Detection of Spectral Resources in Cognitive Radios Using Reinforcement Learning

Berthold, U.; Fu, Fang; Schaar, Mihaela van der; Jondral, Friedrich K.

doi:10.1109/dyspan.2008.82

Cited by 57 publications

(38 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Control signaling to inform users about the chunks that are used in the cell is assumed. Notice also that P m does not depend of the chunk in (5) and (6). This is because transmitted power per chunk is constant and average path loss and shadowing is assumed to be non-frequency dependent into the service bandwidth.…”

Section: Short-term Scheduler (Sts)mentioning

confidence: 92%

“…RL shows inherent cognitive capabilities since it consists in learning the suitable set of actions to choose in order to maximize a numerical reward given that there is a continuous interaction with an environment. Hence, RL has been successfully applied to spectrum sensing [6] or spectrum sharing [7] procedures in Cognitive Radio (CR). Also, in our previous work, we showed that RL can be used to implement centralized dynamic spectrum assignment (DSA) strategies for primary cellular networks [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed spectrum management based on reinforcement learning

Bernardo

Agustí

Perez-Romero

et al. 2009

2009 4th International Conference on Cognitive Radio Oriented Wireless Networks and Communications

View full text Add to dashboard Cite

Abstract-This paper presents a novel distributed framework to decide the spectrum assignment in a primary cellular radio access network. The distributed nature of the framework allows each cell to autonomously decide (by means of machine learning procedures) the best frequencies to use in order to maximize spectral efficiency, preserve quality-of-service, and generate spectrum gaps, so that secondary cognitive radio networks can improve overall spectrum usage. The proposed distributed framework has been validated over a downlink multicell OFDMA radio access network, showing comparable performance results with respect to its centralized counterpart and superior performance with respect to fixed frequency planning schemes.

show abstract

Section: Short-term Scheduler (Sts)mentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Distributed spectrum management based on reinforcement learning

Bernardo

Agustí

Perez-Romero

et al. 2009

2009 4th International Conference on Cognitive Radio Oriented Wireless Networks and Communications

View full text Add to dashboard Cite

show abstract

“…In [5], RL is applied in DCS among the Base Stations (BS)s in order to enable each BS to cover a minimum percentage of service area with the highest SINR so as to reduce call blocking and dropping probability. In [6], RL is applied to identify channels with the most available white spaces at the BS in centralized networks. In [7], RL is applied in spectrum assignment strategy in OFDMA networks in order to improve the PU's performance metrics including spectral efficiency, users' Quality of Service (QoS) satisfaction, and the amount of licensed spectrum to be released to SUs.…”

Section: Introductionmentioning

confidence: 99%

Learning mechanisms for achieving context awareness and intelligence in Cognitive Radio networks

Yau

Komisarczuk

Teal

2011

2011 IEEE 36th Conference on Local Computer Networks

View full text Add to dashboard Cite

Abstract-Given that the licensed or Primary Users (PUs) are oblivious to the presence of unlicensed or Secondary Users (SUs), Cognitive Radio (CR) is a new paradigm in wireless communication that allows the SUs to detect and use the underutilized licensed spectrum opportunistically and temporarily. Context awareness and intelligence are key characteristics of CR to enable the SU to sense for and use the underutilized licensed spectrum in an efficient manner. In this technical report, we investigate into various learning mechanisms for achieving context awareness and intelligence in CR networks. The learning mechanisms are Adaptation (Adapt), Window (Win), Adaptation-Window (AdaptWin), and Reinforcement Learning (RL). We investigate the learning mechanisms with respect to dynamic channel selection scheme that helps SU base station to select channel adaptively for data transmission to SU host in static and mobile centralized CR networks. The purpose is to enhance quality of service, particularly throughput and delay, and in terms of minimising number of channel switchings. Channel heterogeneity is considered in this paper. Our contribution in this paper is to investigate into learning mechanisms that are simple yet pragmatic for CR networks. Simulation results reveal that RL, AdaptWin and Win achieve approximately similar and the best possible network performance, followed by Adapt, and finally Random scheme, which does not apply any learning mechanism and serves as baseline.

show abstract

“…In [7], RL is applied in DCS among the base stations in order to enable each of them to cover a minimum percentage of service area with the highest SINR so as to reduce call blocking and dropping probability. In [8], RL is applied to identify channels with the most available white spaces at the base station in centralized networks. In [9], RL is applied in spectrum assignment strategy in OFDMA networks in order to improve the PU's performance metrics including spectral efficiency, users' quality of service satisfaction, and the amount of licensed spectrum to be released to SUs.…”

Section: Introductionmentioning

confidence: 99%

Enhancing network performance in Distributed Cognitive Radio Networks using single-agent and multi-agent Reinforcement Learning

Yau

Komisarczuk

Paul

2010

IEEE Local Computer Network Conference

View full text Add to dashboard Cite

Abstract-Cognitive Radio (CR) is a next-generation wireless communication system that enables unlicensed users to exploit underutilized licensed spectrum to optimize the utilization of the overall radio spectrum. A Distributed Cognitive Radio Network (DCRN) is a distributed wireless network established by a number of unlicensed users in the absence of fixed network infrastructure. Context awareness and intelligence are the capabilities to enable each unlicensed user to observe and carry out its own action as part of the joint action on its operating environment for network-wide performance enhancement. These capabilities can be applied in various application schemes in CR networks such as Dynamic Channel Selection (DCS), congestion control, and scheduling. In this paper, we apply Reinforcement Learning (RL), including single-agent and multi-agent approaches, to achieve context awareness and intelligence. Firstly, we show that the RL achieves a joint action that provides better network-wide performance in respect to DCS in DCRNs. Secondly, we show that RL achieves high level of fairness. Thirdly, we show the effects of network density and various essential parameters in RL on the network-wide performance.

show abstract

Detection of Spectral Resources in Cognitive Radios Using Reinforcement Learning

Cited by 57 publications

References 8 publications

Distributed spectrum management based on reinforcement learning

Distributed spectrum management based on reinforcement learning

Learning mechanisms for achieving context awareness and intelligence in Cognitive Radio networks

Enhancing network performance in Distributed Cognitive Radio Networks using single-agent and multi-agent Reinforcement Learning

Contact Info

Product

Resources

About