Topology Design for Data Center Networks Using Deep Reinforcement Learning

Haoran Qi, Zhan Shu, Xiaomin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Downloads (Pure)

Abstract

This paper is concerned with the topology design of data center networks (DCNs) for low latency and fewer links using deep reinforcement learning (DRL). Starting from a Kvertex-connected graph, we propose an interactive framework with single-objective and multi-objective DRL agents to learn DCN topologies for given node traffic matrices by choosing link matrices to represent the states and actions as well as using the average shortest path length together with action penalty terms as reward feedback. Comparisons with commonly used DCN topologies are given to show the effectiveness and merits of our method. The results reveal that our learned topologies could achieve lower delay compared with common DCN topologies. Moreover, we believe that the method can be extended to other topology metrics, e.g., throughput, by simply modifying the reward functions.
Original languageEnglish
Title of host publicationThe 37th International Conference on Information Networking (ICOIN)
Place of PublicationPiscataway, US
PublisherIEEE
Number of pages6
Publication statusAccepted/In press - 15 Nov 2022
EventICOIN 2023: The 37th International Conference on Information Networking (ICOIN) - Bangkok, Thailand
Duration: 11 Jan 202314 Jan 2023
http://icoin.org/main.php

Conference

ConferenceICOIN 2023
Country/TerritoryThailand
CityBangkok
Period11/01/2314/01/23
Internet address

Fingerprint

Dive into the research topics of 'Topology Design for Data Center Networks Using Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this