Graph neural networks improve wireless power and data transfer by adjusting antenna polarization
Polarforming-Enabled Power-Splitting SWIPT: A GNN-Based Optimization Approach
Information Theory
Summary
Keeping devices powered while sending data wirelessly is a tough problem for many smart gadgets. This paper shows how changing the way antennas send and receive signals, called polarization, can help. The authors use a type of artificial intelligence called graph neural networks to figure out the best antenna settings and how much power to split for charging and data. Their method works better than fixed settings, especially when the system has imperfect information about the wireless environment.
What this means in practice
- •For iot network engineers: Optimize antenna polarization and power use to improve simultaneous wireless charging and data transfer in complex IoT networks.
- •For wireless system designers: Develop robust communication systems that maintain performance despite imperfect wireless channel knowledge and polarization mismatches.
Authors
Hamed Aghaei-Karkaj, Kamran Ebrahimi, Zahra Mehrzad, Mohammad Robat Mili, Symeon Chatzinotas, Ioannis Krikidis
Abstract
Simultaneous wireless information and power transfer (SWIPT) is a critical technology for the future of the Internet of Things (IoT). However, ensuring a stable power supply in such networks remains a significant challenge. This work introduces dynamic polarization control as an additional degree of freedom (DoF) in SWIPT systems. We propose a system where both the base station (BS) and the users can adjust their antenna polarization, a technique known as polarforming. In addition, each user device is capable of splitting the incident signal to perform simultaneous information decoding (ID) and energy harvesting (EH). The resulting non-convex optimization, with many coupled variables, is solved using a graph neural network (GNN) that learns the sub-optimal beamforming, polarization, and power-splitting variables. Simulation results demonstrate that the proposed GNN-based dynamic polarforming optimization significantly outperforms fixed-polarization schemes, particularly under imperfect channel state information (CSI). Moreover, joint polarforming and GNN-based optimization maintain robust SWIPT performance under both polarization mismatch and imperfect CSI.