Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior

Taoning Zhan; Shanpu Shen; Danny H.K. Tsang

doi:10.1109/WPTCE62521.2025.11062091

Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior

Taoning Zhan^*, Shanpu Shen, Danny H.K. Tsang^*

^*Corresponding author for this work

Department of Electronic and Computer Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

Abstract

The nonlinear behavior of rectenna is a critical bottleneck restricting the efficiency of wireless power transfer. Most existing works utilize a nonlinear model derived from analyzing the I-V characteristics of diodes and taking a Taylor expansion. In this paper, we employ two advanced machine learning models, LASSO regularized Polynomial Regression (LASSO-PR) and Segmented Polynomial Regression (S-PR), to derive a more precise and adaptive nonlinear model. Besides, we design a single-diode rectenna in ADS to compare the accuracy of these models. The training results demonstrate that the existing nonlinear model is only suitable for small input power levels, whereas the S-PR based model can accurately characterizes the nonlinear behavior across the entire input power range, reducing the output dc voltage prediction error by 82%.

Original language	English
Title of host publication	2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331517434
DOIs	https://doi.org/10.1109/WPTCE62521.2025.11062091
Publication status	Published - 2025
Event	2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Rome, Italy Duration: 3 Jun 2025 → 6 Jun 2025

Publication series

Name	2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings

Conference

Conference	2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025
Country/Territory	Italy
City	Rome
Period	3/06/25 → 6/06/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

Machine learning
Schottky diodes
nonlinear rectenna model
rectenna design
wireless power transfer

Access to Document

10.1109/WPTCE62521.2025.11062091

Cite this

Zhan, T., Shen, S., & Tsang, D. H. K. (2025). Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior. In 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings (2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WPTCE62521.2025.11062091

@inproceedings{9602681639bc498783b388f299a0a5ff,

title = "Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior",

abstract = "The nonlinear behavior of rectenna is a critical bottleneck restricting the efficiency of wireless power transfer. Most existing works utilize a nonlinear model derived from analyzing the I-V characteristics of diodes and taking a Taylor expansion. In this paper, we employ two advanced machine learning models, LASSO regularized Polynomial Regression (LASSO-PR) and Segmented Polynomial Regression (S-PR), to derive a more precise and adaptive nonlinear model. Besides, we design a single-diode rectenna in ADS to compare the accuracy of these models. The training results demonstrate that the existing nonlinear model is only suitable for small input power levels, whereas the S-PR based model can accurately characterizes the nonlinear behavior across the entire input power range, reducing the output dc voltage prediction error by 82\%.",

keywords = "Machine learning, Schottky diodes, nonlinear rectenna model, rectenna design, wireless power transfer",

author = "Taoning Zhan and Shanpu Shen and Tsang, \{Danny H.K.\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 ; Conference date: 03-06-2025 Through 06-06-2025",

year = "2025",

doi = "10.1109/WPTCE62521.2025.11062091",

language = "English",

series = "2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings",

}

Zhan, T, Shen, S & Tsang, DHK 2025, Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior. in 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings. 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025, Rome, Italy, 3/06/25. https://doi.org/10.1109/WPTCE62521.2025.11062091

Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior. / Zhan, Taoning; Shen, Shanpu; Tsang, Danny H.K.
2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. (2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior

AU - Zhan, Taoning

AU - Shen, Shanpu

AU - Tsang, Danny H.K.

PY - 2025

Y1 - 2025

N2 - The nonlinear behavior of rectenna is a critical bottleneck restricting the efficiency of wireless power transfer. Most existing works utilize a nonlinear model derived from analyzing the I-V characteristics of diodes and taking a Taylor expansion. In this paper, we employ two advanced machine learning models, LASSO regularized Polynomial Regression (LASSO-PR) and Segmented Polynomial Regression (S-PR), to derive a more precise and adaptive nonlinear model. Besides, we design a single-diode rectenna in ADS to compare the accuracy of these models. The training results demonstrate that the existing nonlinear model is only suitable for small input power levels, whereas the S-PR based model can accurately characterizes the nonlinear behavior across the entire input power range, reducing the output dc voltage prediction error by 82%.

AB - The nonlinear behavior of rectenna is a critical bottleneck restricting the efficiency of wireless power transfer. Most existing works utilize a nonlinear model derived from analyzing the I-V characteristics of diodes and taking a Taylor expansion. In this paper, we employ two advanced machine learning models, LASSO regularized Polynomial Regression (LASSO-PR) and Segmented Polynomial Regression (S-PR), to derive a more precise and adaptive nonlinear model. Besides, we design a single-diode rectenna in ADS to compare the accuracy of these models. The training results demonstrate that the existing nonlinear model is only suitable for small input power levels, whereas the S-PR based model can accurately characterizes the nonlinear behavior across the entire input power range, reducing the output dc voltage prediction error by 82%.

KW - Machine learning

KW - Schottky diodes

KW - nonlinear rectenna model

KW - rectenna design

KW - wireless power transfer

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001545112700004

UR - https://openalex.org/W4412082306

UR - https://www.scopus.com/pages/publications/105011500130

U2 - 10.1109/WPTCE62521.2025.11062091

DO - 10.1109/WPTCE62521.2025.11062091

M3 - Conference Paper published in a book

AN - SCOPUS:105011500130

T3 - 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings

BT - 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE Wireless Power Technology Conference and Expo, WPTCE 2025

Y2 - 3 June 2025 through 6 June 2025

ER -

Machine Learning Based Accurate Modeling of Rectenna Nonlinear Behavior

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this