http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
AFRL: Adaptive Federated Reinforcement Learning for Intelligent Jamming Defense in FANET
Nishat I Mowla,Nguyen H. Tran,Inshil Doh,Kijoon Chae 한국통신학회 2020 Journal of communications and networks Vol.22 No.3
The flying ad-hoc network (FANET) is a decentralizedcommunication network for the unmanned aerial vehicles (UAVs). Because of the wireless nature and the unique network properties, FANET remains vulnerable to jamming attack with additionalchallenges. First, a decision from a centralized knowledge base isunsuitable because of the communication and power constraintsin FANET. Second, the high mobility and the low density of theUAVs in FANET require constant adaptation to newly exploredspatial environments containing unbalanced data; rendering a distributed jamming detection mechanism inadequate. Third, takingmodel-based jamming defense actions in a newly explored environment, without a precise estimation of the transitional probabilities,is challenging. Therefore, we propose an adaptive federated reinforcement learning-based jamming attack defense strategy. Wedeveloped a model-free Q-learning mechanism with an adaptiveexploration-exploitation epsilon-greedy policy, directed by an ondevice federated jamming detection mechanism. The simulation results revealed that the proposed adaptive federated reinforcementlearning-based defense strategy outperformed the baseline methods by significantly reducing the number of en route jammer location hop counts. The results also showed that the average accuracy of the federated jamming detection mechanism, leveraged inthe defense strategy, was 39.9% higher than that of the distributedmechanism verified with the standard CRAWDAD jamming attackdataset and the ns-3 simulated FANET jamming attack dataset