Equilibrium Approximating and Online Learning for Anti-Jamming Game of Satellite Communication Power Allocation

• DOI: 10.3390/electronics11213526
• Publication Date: 2022-10-30T08:57:34Z
• Authors: Mingwo Zou; Jing Chen; Junren Luo; Zhenzhen Hu; Shaofei Chen
• Keywords: Potential game; Communications satellite

Satellite communication systems are increasingly facing serious environmental challenges such as malicious jamming, monitoring, and intercepting. As a current development of artificial intelligence, intelligent jammers with learning ability can effectively perceive the surrounding spectrum environment to dynamically change their jamming strategies. result, mainstream satellite anti-jamming technology based on wide interval high-speed frequency hopping is unable deal this problem effectively. In work, we focus problems in domain, reformulate power allocation under two kinds confrontation scenarios one-shot repeated games model. Specifically, for multi-channel scenario, firstly model allocating limited resource between parties jammer BG (Blotto Game) Secondly, DO-SINR (Double Oracle-Signal Interference plus Noise Ratio) algorithm designed approximate Nash equilibrium game parties. Experiments show that obtain game. For transform into an online shortest path graph structure make solving process more intuitive, then design Exp3-U (Exp3-Uniform) which utilizes solve problem. our minimize expected regret during confrontation, while maintaining good operating efficiency. The constructed paper common formed scenarios. Our research analysis simulate some actual allocation, be used improve adaptability complex environments.