Mostra el registre d'ítem simple
Continuous multi-objective zero-touch network slicing via twin delayed DDPG and OpenAI gym
dc.contributor.author | Rezazadeh, Farhad |
dc.contributor.author | Chergui, Hatim |
dc.contributor.author | Alonso Zárate, Luis Gonzaga |
dc.contributor.author | Verikoukis, Christos |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2021-02-09T13:42:28Z |
dc.date.issued | 2020 |
dc.identifier.citation | Rezazadeh, F. [et al.]. Continuous multi-objective zero-touch network slicing via twin delayed DDPG and OpenAI gym. A: IEEE Global Communications Conference. "Proceedings of IEEE Globecom 2020". Institute of Electrical and Electronics Engineers (IEEE), 2020, p. 1-6. DOI 10.1109/GLOBECOM42002.2020.9322237. |
dc.identifier.other | https://zenodo.org/record/4459653#.YAylATmSmUk |
dc.identifier.uri | http://hdl.handle.net/2117/338159 |
dc.description.abstract | Artificial intelligence (AI)-driven zero-touch network slicing (NS) is a new paradigm enabling the automation of resource management and orchestration (MANO) in multi-tenant beyond 5G (B5G) networks. In this paper, we tackle the problem of cloud-RAN (C-RAN) joint slice admission control and resource allocation by first formulating it as a Markov decision process (MDP). We then invoke an advanced continuous deep reinforcement learning (DRL) method called twin delayed deep deterministic policy gradient (TD3) to solve it. In this intent, we introduce a multi-objective approach to make the central unit (CU) learn how to re-configure computing resources autonomously while minimizing latency, energy consumption and virtual network function (VNF) instantiation cost for each slice. Moreover, we build a complete 5G C-RAN network slicing environment using OpenAI Gym toolkit where, thanks to its standardized interface, it can be easily tested with different DRL schemes. Finally, we present extensive experimental results to showcase the gain of TD3 as well as the adopted multi-objective strategy in terms of achieved slice admission success rate, latency, energy saving and CPU utilization. |
dc.format.extent | 6 p. |
dc.language.iso | eng |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació |
dc.subject.lcsh | Information technology |
dc.subject.lcsh | Data mining |
dc.subject.other | Resource management |
dc.subject.other | Wireless communication |
dc.subject.other | Dynamic scheduling |
dc.subject.other | Network slicing |
dc.subject.other | 5G mobile communication |
dc.subject.other | Delays |
dc.subject.other | Computer architecture |
dc.title | Continuous multi-objective zero-touch network slicing via twin delayed DDPG and OpenAI gym |
dc.type | Conference lecture |
dc.subject.lemac | Mineria de dades |
dc.subject.lemac | Tecnologia de la informació |
dc.contributor.group | Universitat Politècnica de Catalunya. WiComTec - Grup de recerca en Tecnologies i Comunicacions Sense Fils |
dc.identifier.doi | 10.1109/GLOBECOM42002.2020.9322237 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/9322237 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 30413800 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/H2020/856691/EU/5G Solutions for European Citizens/5G-SOLUTIONS |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/H2020/871780/EU/Distributed management of Network Slices in beyond 5G/MonB5G |
dc.relation.projectid | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TEC2017-87456-P/ES/UNICO PUNTO DE ASOCIACION EN REDES DE COMUNICACIONES MOVILES HETEROGENEAS DE 5ª GENERACION/ |
dc.date.lift | 10000-01-01 |
local.citation.author | Rezazadeh, F.; Chergui, H.; Alonso, L.; Verikoukis, C. |
local.citation.contributor | IEEE Global Communications Conference |
local.citation.publicationName | Proceedings of IEEE Globecom 2020 |
local.citation.startingPage | 1 |
local.citation.endingPage | 6 |