Artificial Intelligence-Based Spectrum Allocation Strategies for Dynamic Spectrum Access in 5G and IMS Networks

Adebayo I. Aderonmu, Olanrewaju Oluwaseun Ajayi

Abstract


The advent of Cognitive Radio (CR) technology has significantly enhanced the efficiency and effectiveness of spectrum utilization. In Cognitive Radio Networks (CRNs), secondary users (SUs) dynamically select available radio frequency (RF) spectrum bands for opportunistic use when primary users (PUs) temporarily vacate their allocated spectrum. Despite numerous proposed spectrum selection methods, many fail to adequately address the impact of frequent channel switching on the Quality of Service (QoS) for SUs and the overall throughput of the CR system. Moreover, these methods often overlook the temporal patterns of channel usage by PUs. This paper presents an Artificial Intelligence-Based Spectrum Allocation Strategy designed for dynamic spectrum access in 5G and IP Multimedia Subsystem (IMS) networks. Our approach introduces two heuristic-based algorithms: the AI-driven Spectrum Selection for Minimal Channel Switching (AI-SS-MCS), which identifies the optimal channel for SUs to minimize switching frequency, and the AI-driven Spectrum Selection for Maximum Throughput (AI-SS-MT), which maximizes the CR system's overall throughput. The "optimal" channel is defined as one that allows SUs to remain connected for extended periods with minimal interruptions and offers the highest throughput. Additionally, the study propose an intelligent learning mechanism to identify and exploit spectral opportunities. Our results demonstrate that AI-SS-MCS and AI-SS-MT outperform traditional Random Spectrum Selection Schemes, significantly reducing channel switching and enhancing throughput, thereby proving their efficacy for advanced 5G and IMS network applications.


Full Text:

PDF

References


Federal Communications Comission, Notice of proposal rulemaking and order,ET Docket No. 03-322,USA,Nov.2003

I. F. Akyildiz, W.-Y. Lee, M. C. Vuran, and S. Mohanty, “NeXt generation/dynamic spectrum access/cognitive radio wireless networks: a survey,” Elsevier Computer Networks, vol. 50, no. 13, pp. 2127–2159, 2006.

M. A. McHency, P. A. Tenhula, D. McCloskey, D. A. Reberson, and C. S. Hood, “Chicago spectrum occupancy measurements and analysis and a long- term studies proposal protocol,” in Proc. 1st Int. Workshop on Technology and Policy for Accessing Spectrum, Boston, MA, USA, Aug. 5 2006.

Maziar Nekovee, a Survey of Cognitive Radio Access to TV Whitespaces, International Journal of Digital Multimedia BroadcastingVolume2010.http://www.quasarspectrum.eu/images/stories/Documents/publications/Nekovee_journal2010.pdf.

CEPT Report 24, Technical considerations regarding harmonization options for the Digital Dividend: A preliminary assessment of the feasibility of fitting new/future applications/services into non-harmonized spectrum of the digital dividend (namely the so-called "white spaces" between allotments) http://www.erodocdb.dk/docs/doc98/official/pdf/CEPTRep024.pdf.

R. A. Rashid, M. A. Sarijari, N. Fisal, S. Yusof and N. H. Mahalin “Spectrum Sensing Measurement using GNU Radio and USRP Software Radio Platform” In Proc. of The Seventh International Conference on Wireless and Mobile Communications 2011.pp 237-242 .

J. Mitola III, Maguire, and G. Q. Maguire, Jr., “Cognitive radio: making software radios more personal” IEEE Personal Communications, vol. 6, no. 4, (1999).

Federal Communications Commission (FCC): Facilitating opportunities for flexible, efficient and reliable spectrum use employing cognitive radio technologies: Notice of proposed rulemaking and order. ET Docket 03–108 & 03-322, (2003)

Yang Song; Yuguang Fan; Yanchao Zhang, “Stochastic Channel Selection in Cognitive Radio Networks,” Global Telecommunications Conference, 2007 Washington DC (GLOBECOM ’07), Nov 2007, pp.4878-4882.

Bennai, M.; Sydor, J.; Rahman, M., "Automatic channel selection for cognitive radio systems," IEEE 21st International Symposium on Personal Indoor and Mobile Radio Communications (PIMRC), pp. 1831-1835, Sept. 2010

ICASA, “450 MHz - 470 MHz: Consolidated Audit Report,” May 2010;https://www.icasa.org.za/Portals/0/Regulations/Spectrum%20Usage%20and%20Spare%20Frequencies/Consolidated%20Spectrum%20Audit%20450MHz-470MHz%20final%20100510.pdf.

ICASA, “790 MHz - 862 MHz: Consolidated Audit Report,” May 2009;https://www.icasa.org.za/Portals/0/Regulations/Spectrum%20Usage%20and%20Spare%20Frequencies/790MHz-862MHz%20Consolidated%20Spectrum%20Audit%20Report.pdf

Adebayo I. Aderonmu, Linoh A. Magagula, Karim Djouani (2014), ''spectrum selection technique to reduce the number of channel switching for dynamic spectrum access in cognitive radio networks' 'Proceedings of the IASTED International Conference modelling and Simulation (Africa MS 2014), September 1 - 3, 2014 Gaborone, Botswana

H N Nie, C Comaniciu, Adaptive channel allocation spectrum etiquette for cognitive radio networks in IEEE DySPAN, 269–278 (2005)

H Zheng, L Cao, Device-centric spectrum management. in IEEE DySPAN, 56–65 (2005)

Aderonmu, A.I., Adegnandjou, R.H., Masonta, M.T., Mzyece, M. (2013). VHF Spectrum Monitoring Using Meraka Cognitive Radio Platform. In: Jonas, K., Rai, I.A., Tchuente, M. (eds) e-Infrastructure and e-Services for Developing Countries. AFRICOMM 2012. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 119. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41178-6_6

A Saleem, L Kyung-Geun, Fair, efficient and power optimized spectrum sharing scheme for cognitive radio network. EURASIP J. Wirel. Commun. Netw (2011). Doi:10.1186/1687-1499-2011-201


Refbacks

  • There are currently no refbacks.