Passer à la navigation principale Passer à la recherche Passer au contenu principal

A Bandwidth-Aware Figure of Merit for Behavioral Modeling of Power Amplifiers

  • Institut Polytechnique de Paris
  • Nxp Toulouse

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

This paper introduces a bandwidth-aware figure of merit (FoM) that unifies four dimensions of model performance: average accuracy, prediction stability, bandwidth sensitivity, and model complexity. The FoM is formulated as a weighted sum of normalized indicators, enabling fair comparisons across both polynomial and neural-network-based models. A case study on measured 5G NR signals, spanning 10 bandwidths from 20 to 100 MHz, demonstrates the utility of the proposed FoM. Results show that the NARX neural network (NARXNN) achieves consistently better FoM scores than the generalized memory polynomial (GMP) and other neural baselines, reflecting superior robustness and efficiency under bandwidth scaling. Beyond bandwidth generalization, the framework is extensible to other dynamic conditions such as power scaling and carrier aggregation, making it a versatile benchmark for future RF modeling research.

langue originaleAnglais
titre2026 IEEE 17th Latin American Symposium on Circuits and Systems, LASCAS 2026 - Proceedings
EditeurInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronique)9798331570972
Les DOIs
étatPublié - 1 janv. 2026
Evénement17th Latin American Symposium on Circuits and Systems, LASCAS 2026 - Arequipa, Pérou
Durée: 24 févr. 202627 févr. 2026

Série de publications

Nom2026 IEEE 17th Latin American Symposium on Circuits and Systems, LASCAS 2026 - Proceedings

Une conférence

Une conférence17th Latin American Symposium on Circuits and Systems, LASCAS 2026
Pays/TerritoirePérou
La villeArequipa
période24/02/2627/02/26

Empreinte digitale

Examiner les sujets de recherche de « A Bandwidth-Aware Figure of Merit for Behavioral Modeling of Power Amplifiers ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation