Multi-User Opportunistic Spectrum Access Using Reinforcement Learning

This paper studies the channel exploration problem for the distributed opportunistic spectrum access (D-OSA) system, where multiple secondary users (SUs) sequentially sense multiple licensed channels and utilize one of idle channel. However, channel sensing order can affect the system performance seriously. When using a better sensing order, the SU can find faster a free channel with high quality and the less collisions among SUs can happen. In this paper, we propose a mechanism using reinforcement learning to find dynamically out a sensing order for improving the system performance. In the proposed mechanism, the interactions among SUs are considered. Simulation results are provided to show the effectiveness of the proposed mechanism and the significant improvement of the system performance.

Download Full-text

“Threshold-Deciding” Policy in Distributed Multiuser Opportunistic Spectrum Access

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.926-930.2867 ◽

2014 ◽

Vol 926-930 ◽

pp. 2867-2870

Author(s):

Yu Meng Wang ◽

Liang Shen ◽

Xiang Gao ◽

Cheng Long Xu ◽

Xiao Ya Li ◽

...

Keyword(s):

Opportunistic Spectrum Access ◽

Spectrum Access ◽

Secondary Users ◽

Adaptive Policy ◽

Markov Decision ◽

Single User ◽

Simulation Results ◽

Partially Observable ◽

Time And Energy ◽

The Given

This paper studies the problem of distributed multiuser Opportunistic Spectrum Access based on Partially Observable Markov Decision Process (POMDP). Due to the similarity of spectrum environment, secondary users may choose the same channel adopting their own single user approach, which leads to collision. Referring to the previous works, we propose a more flexible and adaptive policy named “threshold-deciding”. Firstly, the SU gets a channel by adopting the random policy. Secondly, the SU decides whether to sense the channel by comparing the available probability with the given threshold. The policy not only decreases the collisions among SUs but also reduces the consumption of time and energy. The simulation results shows that the upgrade of performance is up to 100% compared with the existing random policy, which demonstrate the advantage of the proposed policy.

Download Full-text

Game Theoretic Cloud-Assisted Opportunistic Spectrum Access in Cognitive Radio Networks

International Journal of Grid and High Performance Computing ◽

10.4018/ijghpc.2016040106 ◽

2016 ◽

Vol 8 (2) ◽

pp. 94-110

Author(s):

Danda B. Rawat ◽

Sachin Shetty

Keyword(s):

Cognitive Radio ◽

Wide Band ◽

Cognitive Networks ◽

Opportunistic Spectrum Access ◽

Packet Error Rate ◽

Theoretic Approach ◽

Spectrum Access ◽

Secondary Users ◽

Computational Capacity ◽

Game Theoretic

Opportunistic Spectrum Access (OSA) in a Cognitive Radio Network (CRN) is regarded as emerging technology for utilizing the scarce Radio Frequency (RF) spectrum by allowing unlicensed secondary users (SUs) to access licensed spectrum without creating harmful interference to primary users (PUs). The SUs are considerably constrained by their limited power, memory and computational capacity when they have to make decision about spectrum sensing for wide band regime and OSA. The SUs in CRN have the potential to mitigate these constraints by leveraging the vast storage and computational capacity of cloud computing approaches. In this paper, the authors investigate a game theoretic approach for opportunistic spectrum access in cognitive networks. The proposed algorithm leverages the geo-locations of both SUs and spectrum opportunities to facilitate OSA to SUs. The active SUs using game theory adapt their transmit powers in a distributed manner based on the estimated average packet-error rate while satisfying the Quality-of-Service (QoS) in terms of signal-to-interference-noise-ratio (SINR). Furthermore, to control greedy SUs in distributed power control game, the authors introduce a manager/leader through a Stackelberg power adaptation game. The performance of the proposed approaches is investigated using numerical results obtained from simulations.

Download Full-text

Gaussian Process Reinforcement Learning for Fast Opportunistic Spectrum Access

IEEE Transactions on Signal Processing ◽

10.1109/tsp.2020.2986354 ◽

2020 ◽

Vol 68 ◽

pp. 2613-2628

Author(s):

Zun Yan ◽

Peng Cheng ◽

Zhuo Chen ◽

Yonghui Li ◽

Branka Vucetic

Keyword(s):

Reinforcement Learning ◽

Gaussian Process ◽

Opportunistic Spectrum Access ◽

Spectrum Access

Download Full-text

Reinforcement learning demonstrator for opportunistic spectrum access on real radio signals

2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN) ◽

10.1109/dyspan.2015.7343919 ◽

2015 ◽

Cited By ~ 1

Author(s):

Christophe Moy ◽

Amor Nafkha ◽

Malek Naoues

Keyword(s):

Reinforcement Learning ◽

Opportunistic Spectrum Access ◽

Spectrum Access ◽

Radio Signals

Download Full-text

Gaussian Process Reinforcement Learning for Fast Opportunistic Spectrum Access

2019 IEEE Global Communications Conference (GLOBECOM) ◽

10.1109/globecom38437.2019.9013555 ◽

2019 ◽

Cited By ~ 1

Author(s):

Zun Yan ◽

Peng Cheng ◽

Zhuo Chen ◽

Yonghui Li ◽

Branka Vucetic

Keyword(s):

Reinforcement Learning ◽

Gaussian Process ◽

Opportunistic Spectrum Access ◽

Spectrum Access

Download Full-text

Sequential opportunistic spectrum access with imperfect channel sensing

Ad Hoc Networks ◽

10.1016/j.adhoc.2012.09.004 ◽

2013 ◽

Vol 11 (3) ◽

pp. 778-797 ◽

Cited By ~ 4

Author(s):

Tao Shu ◽

Marwan Krunz

Keyword(s):

Opportunistic Spectrum Access ◽

Spectrum Access ◽

Channel Sensing

Download Full-text

Performance of secondary users in opportunistic spectrum access

Electronics Letters ◽

10.1049/el:20081625 ◽

2008 ◽

Vol 44 (16) ◽

pp. 981 ◽

Cited By ~ 3

Author(s):

Y. Lee

Keyword(s):

Opportunistic Spectrum Access ◽

Spectrum Access ◽

Secondary Users

Download Full-text

Security in Cognitive Radio Networks

Advances in Wireless Technologies and Telecommunication - Evolution of Cognitive Networks and Self-Adaptive Communication Systems ◽

10.4018/978-1-4666-4189-1.ch013 ◽

2013 ◽

pp. 301-335 ◽

Cited By ~ 2

Author(s):

Krešimir Dabcevic ◽

Lucio Marcenaro ◽

Carlo S. Regazzoni

Keyword(s):

Cognitive Radio ◽

Embedded Systems ◽

Cognitive Radio Networks ◽

Cognitive Radios ◽

Opportunistic Spectrum Access ◽

Spectrum Access ◽

Counter Measures ◽

Security Issues ◽

Systems Security ◽

Simulation Results

While potentially solving the spectrum underutilization problem using methods such as dynamic and opportunistic spectrum access, Cognitive Radios (CRs) also bring a set of security issues and potential breaches that have to be addressed. These issues come from the two important capabilities implemented within CRs: their cognition ability and reconfigurability. This chapter focuses on identifying, presenting, and classifying the main potential security attacks and vulnerabilities, as well as proposing appropriate counter-measures and solutions for them. These are supplemented by simulation results and metrics, with the intention of estimating the efficiency of each of the observed attacks and its counter-measure. The presented simulations are performed in the proprietary C/C++ and Matlab/Simulink simulators. nSHIELD is a major ongoing European embedded systems security-related project, which is used to demonstrate the practicability of the potential implementation of the proposed countermeasures and solutions for the discussed security problems and issues.

Download Full-text