The Reinforcement Learning based Local Routing Optimization for Ad-hoc Network

A reinforcement learning based local routing optimization scheme with two different semiconductor chips - hub IC and node ICs is proposed for the ad-hoc network. The received signal strength indicator (RSSI) in IC generates voltage information for analyzing network quality between each node and collected RSSI data are used for input and reward function of the learning agent. The Q-learning method is utilized for reinforcement learning. The chip fabricated with a 0.18 mu m CMOS process, which uses the standard supply voltage of 1.5 V, achieves the lowest power consumption of 274 mu W at the supply voltage of 0.8 V. The proposed reinforcement learning based local routing optimization for the ad-hoc network reduce 64 % of total network power consumption compare to the conventional infrastructure based network.