A collaborative multi-agent message transmission mechanism in intelligent transportation system – A smart freeway example

Lo, Steven K.C.

doi:10.1016/j.ins.2011.08.024

Cited by 17 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The approach in [52] provides the coordinated behavior of multiple agents, however, it is not scalable to larger systems because the number of actions increases exponentially with the number of agents. To overcome the challenge of non-Markovian and non-stationary environments during learning, the centralized training of decentralized policies can be considered for efficient training of multiple agents and access additional state information of other agents [53]. In general, RA policies should be designed based on system features, e.g., channel gains and users arrivals, to provide user's satisfaction and QoS requirements.…”

Section: Machine Learning Based Solutionsmentioning

confidence: 99%

AI-Assisted Dynamic Frame Structure With Intelligent Puncturing Schemes for 5G Networks

Abedi,

Javan,

Pourghasemian

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The dynamic resource block structure (D-RBS) allows for flexible allocation of radio resources. This flexibility (potentially) enables efficient utilization of available resources and adaptability to changing network conditions. In this context, managing resource contention and optimizing allocation decisions become increasingly challenging. In this research paper, we introduce a new approach for D-RBS for re-allocation of enhanced Mobile Broadband (eMBB) and massive Machine Type Communication (mMTC) resource blocs (RBs) to URLLC users. Our scheme leverages artificial intelligence (AI) to support the three main services of 5th generation networks. To efficiently allocate resources for eMBB/mMTC and URLLC services, we propose an intelligent puncturing scheme. Additionally, we formulate an optimization problem that aims to minimize resource and transmit power usage while meeting the requirements of all three services. Since this problem is non-convex and involves multiple optimization variables, we utilize deep reinforcement learning as a solution algorithm. We then compare our proposed intelligent allocation (IA) scheme with two other schemes: random allocation (RaA) and overallocation (OA), which have lower complexity and overhead. Performance and complexity analyses are conducted in a multi-cell scenario with interference. Our results demonstrate that the IA scheme outperforms RaA and OA, achieving an energy efficiency gain of 40% and 15% respectively. However, it is worth noting that IA has a 36.3% higher complexity in terms of action selection compared to RaA and OA.INDEX TERMS Dynamic RB structure, URLLC puncturing, eMBB and URLLC multiplexing, MA-DRL.

show abstract

Section: Machine Learning Based Solutionsmentioning

confidence: 99%

AI-Assisted Dynamic Frame Structure With Intelligent Puncturing Schemes for 5G Networks

Abedi,

Javan,

Pourghasemian

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A trust model in [14] employs a penalty in case of misleading reports. Experiments with altruist/selfish agents in vanets [13] shown that average speed increased when the vehicular agents cooperate. A vanet-based emergency vehicle warning system has been developed in [8].…”

Section: B Multi-agent Vehicular Simulationmentioning

confidence: 99%

Assisting drivers during overtaking using Car-2-Car communication and multi-agent systems

Cara

Groza

Zaporojan

et al. 2016

2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP)

View full text Add to dashboard Cite

show abstract

“…El estudio de los sistemas multi-agente desde el punto de vista del origen de tecnología ha sido tratado desde la Ingeniería de Sistemas por parte de numerosos investigadores: (Dong et al, 2008), (Lo, 2012), (Innocenti et al, 2007), (Hu et al, 2013), (Wen et al, 2013), (Yu and Wang, 2013), (Zhu, 2014), por citar algunos, donde el interés principal es analizar las interacciones y, en muchos casos, la sincronización de agentes, que pueden ser desde simples robots hasta elementos coordinados de un sistema de control.…”

Section: Introductionunclassified

Modelado Basado en Agentes: un Enfoque desde la Ingeniería de Sistemas

Pereda

Zamarreño

2015

Revista Iberoamericana de Automática e Informática Industrial R

View full text Add to dashboard Cite

El modelado basado en agentes (ABM, Agent Based Modeling) es una técnica de modelado que está siendo explotada con grań exito enáreas como la ecología, ciencias sociales, economía, etc. Sin embargo, su uso como técnica de modelado en el campo de la Automática es más bien testimonial. En este artículo mostramos cómo se puede abordar el modelado basado en agentes desde el punto de vista de la Ingeniería de Sistemas y Automática y las particularidades que tiene como herramienta de modelado. Asimismo, proponemos una descripción matemática de los modelos basados en agentes que ilustramos con un par de ejemplos Copyright c 2015 CEA. Publicado por Elsevier España, S.L. Todos los derechos reservados.

show abstract

A collaborative multi-agent message transmission mechanism in intelligent transportation system – A smart freeway example

Cited by 17 publications

References 31 publications

AI-Assisted Dynamic Frame Structure With Intelligent Puncturing Schemes for 5G Networks

AI-Assisted Dynamic Frame Structure With Intelligent Puncturing Schemes for 5G Networks

Assisting drivers during overtaking using Car-2-Car communication and multi-agent systems

Modelado Basado en Agentes: un Enfoque desde la Ingeniería de Sistemas

Contact Info

Product

Resources

About