Learning to Optimize Energy Efficiency in Energy Harvesting Wireless Sensor Networks

TL;DR

This paper proposes a learning-based approach to optimize energy transmission in energy harvesting wireless sensor networks, using a bandit algorithm to adapt power levels without channel state information, improving energy efficiency.

Contribution

It introduces a novel application of Multi-Armed Bandits to optimize power levels in energy harvesting networks with limited feedback, enhancing energy efficiency.

Findings

The proposed UCB-based algorithm effectively learns optimal power levels.

Numerical results show significant gains over benchmark schemes.

The method adapts well without channel state information.

Abstract

We study wireless power transmission by an energy source to multiple energy harvesting nodes with the aim to maximize the energy efficiency. The source transmits energy to the nodes using one of the available power levels in each time slot and the nodes transmit information back to the energy source using the harvested energy. The source does not have any channel state information and it only knows whether a received codeword from a given node was successfully decoded or not. With this limited information, the source has to learn the optimal power level that maximizes the energy efficiency of the network. We model the problem as a stochastic Multi-Armed Bandits problem and develop an Upper Confidence Bound based algorithm, which learns the optimal transmit power of the energy source that maximizes the energy efficiency. Numerical results validate the performance guarantees of the proposed algorithm and show significant gains compared to the benchmark schemes.