Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer

Lida Kouhalvandi; Sercan Aygun; Serdar Ozoguz; Ladislau Matekovits; M. Hassan Najafi; Saeid Karamzadeh

doi:10.1109/SMACD65553.2025.11091948

Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer

Lida Kouhalvandi^*, Sercan Aygun, Serdar Ozoguz, Ladislau Matekovits, M. Hassan Najafi, Saeid Karamzadeh

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This work is devoted to presenting an intelligent-based methodology leading to model characteristics of power amplifiers (PAs) as well as sizing through the deep neural network (DNN). The long short-term memory (LSTM) architecture is employed to predict the extended frequency responses and achieve optimal hyperparameters of DNN for accurately sizing the PA. The PA is modeled in terms of scattering parameters, output power, power gain, and efficiency, in which nature-inspired optimization algorithms are executed to determine the optimal numbers of hidden layers with neurons of LSTM-based DNN. The proposed method leads to the construction of a reliable network for predicting the future specifications of any PA with design automation and acceptable convergence. To verify the effectiveness of the proposed method, a PA with 1.4 GHz is optimized, and the simulation outcomes prove that the multi-verse optimizer is strong enough to determine optimal hyperparameters of DNN.

Original language	English
Title of host publication	21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331523954
DOIs	https://doi.org/10.1109/SMACD65553.2025.11091948
Publication status	Published - 2025
Event	21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025 - Istanbul, Turkey Duration: 7 Jul 2025 → 10 Jul 2025

Publication series

Name	21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025

Conference

Conference	21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025
Country/Territory	Turkey
City	Istanbul
Period	7/07/25 → 10/07/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

Deep neural network (DNN)
estimation
hyper-parameter
long short-term memory (LSTM)
modeling
multi-verse optimizer (MVO)
nature-inspired optimization algorithms
power amplifier (PA)
sizing

Access to Document

10.1109/SMACD65553.2025.11091948

Cite this

Kouhalvandi, L., Aygun, S., Ozoguz, S., Matekovits, L., Najafi, M. H., & Karamzadeh, S. (2025). Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer. In 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025 (21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMACD65553.2025.11091948

Kouhalvandi, Lida ; Aygun, Sercan ; Ozoguz, Serdar et al. / Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer. 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025).

@inproceedings{0091e2e703774c0bbeeb2437a5f158d2,

title = "Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer",

abstract = "This work is devoted to presenting an intelligent-based methodology leading to model characteristics of power amplifiers (PAs) as well as sizing through the deep neural network (DNN). The long short-term memory (LSTM) architecture is employed to predict the extended frequency responses and achieve optimal hyperparameters of DNN for accurately sizing the PA. The PA is modeled in terms of scattering parameters, output power, power gain, and efficiency, in which nature-inspired optimization algorithms are executed to determine the optimal numbers of hidden layers with neurons of LSTM-based DNN. The proposed method leads to the construction of a reliable network for predicting the future specifications of any PA with design automation and acceptable convergence. To verify the effectiveness of the proposed method, a PA with 1.4 GHz is optimized, and the simulation outcomes prove that the multi-verse optimizer is strong enough to determine optimal hyperparameters of DNN.",

keywords = "Deep neural network (DNN), estimation, hyper-parameter, long short-term memory (LSTM), modeling, multi-verse optimizer (MVO), nature-inspired optimization algorithms, power amplifier (PA), sizing",

author = "Lida Kouhalvandi and Sercan Aygun and Serdar Ozoguz and Ladislau Matekovits and Najafi, \{M. Hassan\} and Saeid Karamzadeh",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025 ; Conference date: 07-07-2025 Through 10-07-2025",

year = "2025",

doi = "10.1109/SMACD65553.2025.11091948",

language = "English",

series = "21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025",

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

booktitle = "21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025",

address = "United States",

}

Kouhalvandi, L, Aygun, S, Ozoguz, S, Matekovits, L, Najafi, MH & Karamzadeh, S 2025, Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer. in 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025. 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025, Institute of Electrical and Electronics Engineers Inc., 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025, Istanbul, Turkey, 7/07/25. https://doi.org/10.1109/SMACD65553.2025.11091948

Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer. / Kouhalvandi, Lida; Aygun, Sercan; Ozoguz, Serdar et al.
21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer

AU - Kouhalvandi, Lida

AU - Aygun, Sercan

AU - Ozoguz, Serdar

AU - Matekovits, Ladislau

AU - Najafi, M. Hassan

AU - Karamzadeh, Saeid

PY - 2025

Y1 - 2025

N2 - This work is devoted to presenting an intelligent-based methodology leading to model characteristics of power amplifiers (PAs) as well as sizing through the deep neural network (DNN). The long short-term memory (LSTM) architecture is employed to predict the extended frequency responses and achieve optimal hyperparameters of DNN for accurately sizing the PA. The PA is modeled in terms of scattering parameters, output power, power gain, and efficiency, in which nature-inspired optimization algorithms are executed to determine the optimal numbers of hidden layers with neurons of LSTM-based DNN. The proposed method leads to the construction of a reliable network for predicting the future specifications of any PA with design automation and acceptable convergence. To verify the effectiveness of the proposed method, a PA with 1.4 GHz is optimized, and the simulation outcomes prove that the multi-verse optimizer is strong enough to determine optimal hyperparameters of DNN.

AB - This work is devoted to presenting an intelligent-based methodology leading to model characteristics of power amplifiers (PAs) as well as sizing through the deep neural network (DNN). The long short-term memory (LSTM) architecture is employed to predict the extended frequency responses and achieve optimal hyperparameters of DNN for accurately sizing the PA. The PA is modeled in terms of scattering parameters, output power, power gain, and efficiency, in which nature-inspired optimization algorithms are executed to determine the optimal numbers of hidden layers with neurons of LSTM-based DNN. The proposed method leads to the construction of a reliable network for predicting the future specifications of any PA with design automation and acceptable convergence. To verify the effectiveness of the proposed method, a PA with 1.4 GHz is optimized, and the simulation outcomes prove that the multi-verse optimizer is strong enough to determine optimal hyperparameters of DNN.

KW - Deep neural network (DNN)

KW - estimation

KW - hyper-parameter

KW - long short-term memory (LSTM)

KW - modeling

KW - multi-verse optimizer (MVO)

KW - nature-inspired optimization algorithms

KW - power amplifier (PA)

KW - sizing

UR - https://www.scopus.com/pages/publications/105013463248

U2 - 10.1109/SMACD65553.2025.11091948

DO - 10.1109/SMACD65553.2025.11091948

M3 - Conference contribution

AN - SCOPUS:105013463248

T3 - 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025

BT - 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025

Y2 - 7 July 2025 through 10 July 2025

ER -

Kouhalvandi L, Aygun S, Ozoguz S, Matekovits L, Najafi MH, Karamzadeh S. Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer. In 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025. Institute of Electrical and Electronics Engineers Inc. 2025. (21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design, SMACD 2025). doi: 10.1109/SMACD65553.2025.11091948

Power Amplifier Modeling along with Hyperparameter Optimization of LSTM-based DNN through Multi-Verse Optimizer

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this