Multi-Agent Deep Learning for Multi-Channel Access in Slotted Wireless Networks

Mennes, Ruben; Figueiredo, Felipe Augusto Pereira de; Latré, Steven

doi:10.1109/access.2020.2995456

Cited by 17 publications

(8 citation statements)

References 27 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mennes et al [30] proposed a deep neural network (DNN) strategy for predicting spectrum occupancy in the near future of unknown neighboring networks. They showed a multi-agent environment that employs RL and supervised learning approaches.…”

Section: Wireless Spectrum Managementmentioning

confidence: 99%

A Review of Deep Learning Applications for the Next Generation of Cognitive Networks

et al. 2022

View full text Add to dashboard Cite

Intelligence capabilities will be the cornerstone in the development of next-generation cognitive networks. These capabilities allow them to observe network conditions, learn from them, and then, using prior knowledge gained, respond to its operating environment to optimize network performance. This study aims to offer an overview of the current state of the art related to the use of deep learning in applications for intelligent cognitive networks that can serve as a reference for future initiatives in this field. For this, a systematic literature review was carried out in three databases, and eligible articles were selected that focused on using deep learning to solve challenges presented by current cognitive networks. As a result, 14 articles were analyzed. The results showed that applying algorithms based on deep learning to optimize cognitive data networks has been approached from different perspectives in recent years and in an experimental way to test its technological feasibility. In addition, its implications for solving fundamental challenges in current wireless networks are discussed.

show abstract

Section: Wireless Spectrum Managementmentioning

confidence: 99%

A Review of Deep Learning Applications for the Next Generation of Cognitive Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…ML algorithms, also called models, have been widely applied to solve different problems related to optimization in wireless network communications systems [25][26][27][28]. These algorithms construct a model based on historical data, known as a training dataset, to perform tasks, for example, solving optimization problems, without being explicitly programmed to do so [29,30].…”

Section: Machine Learning Overviewmentioning

confidence: 99%

Reinforcement Learning-based Wi-Fi Contention Window Optimization

Cruz¹,

Ouameur²,

Figueiredo³

2022

Preprint

View full text Add to dashboard Cite

The collision avoidance mechanism adopted by the IEEE 802.11 standard is not optimal. The mechanism employs a binary exponential backoff (BEB) algorithm in the medium access control (MAC) layer. Such an algorithm increases the backoff interval whenever a collision is detected to minimize the probability of subsequent collisions. However, the expansion of the backoff interval causes degradation of the radio spectrum utilization (i.e., bandwidth wastage). That problem worsens when the network has to manage the channel access to a dense number of stations, leading to a dramatic decrease in network performance. Furthermore, a wrong backoff setting increases the probability of collisions such that the stations experience numerous collisions before achieving the optimal backoff value. Therefore, to mitigate bandwidth wastage and, consequently, maximize the network performance, this work proposes using reinforcement learning (RL) algorithms, namely Deep Q Learning (DQN) and Deep Deterministic Policy Gradient (DDPG), to tackle such an optimization problem. As for the simulations, the NS-3 network simulator is used along with a toolkit known as NS3-gym, which integrates a reinforcement-learning (RL) framework into NS-3. The results demonstrate that DQN and DDPG have much better performance than BEB for static and dynamic scenarios, regardless of the number of stations. Moreover, the performance difference is amplified as the number of stations increases, with DQN and DDPG showing a 27% increase in throughput with 50 stations compared to BEB. Furthermore, DQN and DDPG presented similar performances.

show abstract

“…None of these published works discussed the collaborative flow control mechanisms of the SCATTER system. Overall architecture [25], predicted slot selection [26], physical radio details [27], technology-aware incumbent avoidance [28], [29], and the software architecture details used by the proposed algorithm [21] are discussed in previous work. Note that the discussed architecture could easily be implemented on top of modern wireless radios such as 5G new radio, 4G or Wi-Fi as we discuss later in this section.…”

Section: Architecturementioning

confidence: 99%

Collaborative Flow Control in the DARPA Spectrum Collaboration Challenge

Mennes

Struye

Donato

et al. 2020

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

Wireless network technologies are becoming more and more popular. Because of this, important parts of the wireless spectrum become overloaded. Static spectrum allocation, which has been the norm for decades, is not suitable anymore. To maintain the high demand for spectrum and the continuous development of new wireless technologies, there is a need for an intelligent, dynamic spectrum allocation mechanism, where different network technologies collaboratively optimize the spectrum usage. New wireless network paradigms, such as Neutral Host Networks (NHNs) and private 5G, require a smart, spectrumfootprint-aware flow control algorithm to overcome the spectrum scarcity in collaborative way. This article presents a strategy, vision and flow control mechanism to implement collaboration in a Quality of Service (QoS)-driven way. The solution in this article is based on policies which may activate depending on its current and neighbor's network states. Through a flow ordering and selection strategy, these policies optimize the spectrum footprint, based on the performance and QoS-requirements of the own and surrounding networks. The proposed algorithm is tested extensively and validated on a large scale during the DARPA Spectrum Collaboration Challenge (SC2) competition. The results of the SC2 final event and intermediate scrimmages showed that the proposed approach increased the score, indicating increased inter-network collaboration was achieved. Index Terms-Quality of service, wireless flow control, wireless networks and cellular networks, wireless spectrum collaboration. I. INTRODUCTION C OLLABORATION in the wireless spectrum is key to further exploration of the capacity of today's wireless communication. Driven by the increasing need for wireless capacity [1], spectrum scarcity is a familiar phenomenon,

show abstract

Multi-Agent Deep Learning for Multi-Channel Access in Slotted Wireless Networks

Cited by 17 publications

References 27 publications

A Review of Deep Learning Applications for the Next Generation of Cognitive Networks

A Review of Deep Learning Applications for the Next Generation of Cognitive Networks

Reinforcement Learning-based Wi-Fi Contention Window Optimization

Collaborative Flow Control in the DARPA Spectrum Collaboration Challenge

Contact Info

Product

Resources

About