Ergodic Capacity Estimation and Performance Analysis with Deep Learning Methods in NOMA-based Cognitive Radio Systems

Abstract

In this study, using the cognitive radio (CR)-based non-orthogonal multiple access (NOMA) technique, the total ergodic capacity value of the close user is estimated with high accuracy and fast training times through different training algorithms with the proposed feedforward backpropagation artificial neural network (ANN) and nonlinear autoregressive network with exogenous inputs (NARX) model. The data set used in the neural network was obtained from the CR-NOMA system model, which was modeled with the exponential fading channel characteristic. By training the input and output data to the ANN, which was designed using the supervised learning method, ergodic capacity estimates of the close user were made over the test data. While evaluating the performance of ANN and NARX neural networks, the training time, the number of iterations, and the conditions of the network not reaching saturation were taken into consideration. The actual ergodic capacity value of the close user and the predicted values of feedforward backpropagation ANN and NARX networks were compared. The performance analysis of the proposed neural networks under Levenberg-Marquardt, Bayesian and Scaled-Conjugate training algorithms has been examined in terms of epoch value graph, error histogram analysis, and training state analysis where the error reaches the minimum.

Keywords

• Bayesian
• Cognitive radio
• Levenberg-Marquardt
• NARX
• NOMA
• Artificial neural networks

NOMA TABANLI BİLİŞSEL RADYO SİSTEMLERİNDE SİNİR AĞI YÖNTEMLERİ İLE ERGODİK KAPASİTE TAHMİNİ VE BAŞARIM ANALİZİ

Abstract

Bu çalışmada, bilişsel radyo (BR) tabanlı dikgen olmayan çoklu erişim tekniği (NOMA) kullanılarak, yakın kullanıcıya ait toplam ergodik kapasite değerinin, önerilen ileri beslemeli geri yayılımlı yapay sinir ağı (YSA) ve doğrusal olmayan dışsal girdili otoregresif ağ (Nonlinear Autoregressive Network with Exogenous Inputs, NARX) modeli ile farklı eğitim algoritmaları yoluyla yüksek doğruluk oranında ve hızlı eğitim sürelerinde tahmin edilmesi amaçlanmıştır. Sinir ağında kullanılan veri seti, üstel sönümleme kanalı karakteristiği ile modellenen BR-NOMA sistem modelinden elde edilmiştir. Denetimli öğrenme yöntemi kullanılarak tasarlanan YSA’ya girdi ve çıktı verileri öğretilerek yakın kullanıcıya ait ergodik kapasite tahmini yapılmıştır. YSA ve NARX sinir ağları başarımı değerlendirilirken eğitim süresi, iterasyon sayısı, ağın doygunluğa ulaşmaması durumları göz önünde bulundurulmuştur. Yakın kullanıcıya ait gerçek ergodik kapasite değeri ile ileri beslemeli geri yayılımlı YSA ve NARX ağlarının tahmin etmiş olduğu değerler karşılaştırılmıştır. Önerilen sinir ağlarının Levenberg-Marquardt, Bayesian ve Scaled-Conjugate eğitim algoritmaları altındaki performans analizi, hatanın minimuma ulaştığı epok değer grafiği, hata histogram analizi ve eğitim durum analizi açılarından incelenmiştir.

Keywords

• Bayesian
• Bilişsel radyo
• Levenberg-Marquardt
• NARX
• NOMA
• Yapay sinir ağları

References

1. 1. Bardak, F. K. Namdar, M. and Basgumus A. (2021) Ergodic Capacity Analysis of the Relay Assisted Downlink NOMA Systems in Cognitive Radio Networks, Journal of Engineering Sciences and Design, 9(3), 992-1002, doi:10.21923/jesd.826084
2. 2. Bardak, F.K., Namdar, M., ve Basgumus, A. (2020) Performance analysis of noma systems in relay-assisted cognitive radio networks, 28th Signal Processing and Comm. Applications Conference (SIU), Medipol Üniversitesi, İstanbul, doi:10.1109/SIU49456.2020.9302392
3. 3. Bhatt, A., vd. (2022) Analysis of the Fifth Generation NOMA System using LSTM Algorithm, Int. J. of Comp. and Digital Sys., 11(1), 1367-1376, doi:10.12785/ijcds/120119
4. 4. Boussaada, Z., Curea, O., Ahmed, R., Najiba, M.B. (2018) A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation, Energies, 11(3), 620, doi:/10.3390/en11030620
5. 5. Dai, L., vd. (2018) A Survey of Non-Orthogonal Multiple Access for 5G, IEEE Comm. Surveys & Tutorials, 20(3), 2294-2323, doi:10.1109/COMST.2018.2835558
6. 6. Emir, A., Kara, F., ve Kaya H. (2022) CNN Aided Alternative Detector Design for Uplink and Downlink NOMA Communications Systems, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 70(24), 341-349, doi:/10.21205/deufmd.2022247030
7. 7. Gradshteyn, I. S., ve Ryzhik I. M. (2007) Table of integrals, series and products, 7th edn., Academic Press, New York.
8. 8. Gui, G., vd. (2018) Deep Learning for An Effective Non-Orthogonal Multiple Access Scheme, IEEE Trans. on Veh. Tech., 67(9), 8440-8450, doi:10.1109/TVT.2018.2848294

9. 9. Lin, C., Chang, Q., ve Li, X. (2019) A Deep Learning Approach for MIMO-NOMA Downlink Signal Detection, Sensors Journal, 19(11), 2526, doi:10.3390/s19112526
10. 10. Liu, M., Song, T., ve Gui, G. (2018) Deep Cognitive Perspective: Resource Allocation for NOMA based Heterogeneous IoT with Imperfect SIC, IEEE, Internet of Things Journal, 6(2), 2885-2894, doi:10.1109/JIOT.2018.2876152
11. 11. Naeem, M., Rizvi, S.T.H., ve Coronato, A. (2020) A Gentle Introduction to Reinforcement Learning and its Application in Different Fields, IEEE Access, 8(0), 209320–209344, doi:10.1109/ACCESS.2020.3038605
12. 12. Namdar, M., and Basgumus, A. (2017) Outage Performance Analysis of Underlay Cognitive Radio Networks with Decode‐and‐Forward Relaying, in Cognitive Radio, London, United Kingdom: IntechOpen, ISBN: 978-953-51-3338-4, 25-37, doi:10.5772/intechopen.69244
13. 13. Namdar, M., and Ilhan, H. (2018) Exact Closed-Form Solution for Detection Probability in Cognitive Radio Networks with Switch-and-Examine Combining Diversity, IEEE Transactions on Vehicular Technology, 67(9), 8215-8222, doi:10.1109/TVT.2018.2840227
14. 14. Narengerile, ve Thompson, J. (2019) Deep learning for signal detection in non-orthogonal multiple access wireless systems, UK/ China Emerging Technologies (UCET), (1-4). Glasgow, UK, doi:10.1109/UCET.2019.8881888
15. 15. Sendonaris, A., Erkip, E., ve Aazhang, B. (1998) Increasing uplink capacity via user cooperation diversity. IEEE Int. Symposium on Information Theory, (156), Cambridge, MA, United States, doi:10.1109/ISIT.1998.708750
16. 16. Seyman, M.N. (2022) Symbol Detection Based on Back Tracking Search Algorithm in MIMO-NOMA Systems, Computer Systems Science and Engineering, 40(2), 795-804, doi:10.32604/csse.2022.019734
17. 17. Seyman, M.N., ve Taspinar, N. (2013) Radial Basis Function Neural Networks for Channel Estimation in MIMO-OFDM Systems, Arabian Journal for Science and Engineering, 38(8), 2173-2178, doi:10.1007/s13369-013-0586-1
18. 18. Sim, I., vd. (2020) Deep Learning Based Successive Interference Cancellation Scheme in Non Orthogonal Multiple Access Downlink Network, Energies Journal, 13(23), 6237, doi:10.3390/en13236237
19. 19. Tatlı, A. and Kahvecioğlu S. (2017) Amount of Airworthiness Time Estimation Using TDNN Model in Time Series, IATS2017: 8th Int. Advanced Technologies Symposium.