基于神经网络的RIS通感一体编码优化方法OA

The integrated sensing and communication(ISAC)technology based on reconfigurable intelligent surface(RIS)can effectively enhance the overall system communication and sensing capabilities through direction of arrival(DOA)and beamforming techniques.To address the challenges of high computational complexity and constrained design flexibility in RIS encoding optimization,this paper proposes a neural network-based approach for coding optimization in RIS-enabled ISAC systems.This approach employs a neural network based on an asynchronous space-time coding metasurface to reduce the DOA estimation error to 0.22° under low signal-to-noise ratio(SNR)conditions of-12 dB.Furthermore,by utilizing a cascaded neural network driven by free-form design indicators,it accomplishes high-precision beamforming optimization with an error of merely 0.025.This method offers a solution with low complexity and high real-time performance for the coding optimization in RIS-enabled ISAC systems.