Selfish Bandit-Based Cognitive Anti-Jamming Strategy for Aeronautic Swarm Network in Presence of Multiple Jammer

Abstract

In order to enhance the anti-jamming capability of aeronautic swarm tactical network in the complicated electromagnetic environment, we address the problem of bandit-based cognitive anti-jamming strategy for enabling reliable information transmission. We first present an adversarial multiuser multi-armed bandit model for the aeronautic swarm network employing airborne cognitive radios with the same-frequency simultaneous transmit and receive feature. Then, we utilize the improved energy detection method to perform jamming sensing and derive the closed expression of false alarm probability, false detection probability, and the optimal decision threshold in the case of single and multi-jammer. Finally, using the jamming sensing output to calculate reward and with the objective of maximizing the throughput of each airborne radio, a decentralized selfish doubling trick kl-UCB ++ anti-jamming strategy is developed to allocate an optimal configuration of transmitting power and spectrum channel to each radio. This anytime bandit strategy is simultaneously minimaxed optimal and asymptotically optimal. The simulation results validate that the aggregate average throughput, cumulative regret obtained with the proposed anti-jamming strategy outperform the well-known UCB, kl-UCB ++ bandit algorithm. INDEX TERMS Cognitive anti-jamming, aeronautic swarm, adversarial multi-armed bandit, improved energy detection, doubling trick kl-UCB ++ .

Survey on cognitive anti‐jamming communications

“…A smart jammer is known also as an intelligent jammer or a cognitive jammer [26, 58, 59]. This can be the most advanced and effective technique but at the cost of high implementation complexity.…”

“…Several smart jammers are considered in [40, 59, 65–68]. These jammers are assumed to have cognitive capabilities including spectrum sensing, learning and reconfigurability.…”

“…Several anti‐jamming studies based on MAB framework can be found in [46, 59, 109–112]. MAB is a brute‐force model that captures the relationship between a learning agent and its environment [113].…”

“…MAB is a brute‐force model that captures the relationship between a learning agent and its environment [113]. The learner serially evaluates the reward generated by every available action (each action is an ‘arm’) [59]. Once an initial action‐reward relationship is developed, the model will favour actions that generated greater rewards in the previous cycle.…”

Reinforcement Learning-Based Anti-Jamming in Networked UAV Radar Systems

“…A UAV was used in [15] to send onboard units information, which improved the communication performance of vehicular ad-hoc networks in the presence of intelligent jammer. As for swarm UAV, Li Haitao et al proposed a countermeasure model based on airborne cognitive radio and used an improved energy detection method to detect jamming [16]. Li Zhiwei et al presented a method of using a software-defined network (SDN) to counter software-defined radio (SDR) [17].…”