A mathematical PAPR estimation of OTFS network using a machine learning SVM algorithm
The article presents a Support Vector Machine (SVM) algorithm to lower the peak-to-average power ratio (PAPR) in networks that work in orthogonal time frequency space (OTFS). High PAPR makes power amplifiers less efficient and lowers signal quality. This makes OTFS modulation challenging, even thoug...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Results in Optics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666950125000628 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The article presents a Support Vector Machine (SVM) algorithm to lower the peak-to-average power ratio (PAPR) in networks that work in orthogonal time frequency space (OTFS). High PAPR makes power amplifiers less efficient and lowers signal quality. This makes OTFS modulation challenging, even though it is known for being strong in situations with a lot of movement. We present a mathematical framework that uses SVM, selective mapping (SLM), partial transmission sequence (PTS), and clipping and filtering (C&F) to estimate PAPR correctly, effectively lowering the PAPR while maintaining bit error rate (BER) performance. The proposed SVM method reduces the PAPR associated with conventional PAPR estimation techniques. The numerical results reveal that the proposed SVM obtained a signal-to-noise ratio (SNR) gain in the range of 1 dB–3 dB and retained the BER performance of the framework. This leads to better power control and overall better network performance. This paper demonstrates the potential of machine learning in optimizing OTFS networks, paving the way for more reliable and efficient radio systems. |
|---|---|
| ISSN: | 2666-9501 |