Intelligent deep learning-aided future beam and proactive handoff prediction model in Unmanned Aerial Vehicleassisted anti-jamming Terahertz communication system

摘要

Wireless communications often suffer from legitimate transmissions regardingmalicious jamming attacks launched through the smart jammer. The drone orunmanned aerial vehicle (UAV) communication networks derived with reconfigurableintelligent surfaces (RIS) increase the issues of beam selection andproactive handoff in terahertz (THz). Thus, a new heuristic strategy is designedfor efficient and incorporated optimization of the beamforming vector andanti-jamming transmit power allocation in undefined environments. Here, thetransmit power allocation and beamforming matrix of UAV are optimized withthe developed hybrid heuristic algorithm of the Hybrid Crow Black WidowSearch Optimization (HCBWSO) algorithm for maximizing the system achievablerate. Here, the HCBWSO algorithm is implemented to integrate with theCrow search algorithm (CSO) and Black Widow Optimization (BWO). Thesecond contribution is to adopt RIS into THz–UAV communications, a newEnhanced Deep Temporal Convolutional Network (EDTCN) for predicting thefuture beam and proactive handoff of UAVs based on their prior analysis ofthe UAV locations, where the HCBWSO algorithm is utilized for recommendingEDTCN. Here, the training of the EDTCN needs to be done withthe collection of UAV information from the DEEPMIMO dataset for predictingthe future beams and, also, tracking the location of the UAV. EDTCN helps inincreasing the possibility of expanding the UAV coverage and also increasesthe consistency of the THz communication system. Thus, the prediction of thefuture beam increases the coverage area of the UAV and also maximizes thesystem rate in the THz communication system.