Joint link-level and network-level intelligent system and method for dynamic spectrum anti-jamming

A joint link-level and network-level intelligent system and method for dynamic spectrum anti-jamming are provided. The system includes a link-level anti-jamming subsystem and a network-level anti-jamming subsystem. The link-level anti-jamming subsystem sets a reward value as system transmission throughput in a single decision cycle, and a user makes an intelligent frequency usage decision based on the obtained reward value to skip a frequency band in which jamming exists. The network-level anti-jamming subsystem performs reasonable frequency band allocation and management for lower-level sub-users when link-level anti-jamming fails to further enhance a frequency domain anti-jamming capability of the entire system. The users make intelligent frequency usage decisions through a dynamic spectrum anti-jamming algorithm based on reinforcement learning to effectively avoid external malicious jamming, realize dynamic spectrum access, and enhance a frequency domain anti-jamming capability of the system.