Optimal wireless rate and power control in the presence of jammers using reinforcement learning

Future wireless networks require high throughput and energy efficiency. This paper studies using Reinforcement Learning (RL) to do transmission rate power control for maximizing a joint reward function consisting of both consumption. We design the system state include factors that reflect packet queue length, interference from other nodes, quality channel, battery status, etc. The is normalized does not involve unit conversion. It can be used train three different types agents: throughput-critical, energy-critical, balanced. Using NS-3 network simulation software, we implement these agents in an 802.11ac with presence jammer. then test two jamming nodes interfering packets received at receiver. compare performance our RL optimal policies popular Minstrel adaptation algorithm: approach achieve (i) higher when throughput-critical function; (ii) lower consumption energy-critical (iii) slightly balanced function. Although discussion focused on networks, method readily applicable networks.