Channel Tracking for Wireless Energy Transfer: A Deep Recurrent Neural Network Approach

TL;DR

This paper introduces a deep LSTM RNN-based method for tracking time-varying channels in wireless energy transfer systems, improving the accuracy of channel state information estimation.

Contribution

It proposes a novel deep RNN scheme combining LSTM and feedforward networks for effective channel tracking in WET systems, leveraging energy feedback.

Findings

Superior performance over existing methods

Effective in dynamic channel conditions

Accurate CSI estimation based on energy feedback

Abstract

In this paper, we study channel tracking for the wireless energy transfer (WET) system, which is practically a very important, but challenging problem. Regarding the time-varying channels as a sequence to be predicted, we exploit the recurrent neural network (RNN) technique for channel tracking. Particularly, combining the deep long short-term memory (LSTM) RNN with the deep feedforward neural network, we develop a novel channel tracking scheme for the WET system, which estimates the channel state information (CSI) at the energy transmitter based on the previous CSI estimates, and the current and previous harvested energy feedback information from the energy receiver. Numerical results demonstrate the superior performance and effectiveness of the proposed scheme.