RT info:eu-repo/semantics/article
T1 Deep Reinforcement Learning for the Management of Software-Defined Networks and Network Function Virtualization in an Edge-IoT Architecture
A1 Alonso Rincón, Ricardo S.
A1 Sittón-Candanedo, Inés
A1 Casado Vara, Roberto Carlos
A1 Prieto, Javier
A1 Corchado, Juan M.
K1 Industrial internet of things
K1 Edge computing
K1 Software defined networks
K1 Network function virtualization
K1 Deep reinforcement learning
K1 Informática
K1 Computer science
AB The Internet of Things (IoT) paradigm allows the interconnection of millions of sensordevices gathering information and forwarding to the Cloud, where data is stored and processedto infer knowledge and perform analysis and predictions. Cloud service providers charge usersbased on the computing and storage resources used in the Cloud. In this regard, Edge Computingcan be used to reduce these costs. In Edge Computing scenarios, data is pre-processed and filteredin network edge before being sent to the Cloud, resulting in shorter response times and providinga certain service level even if the link between IoT devices and Cloud is interrupted. Moreover,there is a growing trend to share physical network resources and costs through Network FunctionVirtualization (NFV) architectures. In this sense, and related to NFV, Software-Defined Networks(SDNs) are used to reconfigure the network dynamically according to the necessities during time.For this purpose, Machine Learning mechanisms, such as Deep Reinforcement Learning techniques,can be employed to manage virtual data flows in networks. In this work, we propose the evolution ofan existing Edge-IoT architecture to a new improved version in which SDN/NFV are used over theEdge-IoT capabilities. The proposed new architecture contemplates the use of Deep ReinforcementLearning techniques for the implementation of the SDN controller.
PB MDPI
YR 2020
FD 2020-07
LK http://hdl.handle.net/10259/7245
UL http://hdl.handle.net/10259/7245
LA eng
NO This work has been partially supported by the European Regional Development Fund (ERDF) through the Interreg Spain-Portugal V-A Program (POCTEP) under grant 0677_DISRUPTIVE_2_E (Intensifying the activity of Digital Innovation Hubs within the PocTep region to boost the development of disruptive and last generation ICTs through cross-border cooperation). Inés Sittón-Candanedo has been supported by scholarship program: IFARHU-SENACYT (Government of Panama).
DS Repositorio Institucional de la Universidad de Burgos
RD 23-nov-2024