
Las memorias TCAM (Ternary contentaddressablememory) de las tablas de flujo delos nodos SDN (Software Defined Networking)son muy r´apidas y permiten realizar b´usquedas enparalelo en muy poco tiempo. Sin embargo, presentanun alto consumo de energ´ıa y un elevado coste, loque hace que su tama˜no sea limitado. Esta limitaci´onde tama˜no impacta sobre el n´umero de reglas que sepueden instalar, por lo que una gesti´on ineficiente delas mismas puede suponer una degradaci´on de la QoS(Quality of Service) de la red. Este trabajo proponeuna soluci´on basada en DRL (Deep ReinforcementLearning) que permite ajustar din´amicamente el idletimeout de las reglas de flujo para maximizar eln´umero de flujos que pueden ser encaminados en lared, lo que deriva en una mejora de la QoS.
JITEL2021, SCITEL, Telecommunications
JITEL2021, SCITEL, Telecommunications
| 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 |
