Game-Theory Based Cognitive Radio Policies for Jamming and Anti-Jamming in the IoT

The Cognitive Radio can be considered as a mandatory part of the Internet of Things applications. It helps to solve the sacristy issues in the frequency bands of the wireless network component of the technology. However, the security problem is the primary challenge that needs to be carefully mitigated. Specifically, defending the Cognitive Radio mechanism against the jamming attacks. The aim this research paper is to investigate and provide a reliable and adaptive Cognitive Radio protection methods against the jamming attacks. Thus, improving the performance of the wireless network of IoT technology, enhancing the bandwidth and solving the issue of the sacristy of the frequency bands. The mentioned objectives will be accomplished by the aid of the game theory which is modelled as an anti-jamming game and by adapting the multi-arm bandit (MAB) policies. However, to solve the sacristy issue in the frequency band spectrum of the cognitive radio, some MAB policies were adapted such as Upper Confidence Bound (UCB), Thompson Sampling and Kullback-Leibler Upper Confidence Bound (KL-UCB). The results show some improvements and enhancements to the sacristy problem in the frequency band spectrum. To conclude, the Thompson Sampling MAB policy was the best to be adapted for solving the problem, as it resulted with lowest regrets and highest rewards compared to the other MAB policies.