Abstract
The development of integrated sensing and communication (ISAC) brings new challenges to network optimization. This is not only due to the unpredictable relationship between ISAC network performance and network parameters but also the lack of well-suited ISAC channel models for ISAC network optimization. We propose a framework of multi-beam statistical channel modeling aided ISAC signal signal-to-interference-plus-noise ratios (SINR) prediction, utilizing channel angular power spectrum to accurately characterize both echo signal and communication signal-to-interference-plus-noise ratio after antenna parameter adjustment. Utilizing real-world driving test data for multi-path channel estimation, this framework accurately characterizes the stochastic sensing channels and provides effective prediction strategies for antenna parameter adjustments. Simulation results demonstrate that our approach outperforms the conventional method with a single-beam path loss model.