Ajou University repository

An Effective Deep Q-Learning Architecture for Class Mapping in Multi-domain Software-Defined Internet of Things
Citations

SCOPUS

0

Citation Export

Publication Year
2025-01-01
Journal
Lecture Notes in Networks and Systems
Publisher
Springer Science and Business Media Deutschland GmbH
Citation
Lecture Notes in Networks and Systems, Vol.977 LNNS, pp.765-774
Keyword
Class mappingDeep Q-learningInternet of ThingsQoSSoftware-defined networking
Mesh Keyword
Class mappingDeep Q-learningLearning architecturesMulti-domainsPacket delivery ratioQ-learningQuality-of-serviceService classService requestsSoftware-defined networkings
All Science Classification Codes (ASJC)
Control and Systems EngineeringSignal ProcessingComputer Networks and Communications
Abstract
There are specific communication requirements for each Internet of Things (IoT) application, such as jitter, packet delivery ratio (PLR), and latency. In heterogeneous networks, an end-to-end (E2E) route may pass across several domains with various quality-of-service (QoS) traffic classes in each domain, making it difficult to meet these unique E2E QoS criteria when they are present on the E2E path of IoT networks. This paper provides a hierarchical software-defined networking (SDN) architecture employing deep Q-learning and a multi-criteria decision-making (MCDM) scheme to determine the appropriate QoS class for the E2E route in the SD-IoT heterogeneous network and performs its mapping for the E2E service requests. The architecture is composed of two layers. In the global controller, we map the appropriate service classes for supplying E2E QoS in accordance with application service requests. Our proposed framework is demonstrated with different real Internet topologies.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/37195
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85208185341&origin=inward
DOI
https://doi.org/10.1007/978-981-97-2671-4_57
Journal URL
https://www.springer.com/series/15179
Type
Conference
Funding
This work was supported by the BK21 FOUR program of the National Research Foundation of Korea funded by the Ministry of Education (NRF5199991514504). Conflict of interest The authors declare that they have no conflict of interest.
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

ALI JEHAD Image
ALI JEHADJEHAD, ALI
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.