PINN - Enabled Physical Parameter Identification for Accurate EDFA Gain Modeling
We experimentally demonstrate a PINN-enabled physical parameter identification workflow for EDFA gain modeling. A maximum gain error of 0.303dB and mean absolute error of 0.127dB are achieved with only five sets of data per wavelength.
Authors
- Yuchen Song (ORCID: https://orcid.org/0000-0001-9554-4964)
- Xiaotian Jiang (ORCID: https://orcid.org/0000-0002-2629-8728)
- Danshi Wang (ORCID: https://orcid.org/0000-0001-9815-4013)
- Min Zhang (ORCID: https://orcid.org/0000-0001-9313-6561)
- Jin Li (ORCID: https://orcid.org/0000-0002-0260-3169)
- Jiawei Dong (ORCID: https://orcid.org/0009-0003-6713-4185)
Institutions
- Beijing University of Posts and Telecommunications (CN)
- State Key Laboratory of Information Photonics and Optical Communications
Publication Details
- Published
- 2024-11-02
- DOI
- https://doi.org/10.1109/acp/ipoc63121.2024.10809921
- Primary Topic
- High voltage insulation and dielectric phenomena
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Beijing Nova Program