Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ UPCommons. Portal de...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2014
License: CC BY NC ND
versions View all 4 versions
addClaim

Aprendizaje por refuerzo multi-nivel para sistemas RRM

Multi-layered reinforcement learning for RRM
Authors: Collados Zamora, Kevin;

Aprendizaje por refuerzo multi-nivel para sistemas RRM

Abstract

[CASTELLÀ] Este trabajo se centra en la problemática de la gestión de recursos en el ámbito de los sistemas RRM (Radio Resource Management) con más de un objetivo a maximizar. En concreto se centra en maximizar simultáneamente la calidad de servicio que se ofrece al usuario y el beneficio adquirido para el operador. Para tal fin se evaluará el rendimiento de los sistemas RRM basados en la utilización de la metodología RL (Reinforcement Learning). Esta evaluación se realizará mediante la modificación y evolución de las características propias del sistema a fin de incrementar su rendimiento. Finalmente se realiza una propuesta de resolución, basándose en un sistema de cooperación entre dos agentes. Ambos agentes utilizan la metodología FRL (Fuzzy Reinforcement Learning). Cada agente se centra en maximizar un objetivo, de forma que la colaboración conjunta entre agentes proporcionará una optimización global del sistema.

[CATALÀ] Aquest treball es centra en la problemàtica de la gestió dels recursos en l'àmbit dels sistemes RRM (Radio Resource Management). Concretament es centra en maximitzar simultàniament la qualitat de servei que s'ofereix al usuari i el benefici que obté l'operador. Per complir aquest objectiu s'avaluarà el rendiment dels sistemes RRM basats en la utilització de la metodologia RL (Reinforcement Learning). Aquesta avaluació es realitzarà mitjançant la modificació y evolució de les característiques pròpies del sistema a fi de incrementar el seu rendiment. Finalment es realitza una proposta de resolució, basant-se en un sistema de cooperació entre dos agents. Ambdós agents utilitzen una metodologia FRL (Fuzzy Reinforcement Learning). Cada agent es centra en maximitzar un objectiu, de forma que la col·laboració conjunta entre agents proporcionarà una optimització global del sistema.

[ANGLÈS] This paper focuses on the problem of resource management in the field of RRM (Radio Resource Management) systems with more than one objective to maximize. Specifically focuses on simultaneously maximize the quality of service offered to the user and the benefit for the operator. To this end the performance of the RRM systems based on the use of RL (Reinforcement Learning) systems is evaluated. This evaluation is done by the modification and evolution of the system characteristics in order to increase its performance. Finally a resolution proposal is implemented, this resolution is based on the cooperation between two agents. Both agents uses FRL (Fuzzy Reinforcement Learning) methodology. Each agent is focused on maximize an objective in a way that the joint collaboration between the agents provides a global system optimization.

Sistemas RRM gestionados mediante algoritmos de aprendizaje por refuerzo.

Country
Spain
Keywords

RRM, :Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors [Àrees temàtiques de la UPC], radio resources management, RL, Comunicacions mòbils, gestión de radio recursos, estructura multi-nivel, Sistemes de, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Comunicacions mòbils, Comunicacions mòbils, Sistemes de, Aprendizaje por refuerzo, Reinforcement learning, :Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Comunicacions mòbils [Àrees temàtiques de la UPC], Mobile communication systems, multi-layered structure

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 22
    download downloads 115
  • 22
    views
    115
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
22
115
Green