Aşağı ve Yukarı Yönlü NOMA Haberleşme Sistemleri için CNN Yardımlı Alternatif Sezici Tasarımı

Abstract

Haberleşme sistemlerinde kanal sönümlemelerine karşı işareti iletmek ve alıcıda almak için fiziksel seviyede geliştirilen yöntemler işlem karmaşıklığına sebep olmaktadır. Son yıllarda işlem karmaşıklığını azaltmak için alternatif olarak Derin öğrenme (deep learning-DL) ağlarına başvurulmaktadır. Gelecek nesil haberleşme sistemleri için öncü olacağı düşünülen dikgen olmayan çoklu erişim (non-orthogonal multiple access-NOMA) kullanıcıları aynı kaynak bloğunda güç ekseninde paylaştırarak yüksek spektral verim sağlar. Fakat sinyal sezimi için kullanılan ardışık girişim engelleyici (successive interference cancellation-SIC) işlem karmaşıklığına sebep olmaktadır. Bu çalışmada aşağı yönlü (downlink) ve yukarı yönlü (uplink) NOMA haberleşme sistemlerinde alıcıya ulaşan işaretin alternatif olarak DL ile sezimi amaçlanmıştır. DL ağı olarak evrişimli sinir ağı (convolutional neural network-CNN) kullanılmıştır. CNN yardımlı sezici ve maksimum olabilirlikli (maximum likehood-ML)-SIC sezicisi hata başarımları karşılaştırılmıştır. Aşağı ve yukarı yönlü NOMA haberleşme sistemlerinde yakın ve uzak kullanıcı bitlerinin CNN ağıyla ortak kestirilebilmesi ve bazı durumlarda bit hata oranı grafiklerinin DL sezicilerde SIC-ML sezicilerden daha iyi bulunması önemli bir avantajdır. Ayrıca NOMA sistemlerinde CNN ağının sezici olarak kullanılabilmesi, sınıflandırıcıların kablosuz haberleşme sistemlerinde gücünü ortaya koymaktadır.

Keywords

• CNN
• DL
• ML
• BPSK
• Ortak Kestirim

CNN Aided Alternative Detector Design for Uplink and Downlink NOMA Communications Systems

Abstract

Methods implemented at the physical level in order to transmit and receive signals at the receiver against channel fading in communication systems cause processing complexity. In recent years, Deep learning (DL) networks have been used as an alternative to reduce processing complexity. Non-orthogonal multiple access (NOMA) which has been to be a pioneer for future generation, provides high spectral efficiency by sharing users on the power axis in the same source block. However, successive interference cancellation (SIC) used for signal detection causes processing complexity. In this study, it is proposed to detect the received signal with DL as an alternative method in downlink and non-orthogonal multiple access (NOMA) communication systems. Convolutional neural network (CNN) is used as DL network. The error performance of CNN aided detector and SIC- ML (maximum likehood )based detector has been compared. In downlink and uplink NOMA communication systems, it is an important advantage that the near and far user bits can be estimated jointly with the CNN network and in some cases the bit error rate curves are better in DL detectors than SIC-ML detectors. In addition, the ability using the CNN network as a detector in NOMA systems reveals the power of classifiers in wireless communication systems.

Keywords

• BPSK
• CNN
• DL
• Error Performance
• Signal Matrix
• ML
• Joint Detection
• SIC

References

1. Xuan, Z and Narayanan, K. 2020. Analog Joint Source-Channel Coding for Gaussian Sources over AWGN Channels with Deep Learning. International Conference on Signal Processing and Communication,19-24 July, Bangolere, India.
2. Kim, M., Kim, N., Lee, W. and Cho, D. 2018. Deep Learning-Aided SCMA, IEEE Communications Letters, vol. 22, no. 4, pp. 720-723. doi: 10.1109/LCOMM.2018.2792019.
3. Ye, H., Li, G. Y. and Juang ,B. 2018. Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems, IEEE Wireless Communications Letters, vol. 7, no. 1, pp. 114-117.doi: 10.1109/LWC.2017.2757490
4. Ye, H., Liang, K., Li, G. Y. and Juang, B. 2020. Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels, IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3133-3143. doi: 10.1109/TWC.2020.2970707.
5. Benjebbour, A., Saito, Y., Kishiyama,Y., Li, A., Harada , A. and Nakamura, T. 2013. Concept and practical considerations of non-orthogonal multiple access (NOMA) for future radio access. International Symposium on Intelligent Signal Processing and Communication Systems, 12- 15 Nov., Naha,Japan 770-774.
6. Benjebbour, A., Li, A., Kishiyama, Y., Jiang, H. and Nakamura, T., 2014. System-level performance of downlink NOMA combined with SU-MIMO for future LTE enhancements,IEEE Globecom Workshops (GC Wkshps),8-12 Decemver, Austin,USA, pp. 706-710.
7. Emir, A., Kara, F., Kaya, H. and Yanikomeroglu, H. 2021. DeepMuD: Multi-User Detection for Uplink Grant-Free NOMA IoT Networks via Deep Learning,IEEE Wireless Communications Letters, vol. 10, no. 5, pp. 1133-1137. doi: 10.1109/LWC.2021.3060772.
8. Emir, A., Kara, F., Kaya, H. and Yanikomeroglu, H. 2021. Deep Learning Empowered Semi-Blind Joint Detection in Cooperative NOMA, IEEE Access, vol. 9, 61832-6185. doi: 10.1109/ACCESS.2021.3074350.

9. Narengerile and Thompson, J. 2019. Deep Learning for Signal Detection in Non-Orthogonal Multiple Access Wireless System.UK/ China Emerging Technologies(UCET), 21-22 August, Glasgow, UK, 1-4.
10. Emir, A., Kara, F., Kaya, H. and Li, X. 2021. Deep learning-based flexible joint channel estimation and signal detection of multi-user OFDM-NOMA, Physical Communication, Elsevier, vol. 48. doi: 10.1016/j.phycom.2021.101443.
11. Zhang, N., Cheng, K. and Kang, K. 2018. A Machine-Learning-Based Blind Detection on Interference Modulation Order in NOMA Systems, IEEE Communications Letters, vol. 22, no. 12, pp. 2463-2466. doi: 10.1109/LCOMM.2018.2874218.
12. Lin, C., Chang, Q. and Li, X. 2019. A Deep Learning Approach for MIMO-NOMA Downlink Signal Detection, Sensors, ,vol.19, no.11, pp 1-22. doi: 10.3390/s19112526.
13. Liu, M., Song, T. and Gui ,G. 2019. Deep Cognitive Perspective: Resource Allocation for NOMA-Based Heterogeneous IoT With Imperfect SIC, IEEE Internet of Things Journal, vol. 6, no. 2, pp. 2885-2894. doi: 10.1109/JIOT.2018.2876152.
14. AbdelMoniem, M., Gasser, S. M., El-Mahallawy, M. S., Fakhr, M. W. and Soliman, A.. 2019. Enhanced NOMA system using adaptive coding and modulation based on LSTM neural network channel estimation,. Applied Sciences (Switzerland), vol. 9, No 15,pp.3022. doi: doi.org/10.3390/app9153022.
15. Luong, T. V., Ko, Y., Vien, N. A., Nguyen, D. H. N. and Matthaiou, M. 2019. Deep Learning-Based Detector for OFDM-IM, IEEE Wireless Communications Letters, vol. 8, no. 4, pp. 1159-1162. doi: 10.1109/LWC.2019.2909893.
16. Huang, H., Song,Y., Yang,J., Gui, G. and Adachi, F. 2019. Deep-Learning-Based Millimeter-Wave Massive MIMO for Hybrid Precoding, IEEE Transactions on Vehicular Technology, vol. 68, no. 3, pp. 3027-3032. doi: 10.1109/TVT.2019.2893928.
17. Lee, H., Lee, S. H. and Quek, T. Q. S. 2019. Deep Learning for Distributed Optimization: Applications to Wireless Resource Management, IEEE Journal on Selected Areas in Communications, vol. 37, no. 10, pp. 2251-2266. doi: 10.1109/JSAC.2019.2933890
18. Tang, F., Zhou Y. and Kato N. 2020. Deep Reinforcement Learning for Dynamic Uplink/Downlink Resource Allocation in High Mobility 5G HetNet, IEEE Journal on Selected Areas in Communications, vol. 38, no. 12, pp. 2773-2782. doi: 10.1109/JSAC.2020.3005495.
19. Kim, N, Kim, D., Shim, B. and Lee, K. B. 2021. Deep Learning-Based Spreading Sequence Design and Active User Detection for Massive Machine-Type Communications, IEEE Wireless Communications Letters, vol. 10, no. 8, pp. 1618-1622. doi: 10.1109/LWC.2021.3071453.
20. Yang, Y., Gao, F., Zhong, Z., Ai, B. and Alkhateeb, A. 2020. Deep Transfer Learning-Based Downlink Channel Prediction for FDD Massive MIMO Systems, IEEE Transactions on Communications, vol. 68, no 12, pp. 7485-7497. doi: 10.1109/TCOMM.2020.3019077
21. Park, J., Ji, D. J. and Cho, D., H. 2021. High-Order Modulation Based on Deep Neural Network for Physical-Layer Network Coding, IEEE Wireless Communications Letters, vol. 10, no. 6, pp. 1173-1177. doi: 10.1109/LWC.2021.3060750.
22. Thrane, J., Zibar, D. and Christiansen, H. L. 2020. Model-Aided Deep Learning Method for Path Loss Prediction in Mobile Communication Systems at 2.6 GHz, IEEE Access, vol. 8, pp. 7925-7936. doi: 10.1109/ACCESS.2020.2964103.
23. Felix, A., Cammerer, S., Dörner, S., Hoydis, J. and Ten Brink, S. 2018. OFDM-Autoencoder for End-to-End Learning of Communications Systems. IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 25-28 June, Calamata, Greece, pp. 1,5.
24. Li, T., Liu, W., Zeng ,Z. and Xiong, N. N. 2021. DRLR: A Deep Reinforcement Learning based Recruitment Scheme for Massive Data Collections in 6G-based IoT networks, IEEE Internet of Things Journal(Early Acces). doi: 10.1109/JIOT.2021.3067904.
25. Yang, H., Xiong, Z., Zhao, J., Niyato, D., Xiao, L. and Wu, Q. 2021. Deep reinforcement learning-based intelligent reflecting surface for secure wireless communications, IEEE Transactions on Wireless Communications 20, 1, 375-388. doi: 10.1109/TWC.2020.3024860.
26. Yang, H., Alphones, A., Xiong, Z., Niyato, D., Zhao, J. and. Wu, K. 2020. Artificial-Intelligence-Enabled Intelligent 6G Networks, IEEE Network, vol. 34, no. 6, pp. 272-280. doi: 10.1109/MNET.011.2000195.
27. Keçeli, A., Kaya, A. 2019. Video Görüntülerinde Şiddet İçeren Aktivitelerin Lstm Ağı İle Tespiti, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi , Cilt 21, Sayı 63, s.933-939. doi: 10.21205/deufmd.2019216321.
28. Bozyiğit, F., Taşkın, A., Akar, K., Kılınç, D. 2021. A Deep Learning-Based Hotel Image Classifier for Online Travel Agencies, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi , Cilt 23, Sayı 67, s.257-264, doi: 10.21205/deufmd.2021236722
29. Cun Y. L., Jackel, L. D., Boser, B., Denker, J. S., Graf, H. P., Guyon, I., Henderson, D., Howard, R. E., Hubbard, W. 1989. Handwritten digit recognition: applications of neural network chips and automatic learning, IEEE Communications Magazine, vol. 27, no. 11, pp. 41-46.doi: 10.1109/35.41400