过程（MA-MDP）形式进行的新问题建模、一种新的自适应RD策略设计以及一种名为MA-PPO的新MA-DRL算法来实现的。广泛的仿真研究表明，我们的MA-DRL技术能有效训练RD策略，使其显著优于人工策略、基于模型的策略，以及通过单智能体DRL算法学习到的RD策略。

英文摘要：

Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN). However, the use of distributed controllers introduces a new and important Request Dispatching (RD) problem with the goal for every SDN switch to properly dispatch their requests among all controllers so as to optimize network performance. This goal can be fulfilled by designing an RD policy to guide distribution of requests at each switch. In this paper, we propose a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach to automatically design RD policies with high adaptability and performance. This is achieved through a new problem formulation in the form of a Multi-Agent Markov Decision Process (MA-MDP), a new adaptive RD policy design and a new MA-DRL algorithm called MA-PPO. Extensive simulation studies show that our MA-DRL technique can effectively train RD policies to significantly outperform man-made policies, model-based policies, as well as RD policies learned via single-agent DRL algorithms.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑