A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs

In this paper, we propose a new deep Q-network (DQN) design for quality-of-service (QoS) multicast routing (DQMR) protocol to establish efficient QoS multicast (EQM) trees in cognitive radio mobile ad hoc networks (CR-MANETs). An EQM tree is a shortest-path multicast tree with minimum end-to-end (E2...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Thong-Nhat Tran, Toan-Van Nguyen, Kyusung Shim, Daniel Benevides Da Costa, Beongku An
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/f3477469621944988154e01a655445c7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f3477469621944988154e01a655445c7
record_format dspace
spelling oai:doaj.org-article:f3477469621944988154e01a655445c72021-11-20T00:02:58ZA New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs2169-353610.1109/ACCESS.2021.3126844https://doaj.org/article/f3477469621944988154e01a655445c72021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9610033/https://doaj.org/toc/2169-3536In this paper, we propose a new deep Q-network (DQN) design for quality-of-service (QoS) multicast routing (DQMR) protocol to establish efficient QoS multicast (EQM) trees in cognitive radio mobile ad hoc networks (CR-MANETs). An EQM tree is a shortest-path multicast tree with minimum end-to-end (E2E) cost (a combination of queuing size ratio and link stability) subject to QoS constraints such as queuing size ratio, link stability, number of hops, number of time slots and avoiding the licensed channel of primary users. Particularly, we propose an NP-complete optimization problem such that its feasible solution is an EQM tree. To address this problem, we design a new DQN model and a new game-based model to form EQM trees in real-time by offline training instead of online training as done in previous papers. Moreover, the DQMR protocol is also guaranteed to have high stability, low routing delay, low control overhead, and high packet delivery ratio (PDR). Furthermore, one more new contribution of the paper is that exact closed-form expressions for the E2E queuing delay of a multicast routing tree are also derived assuming random waypoint mobility and the reference point group mobility models to compare with simulation results of routing delay. Simulation results show that the DQMR protocol outperforms multicast ad hoc on-demand distance vector routing protocol in terms of routing delay, control overhead, and PDR.Thong-Nhat TranToan-Van NguyenKyusung ShimDaniel Benevides Da CostaBeongku AnIEEEarticleCognitive mobile ad hoc networkscross-layerdeep Q-networkgame theoryQoS multicast routingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152841-152856 (2021)
institution DOAJ
collection DOAJ
language EN
topic Cognitive mobile ad hoc networks
cross-layer
deep Q-network
game theory
QoS multicast routing
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Cognitive mobile ad hoc networks
cross-layer
deep Q-network
game theory
QoS multicast routing
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Thong-Nhat Tran
Toan-Van Nguyen
Kyusung Shim
Daniel Benevides Da Costa
Beongku An
A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
description In this paper, we propose a new deep Q-network (DQN) design for quality-of-service (QoS) multicast routing (DQMR) protocol to establish efficient QoS multicast (EQM) trees in cognitive radio mobile ad hoc networks (CR-MANETs). An EQM tree is a shortest-path multicast tree with minimum end-to-end (E2E) cost (a combination of queuing size ratio and link stability) subject to QoS constraints such as queuing size ratio, link stability, number of hops, number of time slots and avoiding the licensed channel of primary users. Particularly, we propose an NP-complete optimization problem such that its feasible solution is an EQM tree. To address this problem, we design a new DQN model and a new game-based model to form EQM trees in real-time by offline training instead of online training as done in previous papers. Moreover, the DQMR protocol is also guaranteed to have high stability, low routing delay, low control overhead, and high packet delivery ratio (PDR). Furthermore, one more new contribution of the paper is that exact closed-form expressions for the E2E queuing delay of a multicast routing tree are also derived assuming random waypoint mobility and the reference point group mobility models to compare with simulation results of routing delay. Simulation results show that the DQMR protocol outperforms multicast ad hoc on-demand distance vector routing protocol in terms of routing delay, control overhead, and PDR.
format article
author Thong-Nhat Tran
Toan-Van Nguyen
Kyusung Shim
Daniel Benevides Da Costa
Beongku An
author_facet Thong-Nhat Tran
Toan-Van Nguyen
Kyusung Shim
Daniel Benevides Da Costa
Beongku An
author_sort Thong-Nhat Tran
title A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
title_short A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
title_full A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
title_fullStr A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
title_full_unstemmed A New Deep Q-Network Design for QoS Multicast Routing in Cognitive Radio MANETs
title_sort new deep q-network design for qos multicast routing in cognitive radio manets
publisher IEEE
publishDate 2021
url https://doaj.org/article/f3477469621944988154e01a655445c7
work_keys_str_mv AT thongnhattran anewdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT toanvannguyen anewdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT kyusungshim anewdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT danielbenevidesdacosta anewdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT beongkuan anewdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT thongnhattran newdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT toanvannguyen newdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT kyusungshim newdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT danielbenevidesdacosta newdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
AT beongkuan newdeepqnetworkdesignforqosmulticastroutingincognitiveradiomanets
_version_ 1718419873360510976