Optimization of Transmission Strategy for Wireless Power Transfer Using Multi-Armed Bandit Algorithm

This paper aims to solve the optimization problems in far-field wireless power transfer systems using machine learning techniques. We assembled the RF power transfer robot, which can emit the electromagnetic wave to charge the energy harvesters that are deployed in the experimental field. The wireless transmitter intends to charge all the energy harvesters in a fair manner. Since the energy harvesters can be either stationary or mobile, a multi-armed bandit(MAB) problem is formulated and we use Upper Confidence Bound(UCB) algorithm to determine the optimal transmission strategy. As the number of the transmitters is increased, multiple wireless transmitters coordinate with each other to boost the levels of energy harvesting at all energy harvesters. Correspondingly, we formulate a combinational MAB problem and UCB algorithm is applied to determine the optimal transmission strategy for each transmitter. The simulation results prove the superiority of the Multi-armed bandit approach in solving the proposed optimization problems.