Sayısal Sembollerde Anlık SNR Kestirimi

Öz

Sinyal-gürültü oranı, birçok haberleşme sisteminin verimli çalışabilmesi için bilinmesi gereken çok önemli bir değerdir. Bu değerin belirlenmesi, kullanılan yönteme bağlı olarak ekstra maliyete, karmaşıklığa veya kaynak tahsisinin verimliliğinde düşüşe neden olabilir. Makine öğrenimi yöntemleri, denetimli öğrenme ve çevrimdışı eğitim ile bu olumsuz yönleri ortadan kaldırırken pratik çözüm yolları sunarlar. Derin öğrenme, bir tür makine öğrenimi olarak başarısıyla öne çıkmaktadır. Bu çalışmada, dijital sembollerdeki sinyal-gürültü oranının anlık değerinin tahminin derin öğrenme tekniği kullanılarak yapılması incelenmiştir.

Anahtar Kelimeler

• Haberleşme
• Derin Öğrenme
• Kestirim
• Makine Öğrenimi

Instant SNR Estimation on Digital Symbols

Abstract

Signal-to-noise ratio is a very important data that must be known in order for many communication systems to work efficiently. The determination of this value may cause extra cost, complexity or can cause a decrease in the efficiency of resource allocation depending on the method used. The machine learning methods offer a practical solution while eliminating these negative aspects with supervised learning and offline training. Deep learning stands out with its success as a type of machine learning. In this study, the estimation of the instantaneous value of the signal to noise ratio in digital symbols was investigated using the deep learning technique.

Keywords

• Communication
• Deep Learning
• Estimation
• Machine Learning

References

1. Abeida, H. (2010). Data-aided SNR estimation in time-variant Rayleigh fading channels. IEEE transactions on signal processing, 58(11), 5496–5507. IEEE.
2. Bogale, T. E., & Vandendorpe, L. (2014). Max-Min SNR signal energy based spectrum sensing algorithms for cognitive radio networks with noise variance uncertainty. IEEE transactions on wireless communications, 13(1), 280–290. IEEE.
3. Challita, U., Dong, L., & Saad, W. (2018). Proactive resource management for LTE in unlicensed spectrum: A deep learning perspective. IEEE transactions on wireless communications, 17(7), 4674–4689. IEEE.
4. Daniels, R. C., & Heath, R. W. (2009). An online learning framework for link adaptation in wireless networks. 2009 Information Theory and Applications Workshop (pp. 138–140). IEEE.
5. Farsad, N., & Goldsmith, A. (2018). Neural network detection of data sequences in communication systems. IEEE Transactions on Signal Processing, 66(21), 5663–5678. IEEE.
6. Farsad, N., Rao, M., & Goldsmith, A. (2018). Deep learning for joint source-channel coding of text. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2326–2330). IEEE.
7. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
8. Gruber, T., Cammerer, S., Hoydis, J., & Brink, S. ten. (2017). On deep learning-based channel decoding. 2017 51st Annual Conference on Information Sciences and Systems (CISS) (pp. 1–6). IEEE.

9. He, H., Wen, C.-K., Jin, S., & Li, G. Y. (2018). Deep learning-based channel estimation for beamspace mmWave massive MIMO systems. IEEE Wireless Communications Letters, 7(5), 852–855. IEEE.
10. Nachmani, E., Marciano, E., Lugosch, L., Gross, W. J., Burshtein, D., & Be’ery, Y. (2018). Deep learning methods for improved decoding of linear codes. IEEE Journal of Selected Topics in Signal Processing, 12(1), 119–131. IEEE.
11. Nandakumar, S., Velmurugan, T., Thiagarajan, U., Karuppiah, M., Hassan, M. M., Alelaiwi, A., & Islam, M. M. (2019). Efficient Spectrum management techniques for cognitive radio networks for proximity service. IEEE Access, 7, 43795–43805. IEEE.
12. Rasouli, H., & Anpalagan, A. (2010). SNR-based vs. BER-based power allocation for an amplify-and-forward single-relay wireless system with MRC at destination. 2010 25th Biennial Symposium on Communications (pp. 429–432). IEEE.
13. Salman, T., Badawy, A., Elfouly, T. M., Khattab, T., & Mohamed, A. (2014). Non-data-aided SNR estimation for QPSK modulation in AWGN channel. 2014 IEEE 10th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) (pp. 611–616). IEEE.
14. Samuel, N., Diskin, T., & Wiesel, A. (2019). Learning to detect. IEEE Transactions on Signal Processing, 67(10), 2554–2564. IEEE.
15. Santos Filho, J. C. S., González, D. C., Wolf, A., Mendes, L. L., Yacoub, M. D., & Fettweis, G. (2018). SNR-Aware Power Allocation Scheme for Lossy-Forward Relaying Systems. IEEE Wireless Communications Letters, 7(6), 1018–1021. IEEE.
16. Sun, H., Chen, X., Shi, Q., Hong, M., Fu, X., & Sidiropoulos, N. D. (2018). Learning to optimize: Training deep neural networks for interference management. IEEE Transactions on Signal Processing, 66(20), 5438–5453. IEEE.
17. Thilina, K. M., Choi, K. W., Saquib, N., & Hossain, E. (2013). Machine learning techniques for cooperative spectrum sensing in cognitive radio networks. IEEE Journal on selected areas in communications, 31(11), 2209–2221. IEEE.
18. Va, V., Choi, J., Shimizu, T., Bansal, G., & Heath, R. W. (2017). Inverse multipath fingerprinting for millimeter wave V2I beam alignment. IEEE Transactions on Vehicular Technology, 67(5), 4042–4058. IEEE.