A CRN Based Radio Resource Optimization using Machine Learning

Abstract

Cognitive radio networks (CRNs) have been widely used in various applications for the effective radio spectrum utilization in recent years. It is essential for fend off the growing demand for this finite natural resource for next-generation communications. In CRNs, detecting the activity of primary user requires opportunistic spectrum sensing of efficient usage in available radio spectrum, which is an limited for exquisite resource. Thus, CRNs key component in solving the spectrum scarcity issue in presence of primary user bands through secondary users. Cognitive radio Ad-Hoc networks (CRAHNs) are unique kind of CRNs where infrastructures less cognitive radio (CR) nodes are furnished. In CRAHN, the CR-MAC protocol works slightly different to the traditional wireless network MAC protocols. This proposed method such as high traffic scenario under contention-based IEEE 802.11 DCF MAC protocol. Accordingly it can be observed that both throughput and delay increase as the CW size and packet length of the 802.11 (DCF) MAC protocol for CRAHN varies. The experimental result of proposed framework for CRAHN with FIS shows that altering contention window increases throughput by 70% to 75% and reduces the delay by 25% to 30% compared to the IEEE802.11 (DCF) protocol for CRAHNs without FIS. Moreover, it is also revealed that the throughput is increased by 75% and the delay is reduced by 25% due to altering the packet length.

Introduction

Cognitive Radio Networks (CRNs) are wireless networks that improve spectrum utilization by allowing unlicensed secondary users (SUs) to opportunistically use licensed spectrum when primary users (PUs) are inactive. CRN architectures include infrastructure-based (network-centric, where communication is via base stations), ad-hoc (decentralized nodes communicating directly if they share common channels), and mesh networks (a hybrid supporting multi-hop communication).

CRNs must dynamically detect PU activity to avoid interference, typically using energy detection for spectrum sensing. Communication involves control message exchange via common control channels or channel hopping. Unlike traditional ad-hoc networks, CRNs handle dynamic spectrum availability and PU protection.

The proposed work focuses on radio resource optimization in CR ad-hoc networks, aiming to efficiently allocate channels while minimizing interference and maintaining QoS. Each cognitive node has two transceivers (one for control, one for data), computes a Cluster Head Determining Factor (CHDF) based on neighboring nodes and common channels, and forms clusters managed by Cluster Heads (CHs). Border nodes called FNs facilitate inter-cluster communication.

The routing protocol uses delay metrics—including switching delay (channel changes), back-off delay (to avoid collisions), and queuing delay—to select paths with minimal latency. Route maintenance handles link failures by rerouting accordingly. The clustering scheme maximizes idle channel use within clusters, enhances energy efficiency, reduces node failures, and maintains network stability despite node mobility.

Conclusion

In this article, a spectrum aware cross-layer MAC protocol for CRAHN is presented. In the Radio resource method, the clusters are formed based on the parameter called CHDF and The protocol that attempts to maintain the number of clusters lesser while ensuring a stable and suitable number of common channels per cluster. The suitable number of common channels makes the proposed clustering scheme more robust to varying spectrum availability. The protocol also introduces secondary cluster head in each cluster, which reduces the re-clustering issue for mobile nodes Thus, less number of clusters leads the backbone to be smaller, which results in efficient and reliable communication. On the other hand, a delay aware routing protocol is presented, where delay is considered as the routing metric for the protocol. In the proposed protocol, link weight is calculated based switching delay, back-off delay and queuing delay A. Future Scope ? In future, the CRN has no delay will be occurred , because of the Communication has growing in day by day. So that we will implement the Federated Learning. ? Innetwork communication systems, aFederated Learning algorithmrefers to adecentralized machine learning processwhere multiple networked devices (or nodes) collaboratively train a shared modelwithout sending their raw data to a central server. ? Instead, they only exchangemodel updates(e.g., weights or gradients), which reduces privacy risks and communication costs.But the federated Algorithm is testing in ICOM LABS that was located in AUSTRALIA.

References

[1] S. Haykin, ‘‘Cognitive radio: Brain-empowered wireless communications,’’ IEEE J. Sel. Areas Commun., vol. 23, no. 2, pp. 201–220, Feb. 2024. [2] S. Haykin. (2022). Cognitive Radio: Brain- Empowered Wireless Communcations. Accessed: Oct. 18, 2022. [Online]. Available: https://Web.stanford.edu/class/ee360/previous/lectures/matt.pdf [3] I. F. Akyildiz, W.-Y. Lee, M. C. Vuran, and S. Mohanty, ‘‘Next generation/dynamic spectrum access/cognitive radio wireless networks: A survey,’’ Comput. Netw., vol. 50, pp. 2127–2159, Sep. 2023. [4] N. I. Sarkar, ‘‘Improving WLAN performance by modifying an IEEE 802.11 protocol,’’ Int. J. Wireless Netw. Broadband Technol., vol. 1, no. 1, pp. 15–31, Jan. 2021. [5] A. Sultana, X. Fernando, and L. Zhao, ‘‘An overview of medium access control strategies for opportunistic spectrum access in cognitive radio networks,’’ Peer-Peer Netw. Appl., vol. 10, no. 5, pp. 1113–1141, Sep. 2018. [6] A. De Domenico, E. C. Strinati, and M.-G. Di Benedetto, ‘‘A survey on MAC strategies for cognitive radio networks,’’ IEEE Commun. Surveys Tuts., vol. 14, no. 1, pp. 21–44, 1st Quart., 2017. [7] C. Cordeiro, K. Challapali, D. Birru, and S. Shankar, ‘‘IEEE 802.22: The first worldwide wireless standard based on cognitive radios,’’ in Proc. 1st IEEE Int. Symp. New Frontiers Dyn. Spectr. Access Netw., Nov. 2015, pp. 328–337. [8] A. B. Flores, R. E. Guerra, E. W. Knightly, P. Ecclesine, and S. Pandey, ‘‘IEEE 802.11 af: A standard for TV white space spectrum sharing,’’ IEEE Commun. Mag., vol. 51, no. 10, pp. 92–100, Oct. 2013.

Copyright

Copyright © 2025 S. Sultana Farveen, K. Murugan, A. Faiz Ahmed, S. Susai Raj. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.