Abstract
In this paper, we consider a point-to-point wireless communications for embedded battery powered systems. We aim to provide an optimal use of all the usable capacity inside the battery before it becomes exhausted. For this purpose, we exploit the recovery effect to extend their lifetime. We consider a stochastic battery model and use both dynamic programming and reinforcement learning approaches to compute optimal transmission policies for wireless sensor networks. The obtained results show that the expected total transmitted data and the battery lifetime are maximized when all the charge units inside the battery are consumed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have