Dynamic Resource Aware VNF Placement with Deep Reinforcement Learning for 5G Networks
Gespeichert in:
| Titel: | Dynamic Resource Aware VNF Placement with Deep Reinforcement Learning for 5G Networks |
|---|---|
| Autoren: | Dalgkitsis, Anestis, Mekikis, Prodromos-Vasileios, Antonopoulos, Angelos, Kormentzas, Georgios, Verikoukis, Christos |
| Quelle: | GLOBECOM 2020-2020 IEEE Global Communications Conference |
| Verlagsinformationen: | IEEE, 2020. |
| Publikationsjahr: | 2020 |
| Schlagwörter: | Virtual Network Functions, Software Defined Networking, Deep Reinforcement Learnin, 0202 electrical engineering, electronic engineering, information engineering, Live Migration, 02 engineering and technology |
| Beschreibung: | The increasing demand for fast, reliable, and robust network services has driven the telecommunications industry to design novel network architectures that employ Network Functions Virtualization and Software Defined Networking. Despite the advancements in cellular networks, there is a need for an automatic, self-adapting orchestrating mechanism that can manage the placement of resources. Deep Reinforcement Learning can perform such tasks dynamically, without any prior knowledge. In this work, we leverage a Deep Deterministic Policy Gradient Reinforcement Learning algorithm, to fully automate the Virtual Network Functions deployment process between edge and cloud network nodes. We evaluate the performance of our implementation and compare it with alternative solutions to prove its superiority while demonstrating results that pave the way for Experiential Network Intelligence and fully automated, Zero touch network Service Management. Grant numbers : SPOT5G - Single Point of attachment communications heterogeneous mobile data networks (TEC2017-87456-P) and MonB5G - Distributed management of Network Slices in beyond 5G (code: 871780) projects.© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| Publikationsart: | Article Conference object |
| DOI: | 10.1109/globecom42002.2020.9322512 |
| DOI: | 10.5281/zenodo.4459640 |
| DOI: | 10.5281/zenodo.4459639 |
| Zugangs-URL: | https://zenodo.org/record/4459640/files/Dynamic%20Resource%20Aware%20VNF.pdf https://dblp.uni-trier.de/db/conf/globecom/globecom2020.html#DalgkitsisM0KV20 |
| Rights: | IEEE Copyright CC BY |
| Dokumentencode: | edsair.doi.dedup.....4ec98c44c48fea4962e0bf3141bd10b8 |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | The increasing demand for fast, reliable, and robust network services has driven the telecommunications industry to design novel network architectures that employ Network Functions Virtualization and Software Defined Networking. Despite the advancements in cellular networks, there is a need for an automatic, self-adapting orchestrating mechanism that can manage the placement of resources. Deep Reinforcement Learning can perform such tasks dynamically, without any prior knowledge. In this work, we leverage a Deep Deterministic Policy Gradient Reinforcement Learning algorithm, to fully automate the Virtual Network Functions deployment process between edge and cloud network nodes. We evaluate the performance of our implementation and compare it with alternative solutions to prove its superiority while demonstrating results that pave the way for Experiential Network Intelligence and fully automated, Zero touch network Service Management.<br />Grant numbers : SPOT5G - Single Point of attachment communications heterogeneous mobile data networks (TEC2017-87456-P) and MonB5G - Distributed management of Network Slices in beyond 5G (code: 871780) projects.© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
|---|---|
| DOI: | 10.1109/globecom42002.2020.9322512 |