• Vidya E V
• Dr.B S Shylaja

Wireless Sensor Networks (WSNs) have gained huge attention in several real-time applications such as environment monitoring, military applications. Due to their technological advancements, the demand of these networks is increasing rapidly. However, these networks operate in ISM bands, thus spectrum scarcity becomes a challenging issue in this field. Currently, Cognitive Radio’s (CRs) has come up as a promising resolution in communication to deal with WSN spectrum related issues. Generally, these CRs act as secondary user (SU’s) where these nodes opportunistically access the available spectrum when primary user (PU/licensed) user is not accessing the spectrum. Moreover, the dynamic spectrum access is also considered as promising characteristic which can be beneficial in WSN due to its event driven communication strategy. Conventional methods of spectrum access face several drawbacks such as low accessibility, high interruption and energy consumption. Therefore, this work is focused on energy aware spectrum sensing mechanism by considering the spectrum aware clustering mechanism to cater the spectrum utilization issues and prolong the network lifetime. Current researches have reported the advantage of cooperative spectrum sensing and positive impact of incorporating machine learning methods to increase the spectrum utilization. Therefore, the proposed work is based on Q-learning based reinforcement learning scheme where it uses state-action-reward mechanism to estimate the decision. Along with this, spatial, temporal and residual energy parameters are incorporated to enhance the clustering performance. Based on this model, the outcome of the Proposed QLSS approach is compared with the state-of-art schemes where Proposed QLSS (Q-Learning based spectrum sensing) approach outperforms in terms of network lifetime, spectrum sensing, detection and utilization.

Wireless sensor networks (WSN), Primary users (PUs), Secondary users (SUs), Spectrum Sensing (SS)

"SPECTRUM MANAGEMENT USING Q-LEARNING APPROACH FOR CLUSTER BASED COGNITIVE RADIO WIRELESS SENSOR NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 12, page no.e109-e120, December-2022, Available :http://www.jetir.org/papers/JETIR2212414.pdf

"SPECTRUM MANAGEMENT USING Q-LEARNING APPROACH FOR CLUSTER BASED COGNITIVE RADIO WIRELESS SENSOR NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 12, page no. ppe109-e120, December-2022, Available at : http://www.jetir.org/papers/JETIR2212414.pdf