Abstract
In this study, we explore the task of dynamic spectrum access based on game theory to mitigate spectrum shortage and improve network utilization in multichannel wireless networks. Usually, the available network bandwidth is limited and divided into several channels, and there exists a need for efficient reuse and adaptive allocation of such channels. During the communication process, U users compete with each other for C shared channels even without knowing accurate, complete channel state information. In order to avoid collision, traditional methods usually depend on centralized scheduling or message exchange, which are cumbersome and computationally expensive. To deal with this issue, we propose a deep Q-network, based on LSTM and fair channel allocation policy, to learn the dynamic spectrum access rules for network utility maximization. Extensive validation of the proposed approach shows that our scheme yields quite promising results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kuo FF (1973) The ALOHA system. In: Computer networks, 501–518, Prentice-Hall, Englewood Cliffs, NJ, USA
Jianliang G et al (2013) QSA: query splitting-based anticollision for mobile RFID-based internet-of-things. Int J Distributed Sens Netw 9(7):674698
Zhao Q, Sadler BM (2007) A survey of dynamic spectrum access. IEEE Signal Process Mag 24(3):79–89. https://doi.org/10.1109/MSP.2007.361604
Garhwal A, Bhattacharya PP (2012) A survey on dynamic spectrum access techniques for cognitive radio. arXiv preprint arXiv:1201.1964
Nguyen HQ et al (2018) Deep Q-learning with multiband sensing for dynamic spectrum access. 2018 IEEE international symposium on dynamic spectrum access networks (DySPAN), IEEE
Fu F, van der Schaar M (2009) Learning to compete for resources in wireless stochastic games. IEEE Trans Veh Technol 58(4):1904–1919
van der Schaar M, Fu F (2009) Spectrum access games and strategic learning in cognitive radio networks for delay-critical applications. Proc IEEE 97(4):720–739
Han Z, Pandana C, Liu KR (2007) Distributive opportunistic spectrum access for cognitive radio using correlated equilibrium and no-regret learning. In: proceedings of IEEE wireless communications and networking conference (WCNC’07), pp 11–15
Cohen K, Zhao Q, Scaglione A (2014) Restless multi-armed bandits under time-varying activation constraints for dynamic spectrum access. In: 48th Asilomar conference on signals, systems and computers, pp 1575–1578
Li H (2010) Multiagent-learning for aloha-like spectrum access in cognitive radio systems. EURASIP J Wirel Commun Netw 2010: 1–15
Naparstek O, Cohen K (2017) Deep multi-user reinforcement learning for dynamic spectrum access in multichannel wireless networks. GLOBECOM 2017–2017 IEEE global communications conference, IEEE
Naparstek O, Cohen K (2018) Deep multi-user reinforcement learning for distributed dynamic spectrum access. IEEE transactions on wireless communications, pp 1–1
Selvin S et al (2017) Stock price prediction using LSTM, RNN and CNN-sliding window model. 2017 international conference on advances in computing, communications and informatics (icacci). IEEE
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qu, C., Fan, C., Wang, Y. et al. A game theory based approach for distributed dynamic spectrum access. Evol. Intel. 17, 275–282 (2024). https://doi.org/10.1007/s12065-022-00709-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-022-00709-y