Location-Aware Sleep Strategy for Energy-Delay Tradeoffs in 5G with Reinforcement Learning

Amine, Ali El; Hassan, Hussein Al Haj; Iturralde, Mauricio; Nuaymi, Loutfi

doi:10.1109/pimrc.2019.8904155

Cited by 19 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine Learning (ML) and Deep Learning (DL) are among the most powerful tools in solving complex classification problems. More specifically, they have been employed in wireless communication to efficiently manage the spectrum and the power resources, and to ensure high quality of services for the mobile users [ 84 , 85 , 86 , 87 , 88 ]. In the CR domain, one of the objectives of using ML and DL is to enhance the SS performance.…”

Section: Learning Techniques For Spectrum Sensingmentioning

confidence: 99%

Spectrum Sensing for Cognitive Radio: Recent Advances and Future Challenge

Nasser

Hassan

Chaaya

et al. 2021

Sensors

137

View full text Add to dashboard Cite

Spectrum Sensing (SS) plays an essential role in Cognitive Radio (CR) networks to diagnose the availability of frequency resources. In this paper, we aim to provide an in-depth survey on the most recent advances in SS for CR. We start by explaining the Half-Duplex and Full-Duplex paradigms, while focusing on the operating modes in the Full-Duplex. A thorough discussion of Full-Duplex operation modes from collision and throughput points of view is presented. Then, we discuss the use of learning techniques in enhancing the SS performance considering both local and cooperative sensing scenarios. In addition, recent SS applications for CR-based Internet of Things and Wireless Sensors Networks are presented. Furthermore, we survey the latest achievements in Spectrum Sensing as a Service, where the Internet of Things or the Wireless Sensor Networks may play an essential role in providing the CR network with the SS data. We also discuss the utilisation of CR for the 5th Generation and Beyond and its possible role in frequency allocation. With the advancement of telecommunication technologies, additional features should be ensured by SS such as the ability to explore different available channels and free space for transmission. As such, we highlight important future research axes and challenging points in SS for CR based on the current and emerging techniques in wireless communications.

show abstract

Section: Learning Techniques For Spectrum Sensingmentioning

confidence: 99%

Spectrum Sensing for Cognitive Radio: Recent Advances and Future Challenge

Nasser

Hassan

Chaaya

et al. 2021

Sensors

137

View full text Add to dashboard Cite

show abstract

“…A location-aware BS sleeping strategy that would jointly optimizes the trade-off between energy and delay in a 5G HetNet was introduced in [32]. A Q-learning algorithm which considers the location and velocity of the users in determining the sleep mode level of the BS was developed to maximize the energy delay trade-off of the network.…”

Section: Related Workmentioning

confidence: 99%

A Lightweight Cell Switching and Traffic Offloading Scheme for Energy Optimization in Ultra-Dense Heterogeneous Networks

Abubakar¹,

Mollel²,

Öztürk³

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the major capacity boosters for 5G networks is the deployment of ultra-dense heterogeneous networks (UDHNs). However, this deployment results in tremendous increase in the energy consumption of the network due to the large number of base stations (BSs) involved. In addition to enhanced capacity, 5G networks must also be energy efficient for it to be economically viable and environmentally friendly. Dynamic cell switching is a very common way of reducing the total energy consumption of the network but most of the proposed methods are computationally demanding which makes them unsuitable for application in ultra-dense network deployment with massive number of BSs. To tackle this problem, we propose a lightweight cell switching scheme also known as Threshold-based Hybrid cEll swItching Scheme (THESIS) for energy optimization in UDHNs. The developed approach combines the benefits of clustering and exhaustive search (ES) algorithm to produce a solution whose optimality is close to that of the ES (which is guaranteed to be optimal), but is computationally more efficient than ES and as such can be applied for cell switching in real networks even when their dimension is large. The performance evaluation shows that the THESIS produces a significant reduction in the energy consumption of the UDHN and is able to reduce the complexity of finding a near-optimal solution from exponential to polynomial complexity.

show abstract

“…The latter adds flexibility to cope with the traffic requirements to further enhance the system performance by reducing the energy consumption of future networks while minimizing the impact on the Quality of Service (QoS). In this regard, there exist several studies that consider the problem of Energy-Delay Tradeoff (EDT) using multi-level SM scheme [8]- [10]. By applying tools from machine learning, and in particular reinforcement learning, these works study the multi-objective function of the EDT problem for different SM policies depending on the service use case, allowing the operator to tune the network parameters towards more energy savings or less service delay.…”

Section: Introductionmentioning

confidence: 99%

“…We propose a distributed Qlearning algorithm controller for small cells that adapts their activity based on the level of interference, the traffic load and the size of the buffered data in the cell. Different from the works in [8]- [10], in this paper we take into account the co-channel interference between the cells to minimize its effect to enhance the network's performance. Different from [11], we propose a distributed Qlearning algorithm where each cell makes autonomous decisions according to the Decentralized SON (D-SON) paradigm.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Delay-Constrained Energy-Aware Small Cells with Multi-Sleeping Control

Amine

Dini

Nuaymi

2020

2020 IEEE International Conference on Communications Workshops (ICC Workshops)

Self Cite

View full text Add to dashboard Cite

In 5G networks, specific requirements are defined on the periodicity of Synchronization Signaling (SS) bursts. This imposes a constraint on the maximum period a Base Station (BS) can be deactivated. On the other hand, BS densification is expected in 5G architecture. This will cause a drastic increase in the network energy consumption followed by a complex interference management. In this paper, we study the Energy-Delay-Tradeoff (EDT) problem in a Heterogeneous Network (HetNet) where small cells can switch to different sleep mode levels to save energy while maintaining a good Quality of Service (QoS). We propose a distributed Q-learning algorithm controller for small cells that adapts the cell activity while taking into account the co-channel interference between the cells. Our numerical results show that multi-level sleep scheme outperforms binary sleep scheme with an energy saving up to 80% in the case when the users are delay tolerant, and while respecting the periodicity of the SS bursts in 5G.

show abstract

Location-Aware Sleep Strategy for Energy-Delay Tradeoffs in 5G with Reinforcement Learning

Cited by 19 publications

References 14 publications

Spectrum Sensing for Cognitive Radio: Recent Advances and Future Challenge

Spectrum Sensing for Cognitive Radio: Recent Advances and Future Challenge

A Lightweight Cell Switching and Traffic Offloading Scheme for Energy Optimization in Ultra-Dense Heterogeneous Networks

Reinforcement Learning for Delay-Constrained Energy-Aware Small Cells with Multi-Sleeping Control

Contact Info

Product

Resources

About